WO2025019628A1

WO2025019628A1 - Systems and methods for patella preparation for a knee arthroplasty procedure

Info

Publication number: WO2025019628A1
Application number: PCT/US2024/038464
Authority: WO
Inventors: William J. FUGIT; Paola Michelle JIMENEZ CARRION; Nathaniel M. Lenz; Ruxandra C. Marinescu Tanasoca
Original assignee: Smith and Nephew Orthopaedics AG; Smith and Nephew Asia Pacific Pte Ltd; Smith and Nephew Inc
Current assignee: Smith and Nephew Orthopaedics AG; Smith and Nephew Asia Pacific Pte Ltd; Smith and Nephew Inc
Priority date: 2023-07-20
Filing date: 2024-07-18
Publication date: 2025-01-23
Anticipated expiration: 2026-01-20

Abstract

Disclosed herein are systems and methods for planning a knee arthroplasty procedure. A patella evaluation method may include determining patient-specific patella information and registration of patient anatomy, including specific registration of the patella; anatomy modelling based on the registration; simulation of patient surgery and post-operative knee performance. The simulation results based on the patient patella information may be used to generate a patella classification defining whether preparation of a patient patella is optimal and, if so, the parameters of the patella preparation. The patella evaluation method may use a computational model to generate the patella classification. The patella evaluation method may determine patella preparation information, knee implant components and/or the configuration thereof within the patient based on the patient patella classification.

Description

SYSTEMS AND METHODS FOR PATELLA PREPARATION FOR A KNEE ARTHROPLASTY PROCEDURE

CROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/527,918, filed July 20, 2023, and titled “Systems and Methods for Patella Preparation for a Knee Arthroplasty Procedure,” the entire contents of which application are hereby incorporated by reference in their entirety.

TECH ICAL FIELD

[0002] The present disclosure generally relates to methods, systems, and apparatuses related to a computer-assisted surgical system that includes various hardware and software components that work together to enhance surgical workflows. More specifically, the present disclosure relates to methods, systems, and apparatuses for determining patella preparation characteristics for a particular patient to achieve successful patient outcomes in a knee arthroplasty procedure.

BACKGROUND

[0003] Patella and patella tracking problems account for a substantive number of poor knee arthroplasty outcomes in patients. For example, anterior knee pain after knee arthroplasty, particularly a total knee arthroplasty (TKA), is a typical post-surgery patellofemoral complication that may be attributed to issues with a native patella. [0004] Patella preparation procedures, including, for example, reshaping, facetectomy, and/or the like, may address certain patellofemoral complications; however, there is also a risk that such interventions may introduce a different set of issues. Existing decision processes for assessing patella preparation for knee arthroplasty patients lack consistency and uniform metrics for evaluating individual patients and their unique anatomy. For example, certain planning techniques may recommend patella resurfacing based primarily on a small set of factors, including a single factor in some cases (e.g., patella height). Alternatively, other surgical planning techniques may generally exclude patella preparation as part of knee arthroplasty procedures unless there are certain exceptional patient characteristics.

[0005] Accordingly, there remains a need for improved techniques for patella preparation evaluation and planning during a knee arthroplasty procedure. It is with this in mind that the present disclosure is provided.

SUMMARY

[0006] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended as an aid in determining the scope of the claimed subject matter.

[0007] Disclosed herein are improved systems and methods for planning a knee arthroplasty procedure, including a patella evaluation process for determining optimal patella preparation processes. [0008] In any preceding or subsequent example, the improved systems and methods may operate to perform a surgical process that includes a patella evaluation process to determine an optimal patella state or configuration for a patient for an arthroplasty procedure.

[0009] In any preceding or subsequent example, a surgical method may include determining patient-specific information including anatomical information associated with the knee arthroplasty procedure. Patient anatomical information may be or may include medical imaging or scanning portions of the knee anatomy, including the patella, tibia, and femur, as well as muscle and tendon structures. Non-limiting examples of medical imaging may include diagnostic imaging techniques such as MRI, CT, X-Ray, etc. Patient anatomical information may include pre-operative diagnostic imaging, intraoperative scans, for instance, via diagnostic imaging equipment, CASS robotic scanning/imaging systems (e.g., camera array), sensor arrays, landmarking systems, and/or the like. Patient anatomical information may include patient factors such as varus/valgus knee alignmentjoint line, quadriceps angle (Q-angle), native femur anatomy and size, femoral trochlear groove positioning and shape, native tibia anatomy and size, position of the tibial tubercle, tibial posterior slope, and/or the like.

[0010] Patient-specific patella information may include native patella size, thickness and shape, patella orientation and position relative to the femur, including, for instance, patella superior-inferior or medial-lateral position, patella flexion and/or internal-external rotation, patella mobility, patella tendon length and positioning, and/or the like at 0°, 30° knee flexion, or other clinically relevant knee flexion/extension positions. [0011] In any preceding or subsequent example, the surgical method may include generating patient models. For example, two-dimensional (2D) and/or three-dimensional (3D) models of the patient anatomy may be generated based on the anatomical information. In any preceding or subsequent example, the boney and soft tissue anatomy of the patient knee may be segmented and used to generate anatomical models. In any preceding or subsequent example, the models may include the tibia, femur, and patella bones, along with ligament, tendon, and muscle models that are direct contributors to knee anatomy and function. In any preceding or subsequent example. The anatomical models may include models of the patella, femur, tibia, a patella implant component, a femur implant component, and/or a tibial implant component alone or in combination. [0012] In any preceding or subsequent example, the surgical method may include accessing patient information (or patient factors). In any preceding or subsequent example, patient information may include age, gender, ethnicity, weight, height, body mass index (BMI), clinical characteristics, medical history (e.g., surgeries, injuries, medical records, and/or the like), and knee condition information (e.g., patient description of knee operation, knee pain, and/or the like), and/or the like.

[0013] In any preceding or subsequent example, the surgical workflow may include a surgical simulation. In various examples, a surgical simulation may include a knee arthroplasty simulation, such as a TKA simulation. In some examples, the surgical simulation may simulate a surgery on the patient based on the patient-specific information collected and/or generated for the patient [0014] In any preceding or subsequent example, the surgical simulation may generate simulation results including information corresponding to the results of the simulated surgery based on the patient information. In any preceding or subsequent example, the surgical simulation may include multiple simulations for different patella classifications and/or configurations, such as a simulation for a non-prepared patella, a resurfaced patella with a first set of parameters, a resurfaced patella with a second set of parameters, and so on.

[0015] In any preceding or subsequent example, the surgical method may include a knee movement (knee performance or knee kinematics) simulation. In any preceding or subsequent example, a knee performance simulation may include running the knee through different movements, such as deep knee bend, gait, stair descent, and/or the like. In various examples, the one or more of the different surgical simulations may be fed into the knee performance simulation and each different surgical simulation configuration may be simulated for kinematic results. In any preceding or subsequent example, a plurality of surgical simulations may be generated based on different patella configurations (e.g., prepared, non-prepared, resurfaced, facetectomy, different preparation parameters, and/or the like) and results data from one or more of the surgical simulations may be input into the knee performance simulation to provide performance metrics for the different patella configurations.

[0016] In any preceding or subsequent example, the surgical method may generate one or more patella classifications or patella determinations based on the simulation results. In any preceding or subsequent example, a patella determination may include various forms of information. For instance, a patella determination may include a binary (“yes” or “no”) recommendation (a “patella preparation indicator”) of whether the patella should remain in its native, non-prepared state for the arthroplasty procedure or whether it is recommended that the patella be modified or prepared as part of a knee arthroplasty procedure (e.g., resurfaced or not resurfaced output).

[0017] In any preceding or subsequent example, if the modification determination indicates that the patella should be modified or prepared, the patella classification may include preparation information corresponding with various characteristics of a recommended patella preparation procedure. For example, preparation information may include one or more recommended preparation processes, such as reshaping, resurfacing, denervation, facetectomy, and/or the like. The preparation information may include preparation parameters, for instance, detailing the operating characteristics of the patella preparation process, such as an amount of bone to remove, the location of reshaping, angles or radii of bone cuts, and/or the like.

[0018] In any preceding or subsequent example, a plurality of determinations may be generated, for instance, scored, ranked, or classified based on various factors, such as patient risk, outcomes, and/or the like. In some examples, the evaluation process of workflow 500 may include various evaluation parameters. The evaluation parameters may cause the evaluation process to be biased toward or away from certain preparation determinations. The evaluation parameters may be specified based on patient conditions, risk appetite, patient demographic information (e.g., more conservative for patients over a certain age, more focused on improved kinematic performance for patients under a certain age, and/or the like).

[0019] Examples described in the present disclosure provide numerous advantages over conventional systems and methods. In one non-limiting example advantage, a patella evaluation process allows for automated, patient-specific patella evaluation. In one nonlimiting example advantage, patella classification may allow better surgical decisionmaking, set realistic patient expectations, make better use of resources, identification of high-risk groups for complications, anticipate complications, predict a clinical outcome, and help the surgeon to proactively plan the most appropriate treatment for that patient. In another non-limiting example, proactively identifying and recommending a patella preparation, including parameters for performing a patella preparation, may improve clinical outcomes and reduce adverse effects related to patellar mal-positioning and maltracking. Using automated tools to perform the characterization, analysis, and performance recommendations may enhance outcomes without any additional time, patient impact, and may facilitate performance of the patella evaluation, at least partially, intraoperatively, which is not possible using conventional systems.

[0020] In many examples, one or more of the components described herein may be implemented as a set of rules that improve computer-related technology by allowing a function not previously performable by a computer that enables an improved technological result to be achieved. For example, components may facilitate a computer to generate the technological result of providing an optimized patella preparation diagnosis that directly addresses patient anatomy in combination with the unique risk factors associated with the patient. This technological result may allow a computing device, programmed to operate according to example processes described in the present disclosure, to provide the functionality of determining patella preparation procedures, knee implant components and the configuration of knee implant components, including, specifically, the management of the patella to achieve improved surgical outcomes for the patient.

[0021] In any preceding or subsequent example, an evaluation system may use a trained computational model to provide a practical application and real-world results for patients. For example, evaluation system may provide an improvement in the field of knee arthroplasty, and in particular, computer-based surgical systems through the ability of the evaluation system to perform a patella evaluation process to provide patella classifications in a manner that is not possible using conventional computing systems. Existing computer-based surgical systems, simulation systems (including systems that simulate the patella), and/or the like are not capable of providing a patella classification according to some examples.

[0022] In one example, a computer-implemented method for planning a knee' arthroplasty procedure may include, via a processor of a computing device: accessing anatomical information of a knee joint of a patient, the anatomical information includes patella information of a patella of the patient and femoral information of a femur of the patient; generating a virtual model of the knee joint based on the anatomical information, the virtual model includes a patella model and a femur model; generating a simulated post-surgical knee via performing a simulated knee arthroplasty procedure on the virtual model; determining simulation results via emulating performance of the simulated post- surgical knee; and determining a patella classification based on the simulation results, the patella classification includes a patella preparation indicator of whether the patella should be resurfaced as part of the knee arthroplasty procedure.

[0023] In any preceding or subsequent example of the method, the patella classification is determined based on one or more patella factors, the patella factors include one or more of patella size, patella shape, and patella thickness.

[0024] In any preceding or subsequent example of the method, the virtual model is generated based on at least one patient factor, the at least one patient factor includes at least one of varus/valgus knee alignmentjoint line information, quadriceps angle (Q- angle) information, native femur anatomy, femoral trochlear groove information, or native tibia anatomy.

[0025] In any preceding or subsequent example of the method, the virtual model includes virtual knee tendon, ligament, and muscle elements comprising at least one of anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), lateral collateral ligament (LCL), quadriceps tendon patellar tendon, and quadriceps femoris.

[0026] In any preceding or subsequent example of the method, the method further includes determining patella resurfacing parameters responsive to the patella classification indicating patella resurfacing, the patella resurfacing parameters indicating surgical characteristics of a patella resurfacing procedure. [0027] In any preceding or subsequent example of the method, the patella resurfacing parameters include one or more of bone removal amount, reshaping location, bone cut angle, bone cut radii, or retained thickness.

[0028] In any preceding or subsequent example of the method, the patella classification includes at least one of facetectomy, denervation, or reshaping.

[0029] In any preceding or subsequent example of the method, the simulated post- surgical model includes at least one of a femoral implant or a tibial implant having implant characteristics, the implant characteristics include at least one of a size and a position, the simulation results determined based on the implant characteristics of the femoral implant or the tibial implant.

[0030] In any preceding or subsequent example of the method, the patella information includes a condition factor indicating pre-surgical patella issues, the patella classification biased toward stricter criteria for patella resurfacing based on the condition factor.

[0031] In any preceding or subsequent example of the method, the method further includes characterizing a knee morphology of the knee joint. In any preceding or subsequent example of the method, the knee morphology includes a patella morphology of the patella. In any preceding or subsequent example of the method, the knee morphology includes a femur morphology of the femur. In any preceding or subsequent example of the method, the knee morphology includes a femur morphology of the femur and its contribution to the hip-knee-ankle angle.

[0032] In any preceding or subsequent example of the method, the knee morphology includes a tibia morphology of the tibia. In any preceding or subsequent example of the method, the knee morphology includes a tibia morphology of the tibia and its contribution to the hip-knee-ankle angle. In any preceding or subsequent example of the method, the knee morphology includes a location of the tibia tubercle. In any preceding or subsequent example of the method, the knee morphology includes a location of the tibia tubercle and its effect on the quadriceps angle.

[0033] In any preceding or subsequent example of the method, the virtual model is generated based on the knee morphology.

[0034] In one example, a computer-assisted surgical system for planning a knee arthroplasty procedure includes a computing device comprising at least one processor and a storage device in communication with the at least one processor, the storage device storing instructions that, when executed by the at least one processor, cause the at least one processor to: access patella information of a patient, the patella information includes: anatomical information of a patella of a knee joint of the patient; a virtual model of the knee joint based on the anatomical information, the virtual model comprising a patella model and a femur model; execute a machine learning (ML) model to determine a patella classification, the ML model trained: using training data that includes patella classifications of a population of patients, to receive the patella information as input, and to generate a patella classification as output, the patella classification includes a patella preparation indicator of whether the patella should be resurfaced as part of the knee arthroplasty procedure. [0035] In any preceding or subsequent example of the system, the patella classification is determined based on one or more patella factors, the patella factors include one or more of patella size, patella shape, and patella thickness.

[0036] In any preceding or subsequent example of the system, the patella information includes a virtual model of the knee joint generated based on the anatomical information and at least one patient factor, the at least one patient factor includes at least one of varus/valgus knee alignment, joint line information, quadriceps angle (Q-angle) information, native femur anatomy, femoral trochlear groove information, or native tibia anatomy.

[0037] In any preceding or subsequent example of the system, the virtual model includes virtual knee tendon, ligament, and muscle elements that include at least one of anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), lateral collateral ligament (LCL), quadriceps tendon patellar tendon, and quadriceps femoris.

[0038] In any preceding or subsequent example of the system, the ML model is further trained to generate patella resurfacing parameters as output responsive to the patella classification indicating patella resurfacing, the patella resurfacing parameters indicating surgical characteristics of a patella resurfacing procedure.

[0039] In any preceding or subsequent example of the system, the patella resurfacing parameters include one or more of bone removal amount, reshaping location, bone cut angle, bone cut radii, or retained thickness. [0040] In any preceding or subsequent example of the system, the patella classification includes at least one of facetectomy, denervation, or reshaping.

[0041] In any preceding or subsequent example of the system, the patella information includes a simulated post-surgical model generated via performing a simulated knee arthroplasty procedure on a virtual model of the knee joint, the post-surgical model includes at least one of a femoral implant or a tibial implant having implant characteristics, the implant characteristics include at least one of a size and a position, the simulation results determined based on the implant characteristics of the femoral implant or the tibial implant.

[0042] In any preceding or subsequent example of the system, the patella information includes a condition factor indicating pre-surgical patella issues, the patella classification biased toward stricter criteria for patella resurfacing based on the condition factor.

[0043] In any preceding or subsequent example of the system, the method further includes characterizing a knee morphology of the knee joint. In any preceding or subsequent example of the system, the knee morphology includes a patella morphology of the patella. In any preceding or subsequent example of the system, the knee morphology includes a femur morphology of the femur. In any preceding or subsequent example of the system, the knee morphology includes a femur morphology of the femur and its contribution to the hip-knee-ankle angle.

[0044] In any preceding or subsequent example of the system, the knee morphology includes a tibia morphology of the tibia. In any preceding or subsequent example of the system, the knee morphology includes a tibia morphology of the tibia and its contribution to the hip-knee-ankle angle. In any preceding or subsequent example of the system, the knee morphology includes a location of the tibia tubercle. In any preceding or subsequent example of the system, the knee morphology includes a location of the tibia tubercle and its effect on the quadriceps angle.

[0045] In any preceding or subsequent example of the system, the virtual model is generated based on the knee morphology.

[0046] Further features and advantages of at least some of the examples described in the present disclosure, as well as the structure and operation of any preceding or subsequent example of the present disclosure, are described in detail below with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By way of example, specific examples of the disclosed device will now be described, with reference to the accompanying drawings, in which:

[0048] FIG. 1 depicts an operating theatre including an illustrative computer-assisted surgical system (CASS) in accordance with one or more features of the present disclosure;

[0049] FIG. 2A depicts illustrative control instructions that a surgical computer provides to other components of a CASS in accordance with one or more features of the present disclosure; [0050] FIG. 2B depicts illustrative control instructions that components of a CASS provide to a surgical computer in accordance with one or more features of the present disclosure;

[0051] FIG. 2C depicts an illustrative implementation in which a surgical computer is connected to a surgical data server via a network in accordance with one or more features of the present disclosure;

[0052] FIG. 3 depicts an operative patient care system and illustrative data sources in accordance with one or more features of the present disclosure;

[0053] FIG. 4A depicts an illustrative flow diagram for determining a pre-operative surgical plan in accordance with one or more features of the present disclosure;

[0054] FIG. 4B depicts an illustrative flow diagram for determining an episode of care including pre-operative, intraoperative, and post-operative actions in accordance with one or more features of the present disclosure;

[0055] FIGS. 4C-4E depict illustrative graphical user interfaces including images depicting an implant placement in accordance with one or more features of the present disclosure;

[0056] FIG. 5 illustrates an example of a surgical workflow in accordance with one or more features of the present disclosure;

[0057] FIG. 6 depicts illustrative anatomical and functional measurement properties for a patella in accordance with one or more features of the present disclosure;

[0058] FIG. 7 depicts a first illustrative operating environment for a surgical planning process in accordance with the present disclosure; [0059] FIG. 8 depicts simulation results of patellar shift for a native patella with an implant system in accordance with the present disclosure;

[0060] FIG. 9 depicts simulation results of retinaculum strain for a native patella in accordance with the present disclosure;

[0061] FIGS. 10A and 10B depict simulation results of patella-femur contact through a range of motion in accordance with the present disclosure; and

[0062] FIG. 11 depict simulation results of patella-femur implant contact through a range of motion in accordance with the present disclosure;

[0063] FIG. 12 depicts simulation results for prepared and non-prepared (native) patellae in accordance with the present disclosure; and

[0064] FIG. 13 depicts a second illustrative operating environment for a surgical planning process in accordance with the present disclosure.

[0065] It should be understood that the drawings are not necessarily to scale and that the disclosed examples are sometimes illustrated diagrammatically and in partial views. In certain instances, details which are not necessary for an understanding of the disclosed methods and devices, or which render other details difficult to perceive may have been omitted. It should be further understood that this disclosure is not limited to the particular examples illustrated herein. In the drawings, like numbers refer to like elements throughout unless otherwise noted. DETAILED DESCRIPTION

[0066] This disclosure is not limited to the particular systems, devices and methods described, as these may vary. The terminology used in the description is for the purpose of describing the particular versions or examples only and is not intended to limit the scope.

[0067] As used in this document, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise. Unless defined otherwise, all technical and scientific terms used herein have the same meanings as commonly understood by one of ordinary skill in the art. As used in this document, the term “comprising” means “including, but not limited to.”

[0068] The described technology generally relates to surgical processes, for example, knee arthroplasty procedures including, without limitation, a total knee arthroplasty (TKA) procedure. Although TKA is used in some examples, the present disclosure is not limited to TKA, as processes according to some examples may operate with other knee arthroplasty procedures, including, without limitation, a partial (unicondylar or unicompartmental) knee arthroplasty procedure, a revision knee arthroplasty procedure, and/or the like.

[0069] In some examples, a surgical process may include a method for optimizing patella preparation through patient anatomy characterization. A surgical workflow according to various examples may include registering the patient anatomy, particularly the patella and optionally the femur and/or tibia, generating models and/or anatomical landmarks, determining patella morphological characterization, determining femur and/or tibia morphological characterization, and generating a patella classification.

[0070] In some examples, a patella evaluation process may include determining a patella classification indicating whether the patella should be prepared as part of a knee arthroplasty procedure or whether the patella should be retained in its native, original, natural, or non-prepared form. The patella classification may be used as input into a surgical planning process, such as one or more of an implant planning/optimizing/selection step, one or more bone preparation or cutting steps, one or more implant trialing steps, a final implant placement step, and/or other surgical steps. [0071] In some examples, a patella classification may include various forms of information. For example, a patella determination may include a binary (“yes” or “no”) recommendation (a “modification determination”) of whether the patella should remain in its native, non-prepared state for the arthroplasty procedure or whether it is recommended the patella to be modified or prepared as part of a knee arthroplasty procedure (e.g., resurfaced or not resurfaced output).

[0072] If the modification determination indicates that the patella should be prepared, the patella classification may include preparation information corresponding with various characteristics of a recommended patella preparation procedure. For example, preparation information may include one or more recommended preparation processes, such as reshaping, resurfacing, denervation, facetectomy, and/or the like. The preparation information may include preparation parameters, for instance, detailing the operating characteristics of the patella preparation process, such as an amount of bone to remove, the location of reshaping, angles or radii of bone cuts, and/or the like.

[0073] In some examples, surgical processes may be or may include a surgical workflow for computer-assisted or navigated knee arthroplasty procedures. A surgical workflow may include registering the patient’s anatomy pre-operatively and/or intra-operatively in order to create a three-dimensional (3D) representation of the femur, tibia, and patellar anatomy. The patient’s anatomy may be automatically landmarked and measured in order to characterize the anatomy, including the patellar anatomy, and classify the patella into a classification group indicating a patella preparation determination.

[0074] After patella classification, a module or tool (for instance, a surgical planning optimizer) may provide information to the surgeon, such as whether a patella preparation process should be performed, the type of preparation process, and preparation parameters. The surgeon can perform certain surgical steps, such as performing the patella preparation process, surgical cuts, placing trials, including a patellar implant trial for capturing range of motion (ROM), collecting post-operative baseline information, confirming implant size, shape, position, and orientation, and/or the like. After trialing, the surgeon may finish the implantation of the remaining components.

[0075] There are multiple benefits to computer-assisted surgery, which has led to its widespread adoption and promoted technological advancement. For knee arthroplasty procedures, benefits may include more accurate implant size, position, and orientation, improved range of motion, improved soft tissue balance, reduced risk of injury to soft tissues, reduced outliers, quicker recovery, and/or reduced post-operative pain. Overall, computer-assisted knee arthroplasty may allow for more accurate and precise bone cuts, implant placement, and/or better joint alignment which, ultimately, facilitates improved patient outcomes.

[0076] However, although important to the outcome of the surgery, the patella and patellar tracking have not been included in conventional patient-specific or computer- assisted surgery technologies or techniques. For instance, surgical systems that use patient-specific instrumentation (PSI) and automated surgical planning tools typically only include femur and tibia preparation evaluations, and do not include patellar cutting guides or patella preparation evaluations, particularly personalized for each individual patient anatomy. Even within a computer-assisted surgical setting, knee arthroplasty procedures do not include automated, computer-assisted patellar preparation evaluations. [0077] For example, patella resurfacing continues to be a disputed aspect of knee arthroplasty with wide disparities in the practice among geographic regions and practice groups. Some surgeons consistently resurface the patella in an effort to minimize postoperative anterior knee pain and to avoid the need for secondary patellar resurfacing.

Alternatively, other surgeons selectively resurface the patella or typically exclude patella resurfacing in an effort to decrease surgery time and address certain patellofemoral joint complications such as fracture, instability, and implant wear. Accordingly, there can be value in both patella preparation and retaining native anatomy; however, conventional techniques and technologies do not provide consistent and effective protocols to provide a patient-specific, personalized evaluation of the potential benefits and challenges for each individual patient. [0078] Although various studies have conducted systematic reviews and meta-analysis on patellar preparation, such as resurfacing in TKA, patella preparation during knee arthroplasty, especially resurfacing versus not resurfacing, remains inconsistent among practice groups and even individual surgeons. For example, certain theories propose determining whether the patella should be resurfaced based solely on the height of the patella, for instance, proposing that if patella height is 15 millimeters (mm) or higher above the joint line, resurfacing is recommended, and that up to 80% of resurfacing can be avoided below this 15 mm threshold. Other theories derive conclusions of patellar resurfacing based on clinical outcomes such as patient reported outcome measures, complications, or secondary revision.

[0079] As a result, existing techniques typically use generic and universal (i.e., “one- size-fits-all”) tests or theories that may be beneficial on average to a large patient population, but may not be the optimal process for a particular patient. Therefore, conventional techniques do not provide patients with personalized patella preparation evaluations and, in effect, may cause patients to have their patella prepared/not prepared contrary to the optimal evaluation for their particular anatomy (for instance, if a personalized patella evaluation according to some examples were performed for the patient).

[0080] Accordingly, patella evaluation processes according to some examples may provide a patella classification that is based on patient-specific factors and implant design factors to generate a preparation determination to guide the surgeon to a decision regarding patella preparation, including patella resurfacing and resurfacing implant shape, reshaping, facetectomy, and/or the like and parameters associated with a recommended preparation procedure.

[0081] Introducing additional steps in the surgical workflow, to capture the patellar anatomy and predict clinical outcomes, for instance, based on simulation of a prepared patella, is critical in providing a surgeon with a better understanding as to how the patellar preparation can be optimized and to reduce the risk of poor outcomes.

[0082] Accordingly, various examples may include technologies and processes for determining patella information to optimize patella preparation and the post-operative biomechanics and performance of the patella.

[0083] For instance, some examples may include a pre-operative surgical workflow where the patient may have their affected lower limb analyzed, including, without limitation, manual landmarking, scanned by a robotic surgical system (including intra- operatively), computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, X-ray, and/or other imaging modalities, the boney and soft tissue anatomy may be segmented, and three-dimensional (3D) models may be generated and input into a computerized model.

[0084] These 3D models may include the tibia, femur, and patella bones, along with ligament, tendon, and muscle models that are direct contributors to knee anatomy. Along with the 3D models, patient information such as gender, age, ethnicity, weight, height, body mass index (BMI), clinical characteristics, medical imaging findings (patellar height alta/baja, patellar tilt, patellar shift, posterior patellar angle, elongated patellar tendons, trochlear dysplasia, femoral sulcus angle, etc.), and/or the like may be included. The computerized model may assess the lower limb for multiple patient-specific factors in determination of patella classification.

[0085] The computerized model may also assess patient factors such as varus/valgus knee alignmentjoint line, the quadriceps angle (Q-angle), native femur anatomy and size, femoral trochlear groove positioning and shape, native tibia anatomy and size, position of the tibial tubercle, tibial posterior slope, and/or the like. In some examples, patient factors may also include the computerized model accessing and analyzing native patella size, thickness, and shape data in order to determine if an implant would be safe and effective. In various examples, patient factors may also include receiving and/or calculating patella orientation and position relative to the femur, including, without limitation, patella superior-inferior and/or medial-lateral position, patella flexion and/or internal-external rotation patella mobility, patella tendon length and positioning, and/or the like at 0°, 30° knee flexion, or other clinically relevant knee flexion/extension positions.

[0086] The computerized model may also simulate a knee arthroplasty procedure with and without patella preparation (e.g., resurfacing, lateral facetectomy, reshaping, and/or the like) as well as different alignment techniques of the femoral and tibial implants such as kinematic, anatomic, mechanical, and functional alignment.

[0087] The simulations may run the virtual knee through different movements, such as deep knee bend, gait, stair descent, etc. The computerized model may then determine outputs from the simulations, including patella kinematics (for instance, relative to the femur and/or tibia) and resulting patella forces, quad efficiency, tendon and ligament strains and pressure, patella contact pressure, and/or the like. Using the input factors and 3D models, the computerized model algorithm with simulations may determine the most optimal outcome prediction and help surgeons determine the best course of action for each particular patient.

[0088] In some examples, a patella classification may be weighted or otherwise modified based on certain patient criteria. For instance, knee condition patient criteria may include certain condition factors of a patient knee indicating pre-surgical patella or knee issues, such as if a patient had pre-op anterior knee pain or if a bone scan showed a “hot patella,” the computerized model may be more weighted towards having more strict criteria for patella measures with the simulated knee arthroplasty to recommend not preparing the patella (e g., leaving the patella unresurfaced). In general, a “hot patella” refers to a tracer uptake in nuclear medicine imaging at the patella, which shows the possibility of osteoarthritis, increased pressures, and/or other painful symptoms near the patellofemoral joint.

[0089] If the patella is classified as a non-resurfaced patella (e.g., the recommendation is to not resurface the patella), the computerized model may also evaluate and recommend other preparation procedures, including, without limitation, whether the patella should have a lateral facetectomy, reshaping, or denervation.

[0090] For lateral facetectomy or patella reshaping, preparation parameters may be determined that include recommendations of amount of bone to remove, angles or radii of bone cuts, methods to accomplish the bone preparation, such as resections through cutting guides, patient specific cutting guides that reference the bone or surrounding soft tissue, robotic surgery using a burr, saw, reamer, laser, or other controlled bone removal methods, and/or the like.

[0091] In some examples, patient factors or other patient-specific information may be provided into various computational models, for instance, configured using regression equations, look up tables, and/or the like based on historical information of previous simulations, thereby allowing faster intraoperative feedback based on classification of patient anatomy, which may involve identifying the features of the patella through statistical shape modeling or other bone morphing methods to quantify the native patella anatomy, for instance, for input to a computational model (e.g., a regression model, machine learning model, artificial intelligence model, neural network, etc.).

[0092] Patella classification according to any preceding or subsequent example may provide multiple advantages over existing systems, including, without limitation, better surgical decision-making, setting realistic patient expectations, making better use of resources, identification of high-risk groups for complications, anticipating complications, predicting clinical outcomes, and assisting surgeons to proactively plan the most appropriate treatment for that patient. In another non-limiting example of a technological advantage, proactively identifying a patella classification specific for a patient may provide a direction to the surgeon in terms of managing the patella, implant choices, what implant would be best for that patient, constraint decisions, and/or the like. [0093] Processes according to some examples may provide a technological advantage of determining recommendations on preparing (e.g., resurfacing) a patella based upon patient-specific and implant design factors for surgeons. Processes according to some examples may also provide possible clinical benefits including, without limitation, reduced anterior knee pain and reduction of secondary patellar resurfacing. Processes according to some examples may also provide increased insight and knowledge behind different patella variations within patients, which is currently lacking or even nonexistent. Processes according to various examples may also provide clinical determinations of whether knee arthroplasty implant designs may achieve positive outcomes for both prepared (for instance, resurfaced) and native, non-prepared patellae. [0094] As a result, surgical processes including patella classification according to any preceding or subsequent example may provide surgeons with improved surgical methods that are more accurate, personalized for each patient, and reduce complexity and cognitive load (particularly during an active surgery), while also improving patient outcomes.

[0095] FIG. 1 provides an illustration of an example computer-assisted surgical system (CASS) 100 according to any preceding or subsequent example that uses computers, robotics, and imaging technology to aid surgeons in performing orthopedic surgery procedures such as knee arthroplasty (e.g., total knee arthroplasty (TKA)) or total hip arthroplasty (THA). An Effector Platform 105 positions surgical tools relative to a patient during surgery. For example, for a knee surgery, the Effector Platform 105 may include an End Effector 105B that holds surgical tools or instruments during their use. The Effector Platform 105 can include a Limb Positioner 105C for positioning the patient’s limbs during surgery. Resection Equipment 110 (not shown in FIG. 1) performs bone or tissue resection using, for example, mechanical, ultrasonic, or laser techniques. The Effector Platform 105 can also include a cutting guide or jig 105D that is used to guide saws or drills used to resect tissue during surgery. Such cutting guides 105D can be formed integrally as part of the Effector Platform 105 or Robotic Arm 105 A, or cutting guides can be separate structures that can be matingly and/or removably attached to the Effector Platform 105 or Robotic Arm 105 A.

[0096] The Tracking System 115 uses one or more sensors to collect real-time position data that locates the patient’s anatomy and surgical instruments. Any suitable tracking system can be used for tracking surgical objects and patient anatomy in the surgical theatre. For example, a combination of infrared (ER) and visible light cameras can be used in an array.

[0097] The registration process that registers the CASS 100 to the relevant anatomy of the patient can also involve the use of anatomical landmarks, such as landmarks on a bone or cartilage. For example, the CASS 100 can include a 3D model of the relevant bone or joint and the surgeon can intraoperatively collect data regarding the location of bony landmarks on the patient’s actual bone using a probe that is connected to the CASS. Alternatively, the CASS 100 can construct a 3D model of the bone or joint without preoperative image data by using location data of bony landmarks and the bone surface that are collected by the surgeon using a CASS probe or other means.

[0098] A Tissue Navigation System 120 (not shown in FIG. 1) provides the surgeon with intraoperative, real-time visualization for the patient’s bone, cartilage, muscle, nervous, and/or vascular tissues surrounding the surgical area. [0099] The Display 125 provides graphical user interfaces (GUIs) that display images collected by the Tissue Navigation System 120 as well other information relevant to the surgery. For example, in some examples, the Display 125 overlays image information collected from various modalities (e.g., CT, MRI, X-ray, fluorescent, ultrasound, etc.) collected pre-operatively or intra-operatively to give the surgeon various views of the patient’s anatomy as well as real-time conditions. Surgical Computer 150 provides control instructions to various components of the CASS 100, collects data from those components, and provides general processing for various data needed during surgery. [0100] Data acquired during the pre-operative phase generally includes all information collected or generated prior to the surgery. Thus, for example, information about the patient may be acquired from a patient intake form or electronic medical record (EMR). Examples of patient information that may be collected include, without limitation, patient demographics, diagnoses, medical histories, progress notes, vital signs, medical history information, allergies, and lab results. The pre-operative data may also include images related to the anatomical area of interest. These images may be captured, for example, using Magnetic Resonance Imaging (MRI), Computed Tomography (CT), X-ray, ultrasound, or any other modality known in the art.

[0101] FIGS. 2A and 2B provide examples of data that may be acquired during the intraoperative phase of an episode of care. These examples are based on the various components of the CASS 100 described above with reference to FIG. 1; however, it should be understood that other types of data may be used based on the types of equipment used during surgery and their use. FIG. 2A shows examples of some of the control instructions that the Surgical Computer 150 provides to other components of the

CASS 100, according to any preceding or subsequent example.

[0102] Resection Equipment 110 is provided with a variety of commands to perform bone or tissue operations. As with the Effector Platform 105, position information may be provided to the Resection Equipment 110 to specify where it should be located when performing resection.

[0103] During the registration process, for example, the display 125 can show a preoperatively constructed 3D bone model and depict the locations of the probe as the surgeon uses the probe to collect locations of anatomical landmarks on the patient. The display 125 can include information about the surgical target area. For example, in connection with a TKA, the display 125 can depict the mechanical and anatomical axes of the femur and tibia. The display 125 can depict varus and valgus angles for the knee joint based on a surgical plan, and the CASS 100 can depict how such angles will be affected if contemplated revisions to the surgical plan are made. As the workflow progresses to preparation of bone cuts or resections, the display 125 can depict the planned or recommended bone cuts before any cuts are performed.

[0104] In some examples, one or more surgical planning models may be incorporated into the CASS 100 and used in the development of the surgical plans provided to the surgeon 111. The term “surgical planning model” may refer to software that simulates the biomechanics performance of anatomy under various scenarios to determine the optimal way to perform cutting and other surgical activities. For example, for knee replacement surgeries, the surgical planning model can measure parameters for functional activities, such as deep knee bends, gait, etc., and select cut locations on the knee to optimize implant placement. One example of a surgical planning model is the LIFEMOD® simulation software from Smith & Nephew, Inc. In some examples, the Surgical Computer 150 includes computing architecture that allows full execution of the surgical planning model during surgery (e.g., a GPU-based parallel processing environment). As an alternative to full execution of the surgical planning model, in some examples, a set of transfer functions are derived that simplify the mathematical operations captured by the model into one or more predictor equations. Then, rather than execute the full simulation during surgery, the predictor equations are used. Further details on the use of transfer functions are described in U.S. Patent Application Serial No. 17/269,091, entitled “Patient Specific Surgical Method and System,” the entirety of which is incorporated herein by reference in the present disclosure.

[0105] FIG. 2B shows examples of some of the types of data that can be provided to the Surgical Computer 150 from the various components of the CASS 100. FIG. 2C illustrates a “cloud-based” implementation in which the Surgical Computer 150 is connected to a Surgical Data Server 180 via a Network 175.

[0106] The general concepts of optimization may be extended to the entire episode of care using an Operative Patient Care System 320 that uses the surgical data, and other data from the Patient 305 and Healthcare Professionals 330 to optimize outcomes and patient satisfaction as depicted in FIG. 3.

[0107] The Operative Patient Care System 320 is designed to utilize patient specific data, surgeon data, healthcare facility data, and historical outcome data to develop an algorithm that suggests or recommends an optimal overall treatment plan for the patient’s entire episode of care (preoperative, operative, and postoperative) based on a desired clinical outcome. In addition to utilizing statistical and mathematical models, simulation tools (e.g., LIFEMOD®) can be used to simulate outcomes, alignment, kinematics, etc. based on a preliminary or proposed surgical plan, and reconfigure the preliminary or proposed plan to achieve desired or optimal results according to a patient’s profile or a surgeon’s preferences.

[0108] Data derived from simulation of the procedure may be captured. Simulation inputs include implant size, position, and orientation. Simulation can be conducted with custom or commercially available anatomical modeling software programs (e.g., LIFEMOD®, AnyBody, or OpenSIM). It is noted that the data inputs described above may not be available for every patient, and the treatment plan will be generated using the data that is available.

[0109] Historical data sets from the online database are used as inputs to a machine learning model such as, for example, a recurrent neural network (RNN) or other form of artificial neural network. As is generally understood in the art, an artificial neural network functions similar to a biologic neural network and includes a series of nodes and connections. The machine learning model is trained to predict one or more values based on the input data. For the sections that follow, it is assumed that the machine learning model is trained to generate predictor equations. These predictor equations may be optimized to determine the optimal size, position, and orientation of the implants to achieve the best outcome or satisfaction level. [0110] FIG. 4A illustrates how the Operative Patient Care System 320 may be adapted for performing case plan matching services. In this example, data is captured relating to the current patient 310 and is compared to all or portions of a historical database of patient data and associated outcomes 315. Once the case plan has been fully executed all data associated with the case plan, including any deviations performed from the recommended actions by the surgeon, are stored in the database of historical data. In some examples, the system utilizes preoperative, intraoperative, or postoperative modules in a piecewise fashion, as opposed to the entire continuum of care. In other words, caregivers can prescribe any permutation or combination of treatment modules including the use of a single module. These concepts are illustrated in FIG. 4B and can be applied to any type of surgery utilizing the CASS 100.

[0111] Training of the machine learning model can be performed as follows. The overall state of the CASS 100 can be sampled over a plurality of time periods for the duration of the surgery. The machine learning model can then be trained to translate a current state at a first time period to a future state at a different time period. By analyzing the entire state of the CASS 100 rather than the individual data items, any causal effects of interactions between different components of the CASS 100 can be captured. In some examples, a plurality of machine learning models may be used rather than a single model. In some examples, the machine learning model may be trained not only with the state of the CASS 100, but also with patient data (e.g., captured from an EMR) and an identification of members of the surgical staff. This allows the model to make predictions with even greater specificity. Moreover, it allows surgeons to selectively make predictions based only on their own surgical experiences if desired.

[0112] In some examples, predictions or recommendations made by the aforementioned machine learning models can be directly integrated into the surgical workflow. For example, in some examples, the Surgical Computer 150 may execute the machine learning model in the background making predictions or recommendations for upcoming actions or surgical conditions. A plurality of states can thus be predicted or recommended for each period. For example, the Surgical Computer 150 may predict or recommend the state for the next 5 minutes in 30 second increments. Using this information, the surgeon can utilize a “process display” view of the surgery that allows visualization of the future state. For example, FIGS. 4C-4E depict a series of images that may be displayed to the surgeon depicting the implant placement interface. The surgeon can cycle through these images, for example, by entering a particular time into the display 125 of the CASS 100 or instructing the system to advance or rewind the display in a specific time increment using a tactile, oral, or other instruction.

[0113] Use of a point probe is described in U.S. Patent Application No. 14/955,742 entitled “Systems and Methods for Planning and Performing Image Free Implant Revision Surgery,” the entirety of which is incorporated herein by reference. Briefly, an optically tracked point probe may be used to map the actual surface of the target bone that needs a new implant. This is referred to as tracing or “painting” the bone. The collected points are used to create a three-dimensional model or surface map of the bone surfaces in the computerized planning system. The created 3D model of the remaining bone is then used as the basis for planning the procedure and necessary implant sizes. An alternative technique that uses X-rays to determine a 3D model is described in U.S.

Patent Application Serial No. 16/387,151, filed April 17, 2019 and entitled “Three

Dimensional Selective Bone Matching,” the entirety of which is incorporated herein by reference in the present disclosure.

[0114] As noted above, in some examples, a 3D model is developed during the preoperative stage based on 2D or 3D images of the anatomical area of interest. In such examples, registration between the 3D model and the surgical site is performed prior to the surgical procedure. The registered 3D model may be used to track and measure the patient’s anatomy and surgical tools intraoperatively.

[0115] Included herein are one or more workflows representative of exemplary methodologies for performing novel aspects of the disclosed examples. While, for purposes of simplicity of explanation, the one or more methodologies shown herein are shown and described as a series of acts, those skilled in the art will understand and appreciate that the methodologies are not limited by the order of acts. Some acts may, in accordance therewith, occur in a different order and/or concurrently with other acts from that shown and described herein. For example, those skilled in the art will understand and appreciate that a methodology could alternatively be represented as a series of interrelated states or events, such as in a state diagram. Moreover, not all acts illustrated in a methodology may be required for a novel implementation. Blocks designated with dotted lines may be optional blocks of a workflow. [0116] A workflow or portions (or steps) thereof may be implemented in software, firmware, hardware, or any combination thereof. In software and firmware examples, one or more workflow steps (or logic flow) may be implemented by computer executable instructions stored on a non-transitory computer readable medium or machine readable medium (for instance, executed by CASS 100 or similar system). The examples are not limited in this context.

[0117] FIG. 5 illustrates an example of a surgical workflow 500 in accordance with one or more features of the present disclosure. Workflow 500 may be representative of some or all of the operations executed by or according to any preceding or subsequent example described in the present disclosure. For example, workflow 500 may include a patella evaluation or patella analysis process for optimizing the treatment of the patella, including whether to prepare the patella, selection of patella preparation processes, and/or determination of patella preparation parameters through patient anatomy characterization and analysis.

[0118] At block 502, workflow 500 may include determining patient-specific information including anatomical information associated with the knee arthroplasty procedure. In some examples, determining patient anatomical information may be or may include medical imaging or scanning portions of the knee anatomy, including the patella, tibia, and femur, as well as muscle and tendon structures. Non-limiting examples of medical imaging may include diagnostic imaging techniques such as MRI, CT, X-Ray, etc. In various examples, determining patient anatomical information may include pre-operative diagnostic imaging. In some examples, determining patient anatomical information may include intraoperative scans, for instance, via diagnostic imaging equipment, CASS robotic scanning/imaging systems (e g., camera array), sensor arrays, landmarking systems, and/or the like.

[0119] In various examples, the patient anatomical information may include patient factors such as varus/valgus knee alignment, joint line, quadriceps angle (Q-angle), native femur anatomy and size, femoral trochlear groove positioning and shape, native tibia anatomy and size, position of the tibial tubercle, tibial posterior slope, and/or the like.

[0120] FIG. 6 depicts illustrative anatomical and functional measurement properties for a patella in accordance with one or more features of the present disclosure. As shown in FIG. 6, patient-specific patella information of a patella 605, alone or in relation to other patient anatomy, such as a femur 606, tibia 607, and/or implant components thereof, may be determined, including native patella size, thickness and shape, for example, in order to determine if an implant would be safe and effective. In various examples, patient factors may include patella orientation and position relative to the femur, including, for instance, patella superior-inferior 610 and/or medial-lateral position 611, patella flexion and/or internal-external rotation 612 at 0°, 30° knee flexion, and/or other clinically relevant knee flexion/extension positions. In some examples, patient factors may include patella mobility, patella tendon length and positioning 613, and/or the like.

[0121] In some examples, determining patient anatomical information may include registration of patient anatomy. In some examples, registration may include measuring, gathering, or otherwise determining information associated with a femur, tibia, patella, muscle and tendon structures, surface mapping, ROM collection, and/or the like. In various examples, patient anatomy registration may include a specific patella registration for instance, via a fixture device affixed in place on the patella. The patella registration process may be the same or similar to the patella registration process described in International PCT Application Publication No, WO 2024/091549 (the ‘“549 PCT Application”) filed on October 25, 2023 and claiming priority to U.S. Provisional Patent Application No. 63/419,471 filed on October 26, 2022, titled “Systems and Methods for Planning a Patella Replacement Procedure, and, the entire contents of which applications are hereby incorporated by reference into the present disclosure.

[0122] For example, tracking hardware may be fixed to (or placed in an area capable of tracking) bones of the knee joint and a registration process may be initiated. In some examples, registration may include using a point probe at several points for collection of registration information, including, without limitation, landmarks on the femoral condyles, the knee center, the patella and patella landmarks, and/or tibia landmark points. References axes, such as trans-epicondylar axis, femoral AP axis and posterior condylar axis, may be defined during registration for later use, such as during implant planning, component placement, and/or the like.

[0123] In some examples, registration may include a surface mapping step for patella, the femoral and tibial condyles, and/or the like, for instance, to create a virtual 3D representation of patient anatomy, generated from the collected points (for example, at block 504).

[0124] In some examples, some or all of the patient anatomical information may be measured directly. In various examples, a portion of the patient anatomical information may be estimated, predicted, or otherwise determined indirectly based on patient information, patient population databases, anatomical databases, combinations thereof, and/or the like.

[0125] Workflow 500 may include generating patient models at block 504. For example, two-dimensional (2D) and/or three-dimensional (3D) models of the patient anatomy may be generated based on the anatomical information. In some examples, the boney and soft tissue anatomy of the patient knee may be segmented and used to generate anatomical models. In some examples, the models may include the tibia, femur, and patella bones, along with ligament, tendon, and muscle models that are direct contributors to knee anatomy and function.

[0126] In various examples, the anatomical models may be or may include computergenerated virtual models of patient anatomy associated with a surgical procedure being performed via surgical system. In some examples, the virtual models may include mathematical models, graphical models, feature maps, combinations thereof, and/or the like configured to virtually represent patient anatomy within a computing system. The anatomical models may be configured for display as graphical user interface (GUI) objects on a user interface display presented to a user, such as a surgeon, as part of a surgical planning process according to various examples.

[0127] In some examples, the anatomical models may be two-dimensional (2D) models. In various examples, the anatomical models may be three-dimensional (3D) models. The anatomical models may include models of the patella, femur, tibia, a patella implant component, a femur implant component, and/or a tibial implant component alone or in combination.

[0128] In some examples, anatomical models may be generated of a patient via an anatomical model generation process the same or similar to the methods described in U.S. Patent Application Publication No. 2019/0365474, titled “Systems and Methods for Planning and Performing Image Free Implant Revision Surgery,” and/or PCT International Application No. PCT/US2020/054231, titled “Registration of Intramedullary Canal During Revision Total Knee Arthroplasty,” both of which are incorporated by reference in the present disclosure as if fully written herein. Examples are not limited in this context. For example, surgical planning processes according to some examples may generate and/or access anatomical models created via various other processes (for instance, image-based processes) capable of operating with examples described in the present disclosure.

[0129] The anatomical models may be or may include virtual representations of portions of the patient, such as the knee joint (including, for instance, the joint portions of the distal femur and/or proximal femur that interface as part of the knee joint), for example, the same or similar to the computer models of patient anatomy provided in the Navio® Surgical System from Blue Belt Technologies of Plymouth, Minnesota, United States of America). The anatomical models may be stored in a data store and/or graphically depicted via a display device and visually manipulated (for instance, rotated, moved, viewed wholly or partially transparent or semi-transparent, viewed as wireframe or similar images, and/or the like) (see, for example, FIGS. 4C-4E). Non-limiting examples of a data store may include a healthcare information system (HIS), an electronic medical record (EMR) system, a picture archiving and communication system (PACS), and/or the like

[0130] In one non-limiting example, the anatomical model generation process may include an image-free process using a point probe (for instance, an optically tracked point probe) to map the actual surface of the target bone(s). Points may be collected on the bone surfaces via “painting” by brushing or scraping the entirety of the remaining bone with the tip of the point probe. The collected points may be used to create a 3D model or surface map of the bone surfaces in the surgical planning system. In another non-limiting example, an anatomical model may be mathematically accomplished by capturing a series of Cartesian coordinates that represent the tissue surface, for instance, to generate a model fde (for instance, without limitation, *.stl, *.obj., *.fea, *.stp, *.sur, *.igs, *.wrl, *.xyz, and/or the like file formats). In an additional non-limiting example, the anatomical model generation process may include an image-based process based on diagnostic images of the subject anatomy of a patient, such as X-ray images, CT images, and/or the like (for instance, captured during block 502). Image analysis software may be used to analyze the diagnostic images to generate anatomical models, such as 2D or 3D models. In some examples, the anatomical model generation process may use a combination of image-free and image-based processes. In general, anatomical models according to some examples may be generated using various processes, including, without limitation, traditional probe painting, 3D imaging mapped with references, visual edge detection, combinations thereof, and/or the like. [0131] For example, pre- or intra-operatively, a control system, such as surgical computer 150, may create a 2D or 3D anatomical model of one or more portions of the patient, including a femur and/or tibia for a TKA or rTKA procedure. The anatomical model may be generated based on information specific to the patient, such as anatomical dimensions of the bony anatomy of interest of the patient, the mechanical and anatomical axes of the leg bones, key patella landmarks (including, without limitation, patellar medial-lateral (ML) width, superior-inferior (SI) height, AP thickness, patellar ridge, and/or the like), ends of the distal femur and proximal tibia, the epicondylar axis, the femoral neck axis, the dimensions (e.g., length) of the femur and/or tibia, the location of anatomical landmarks such as the lesser trochanter landmarks, the distal landmark, combinations thereof and/or the like.

[0132] At block 506, workflow 500 may include the morphological classification of the patella and/or other knee components. Non-limiting examples of morphological classification include patella size, shape, thickness, and/or positioning, Q-angle, soft tissues, varus/valgus knee alignment, and/or the like. In some examples, the morphological characterization may include characterization of the patella, femur (e.g., femoral trochlear groove), tibia, patellar tracking, and/or the like. For example, patella and femoral trochlear groove measurements may be automatically calculated using landmarks automatically determined according to any preceding or subsequent example (for instance, step 508).

[0133] In some examples, the morphology includes a patella morphology of the patella.

In some examples, the morphology includes a femur morphology of the femur. In some examples, the morphology includes a femur morphology of the femur and its contribution to the hip-knee-ankle angle. In some examples, the morphology includes a tibia morphology of the tibia. In some examples, the morphology includes a tibia morphology of the tibia and its contribution to the hip-knee-ankle angle. In some examples, the morphology includes a location of the tibia tubercle. In some examples, the morphology includes a location of the tibia tubercle and its effect on the quadriceps angle.

[0134] From the generated 3D model of the patella, a full morphological characterization can be performed by calculating several key patella measurements. The autolandmarking process, patellar and/or femoral landmarks, and/or measurements may be the same or substantially similar to the processes described in International Patent Application Publication No. WO 2022/076773, titled “Automatic Patellar Tracking in Total Knee Arthroplasty” and filed on October 8, 2021, the entire contents of which are incorporated by reference in the present disclosure. A non-limiting example of anatomical morphological classification may be the same or substantially similar to the processes described in the ‘549 PCT Application, the entire contents of which are incorporated by reference in the present disclosure.

[0135] At block 508, workflow 500 may include accessing patient information (or patient factors). In some examples, patient information may include age, gender, ethnicity, weight, height, body mass index (BMI), clinical characteristics, medical history (e.g., surgeries, injuries, medical records, and/or the like), and knee condition information (e.g., patient description of knee operation, knee pain, and/or the like), and/or the like. In various examples, the patient information may be obtained from a data store, such as a HIS, EMR, PACS, and/or the like. In some examples, the patient information may be obtained from a patient survey, a healthcare professional survey (i.e., concerning the patient), and/or the like.

[0136] In some examples, some or all of the patient information or factors may be measured directly. In various examples, a portion of the patient information may be estimated, predicted, or otherwise determined indirectly based on patient information, patient population databases, anatomical databases, combinations thereof, and/or the like. [0137] At block 510, workflow 500 may include a surgical simulation. In various examples, a surgical simulation may include a knee arthroplasty simulation, such as a TKA simulation. In some examples, the surgical simulation may simulate a surgery on the patient based on the patient-specific information collected and/or generated in blocks 502, 504, 506, and/or 508 of workflow 500.

[0138] In various examples, the surgical simulation may generate simulation results including information corresponding to the results of the simulated surgery based on the patient information. In some examples, the surgical simulation may include multiple simulations for different patella classifications and/or configurations, such as a simulation for a non-prepared patella, a resurfaced patella with a first set of parameters, a resurfaced patella with a second set of parameters, and so on.

[0139] The surgical simulation may include one or more femoral and/or tibial implant component types and sizes, orientations, cemented/cementless variations, alignment techniques, different surgical techniques, and/or the like. In some examples, the surgical simulation may include simulations with and without patellar preparation (for instance, patella resurfacing). For example, workflow 500 may simulate a TKA procedure with and without patella resurfacing or treatment of the native, non-prepared (i.e., nonresurfaced) patella such as lateral facetectomy or reshaping, as well as different alignment techniques of the femoral and tibial implants such as kinematic, mechanical, and physiological alignment.

[0140] FIG. 7 depicts an illustrative operating environment for a surgical planning process in accordance with the present disclosure. As shown in FIG. 7, an operating environment 700 may include a simulation platform 705. In various examples, operating environment 700 may operate to perform simulations, modeling, and/or the like for blocks 510 and/or 512 of workflow 500.

[0141] In some examples, the simulation platform 705 may include, may be, or may be the same as the LIFEMOD® KneeSIM simulation software provided by LifeModeler, Inc., San Clemente, California, including, for instance, LIFEMOD® simulation software transfer functions.

[0142] In various examples, operating environment 700 may facilitate a process of patellar characterization and morphological determination within a surgical process in which 3D geometry data is already known before operation begins. The 3D geometry of the patella could be measured directly from the available patient scan data, or it could be determined by a machine learning rubric based on digitization of only a few key patellar points. The surgical process for patellar characterization may be the same or similar to a Visionaire process for femur or tibia provided by Smith & Nephew, Inc. of Cordova,

Tennessee, United States of America. [0143] In some examples, simulation platform 705 may use or implement a set of transfer functions that simplify the mathematical operations captured by the models into one or more predictor equations. These transfer functions may be generated by performing a wide range of simulations of knee performance while varying the model input parameters which define demographic (for instance, size, height, weight, etc.), clinical (for instance, strength, ROM, etc.), medical diagnostic (for instance, wear, damage, deformity, etc.), or morphological (bone geometry, angles, anatomic dimensions, etc.), characterizations, and/or the like. For each simulation model, the resulting model responses are captured to represent post-operative kinematics, rotation, laxity, strain, and alignment, and the transfer equations may be generated to capture these relationships. Then, rather than execute the full simulation during surgery, the predictor equations are used. Further details on the use of transfer functions are described in WIPO Publication No.

2020/037308, filed August 19, 2019, entitled “Patient Specific Surgical Method and System,” the entirety of which is incorporated by reference into the present disclosure. [0144] The simulation platform 705 may receive various inputs, including, patientspecific inputs 710 determined through various processes of workflow 500. Non-limiting examples of patient-specific inputs 710 may include patient information 711 (e.g., blocks 502, 506, and 508), patient models 712 (e.g., block 504), and/or other simulation data 712 (e.g., blocks 510 and/or 512).

[0145] In some examples, the simulation platform 705 may retrieve information from a model database storing patient-specific models, population-based models (e.g., actual or estimated models generated and labeled for a population of patients, for instance, based on gender, age, surgical outcomes, and/or the like), and/or historical models (actual or estimated models of the same patient or other patients). In some examples, the simulation platform 705 may receive optimization targets 720, including, without limitation a patellar tracking target (for instance, within 1 mm pre-operative and/or less than 3 degrees of tilt), a medial retinaculum strain (for instance, < 0.1), and/or the like. The simulation platform 705 may be configured to generate a patella determination (e.g., whether or not to surgically prepare the patella) and/or preparation information (e.g., parameters for preparing the patella).

[0146] At block 512, workflow 500 may include a knee movement (knee performance or knee kinematics) simulation. For example, a knee performance simulation via simulation platform 705 may include running the knee through different movements, such as deep knee bend, gait, stair descent, and/or the like. In various examples, the one or more of the different surgical simulations may be fed into the knee performance simulation (for instance, as simulation data 713) and each different surgical simulation configuration may be simulated for kinematic results.

[0147] In various examples, a knee performance simulation may simulate movement of the post-surgery knee joint on the patient based on the patient-specific information collected and/or generated in blocks 502, 504, 506, and/or 508 and/or the simulation data block 510 of workflow 500. The knee performance simulations may be performed based on different surgical simulations of block 510 of workflow 500. For example, a plurality of surgical simulations may be generated based on different patella configurations (e.g., prepared, non-prepared, resurfaced, facetectomy, different preparation parameters, and/or the like) and results data from one or more of the surgical simulations may be input into the knee performance simulation to provide performance metrics for the different patella configurations.

[0148] In various examples, the knee performance simulation may be configured at various post-operative time periods, such as one week post-surgery, one month postsurgery, and so on. Simulations may include patient profiles (for instance, age, gender, ethnicity, BMI, and/or the like) and activities such as standing, sitting, walking, running, walking up and down stairs, twisting, and performing deep knee bends.

[0149] The knee performance simulations performed at block 514 of workflow 500 may generate various types of simulation results 720 indicating knee performance metrics, including, without limitation, kinematics/forces, tendon and bone strains, contact pressure, patellar kinematics relative to the femur, tibia, and/or implant components thereof, and/or any other type of kinematic or knee/patella performance metric.

Simulation results may be the same or similar to data generated in the system described in U.S. Patent No. 11,337,762, filed August 4, 2021 and titled “Patient-Specific Simulation Data for Robotic Surgical Planning,” the contents of which are incorporated by reference in the present disclosure.

[0150] At block 516, workflow 500 may generate one or more patella classifications or determinations. In some examples, the patella determination may be based on the simulation results. In some examples, a patella determination may include various forms of information. For example, a patella determination may include a modification determination which may have the form of a binary (“yes” or “no”) recommendation of whether the patella should remain in its native, non-prepared state for the arthroplasty procedure or whether it is recommended the patella to be modified or prepared as part of a knee arthroplasty procedure (resurfaced or not resurfaced output).

[0151] In some examples, the patella classification may be based on one or more thresholds for one or more simulation results and/or anatomical measurements. For instance, if simulation result A (i.e., a post-surgical kinematic property) has a value over threshold X, then the patella classification may be for resurfacing. In another instance, if anatomical measurement B (patella thickness) is over threshold Y, then the patella classification may be a recommendation to not resurface the patella.

[0152] In various examples, certain sets of simulation results and/or anatomical measurements may be used, with threshold values, to arrive at the patella classification. For example, if the set of simulation results A, B, and C and anatomical measurements T and U are within certain threshold values, then the patella classification is for resurfacing; otherwise, the patella classification is for not resurfacing.

[0153] Non-limiting examples of anatomical measurements that may serve as indicators for patella resurfacing may include one or more of a patella facet angle, a femoral sulcus angle, a patella thickness, a trochlea groove depth, a trochlea dysplasia. In some examples, the threshold for the patella facet angle may be an angle greater than 150 degrees, the threshold for the femoral sulcus angle may be an angle greater than 144°, the threshold for the patella thickness may be less than 19 mm for a non-resected patella, the threshold for the patella thickness may be less than 12 mm for after resection, the threshold for the trochlea groove depth may be less than 5 mm, and the trochlea dysplasia may be indicated by Dejour classification Type A-D.

[0154] For example, if during simulations with an unresurfaced patella, the patellar shift moves outside of an accepted range for native patellae during knee flexion, especially large lateral movements, the patella may be classified for resurfacing or a lateral facetectomy. Large lateral shifts in patellar tracking can lead to anterior knee pain and patellar dislocation. FIG. 8 depicts graph 810 of simulation results of medial/lateral patellar shift for a native patella with an implant system (The Journey II bi-cruciate stabilizing (JIIBCS) knee implant provided by Smith & Nephew, Inc) 815 in relation to an accepted native patella range 820 (with limits 825). In some examples, simulation results of patellar shift, such as those depicted in FIG. 8, can be used to make patella determinations according to some examples provided in the present disclosure.

[0155] In another example, if simulation data indicates that ligament strain is lower for a resurfaced patella a patella determination may classify the patella s requiring resurfacing (as opposed to a native patella or a native patella with a lateral facetectomy). In a further example, if simulation data indicates that ligament strain is lower for a resurfaced patella, especially the lateral retinaculum, primarily in early flexion a patella determination may classify the patella s requiring resurfacing (as opposed to a native patella or a native patella with a lateral facetectomy). FIG. 9 depicts graph 910 of simulation results of lateral retinaculum strain for a native patella 901, a patella with a facetectomy 902 (for instance, a lateral facetectomy), and a resurface patella 903. In some examples, simulation results for retinaculum strain, such as those depicted in FIG. 9, can be used to make patella determinations according to some examples provided in the present disclosure.

[0156] In one example, simulation data may include comparing the path and contact pressure a native patella produces on the native versus implanted femur as it goes through its normal range of motion. FIGS. 10A and 10B depict simulation results 1003 of contact of a patella (not shown) on a femur 1005 through a range of motion. The contact key or legend 1002 indicates the amount of contact of the simulation results 1003 overlaid on the simulated femur 1005. If the unresurfaced/native patella is tracking too medially or laterally, an analysis can help correct its path and determine if resurfacing is needed. A further analysis can then evaluate whether the patient would benefit more from a facetectomy, and if so, which type of facetectomy would be most suitable. For instance, contact simulation data may be generated for different types of facetectomies. For example, FIG. 10B depicts simulations 1020, 1021, and 1022 for no facetectomy, a lateral facetectomy, and a lateral facetectomy at a 45 degree cut, respectively.

Accordingly, in some examples, simulation results for patella-femoral contact, such as those depicted in FIGS. 10A and 10B, can be used to make patella determinations according to some examples provided in the present disclosure.

[0157] In some examples, once the patella has been classified and a facetectomy has been performed or deemed unnecessary, a final analysis can be conducted to compare different types of implants. FIG. 11 depicts simulation results 1003 of contact of a patella (not shown) on a femur 1005 through a range of motion for two different implant types 1030 (JIIBCS) and 1031 (P.F.C. Sigma). For example, contact pressure surrounding the intercondylar box during flexion may be simulated because it is relevant to patellar crepitus, which can potentially cause anterior knee pain. Other types of simulations may be performed according to various examples.

[0158] If the modification determination indicates that the patella should be modified or prepared, the patella classification may include preparation information corresponding with various characteristics of a recommended patella preparation procedure. For example, preparation information may include one or more recommended preparation processes, such as reshaping, resurfacing, denervation, facetectomy, and/or the like. The preparation information may include preparation parameters, for instance, detailing the operating characteristics of the patella preparation process, such as an amount of bone to remove, the location of reshaping, angles or radii of bone cuts, and/or the like.

[0159] Given all of the input factors and models, the patella evaluation process with simulations may output one or more optimal outcome predictions, for instance, to assist surgeons in determining the best course of action for that particular patient.

[0160] In various examples, block 516 may generate a plurality of determinations, for instance, scored, ranked, or classified based on various factors, such as patient risk, outcomes, and/or the like. For instance, for a patient, a first patella determination may recommend retaining the native, non-prepared patella and a second patella determination may recommend resurfacing the patella with a set of parameters which may include a selected implant. The patella evaluation process may indicate various factors associated with first patella determination approach and the second patella determination approach, such as recovery time, outcome risks (e.g., pain, risk of implant failure), kinematic results (e g., estimated knee flexibility, mobility, and/or the like) and other factors. In this manner, a surgeon and patient may evaluate the risks and costs associated with different approaches using accurate models and simulation predictions. For instance, a first recommended approach may indicate a longer recovery time with a greater risk of failure, but with increased mobility and kinematic performance, and a second approach may indicate a shorter recovery time, low risk of pain, but with decreased knee mobility. A patient and surgeon may use this information to arrive at a surgical plan based on accurate and precise surgical modeling.

[0161] In some examples, the evaluation process of workflow 500 may include various evaluation parameters. The evaluation parameters may cause the evaluation process to be biased toward or away from certain preparation determinations. The evaluation parameters may be specified based on patient conditions, risk appetite, patient demographic information (e.g., more conservative for patients over a certain age, more focused on improved kinematic performance for patients under a certain age, and/or the like). For example, the evaluation process for a first patient may be biased toward not preparing the patella, while the evaluation process for a second patient may be biased toward resurfacing the patella.

[0162] For example, if a patient had pre-op anterior knee pain or if a bone scan showed a “hot patella,” the evaluation process may have more strict criteria for patella measures with the simulated TKA to recommend leaving the patella unresurfaced. In general, a “hot patella” refers to a tracer uptake in nuclear medicine imaging at the patella, which shows the possibility of osteoarthritis, increased pressures, and other painful symptoms near the patellof emoral joint.

[0163] In the event of a patella classification to not resurface the patella, the patella classification may also recommend whether the patella should have a lateral facetectomy, reshaping, denervation, and/or other preparation process.

[0164] In some examples, a patella classification recommending patella preparation may include preparation information providing parameters for the preparation. For example, for lateral facetectomy or patella reshaping, preparation information may include an amount of bone to remove, angles or radii of bone cuts, and/or the like.

[0165] In various examples, preparation information may include surgical processes, such as enabling methods to accomplish the patella preparations. Such preparation information may include, bone resections, cutting guide use and specifications, patient specific cutting guides that reference the bone or surrounding soft tissue, robotic surgery processes (e.g., using a burr, saw, reamer, laser, or other controlled bone removal methods), and/or the like.

[0166] The patient specific information could also be fed into regression equations or look up tables based on already completed simulations allowing faster intraoperative feedback based on classification of patient anatomy, which may involve identifying the features of the patella through statistical shape modeling or other bone morphing methods to quantify the native patella anatomy for input to a regression model. Examples are not limited in this context. [0167] FIG. 12 depicts simulation results for prepared and non-prepared (native) patellae. Graph 1210 depicts simulated results for non-prepared patellae 1201-903 and graph 1211 depicts simulated results for patellae 1201-903 after a preparation procedure, in particular, a lateral facetectomy.

[0168] FIG. 13 depicts an illustrative operating environment for a surgical planning process in accordance with the present disclosure. As shown in FIG. 13, an operating environment 1300 may include a patella evaluation system 1301. Evaluation system 1301 may be or may include a computing device and associated processing circuitry, memory, and/or the like, for instance, the same or similar to surgical computer 150. In various examples, evaluation system 1301 may be a computer device for performing a patella evaluation process according to the present disclosure.

[0169] Evaluation system 1301 may store or access a computational model 1302. In some examples, computational model 1302 may be or may include various types of computational models including, without limitation, regression models, lookup tables, transfer functions, simulation models, virtual anatomical models, artificial intelligence (Al) and machine learning (ML) (AI/ML) models, neural networks (ANN), convoluted neural network (CNN), combinations thereof, variations thereof, and/or the like.

[0170] In various examples, computational model 1302 may be configured to receive patient-specific input (e.g., patella information 1304 and/or patient information 1306) associated with evaluating a patient’s patella and generating output in the form of a patella classification 1308 in the form of a binary (“yes” or “no”) recommendation of whether a patella is recommended to be modified or prepared as part of a knee arthroplasty procedure. In various examples, patella information may include any virtual models, morphological information, simulated knee arthroplasty, knee movement or performance simulations, simulation results, and/or the like (for instance, steps 502-512 of FIG. 5).

[0171] If computational model 1302 outputs a patella classification 1308 recommending preparation of the patient patella, computational model 1302 may generate preparation information 1310. In some examples, preparation information 1310 may include information, parameters, data, instructions, recommendations, and/or the like for performing the patella preparation, including, without limitation, recommended preparation procedures (e.g., resurfacing, facetectomy, reshaping, etc.) and recommended instructions for performing the preparation procedures (e.g., location and/or amount of resurfacing and/or reshaping, cutting information, angles, dimensions, tools, surgical procedures, and/or the like).

[0172] In various examples, patella information 1304 may be input into the patella evaluation system 1301 and provided to computational model 1302. In general, patella information 1304 may include any information associated with the patella of the patient that is the subject of the patella evaluation process. Patella information 1304 may include patella anatomical or physical characteristics, such as dimensions, facets, and/or the like and functional characteristics, such as location, movement, etc. during knee extension/flexion, tension, pressure, patient pain, kinematic information, performance information, and/or the like. In some examples, patella information 1304 may include virtual models and/or model information of a patient patella. In various examples, patella information 1304 may include information associated with other knee structures, such as the femur, tibia, muscles, tendons, femoral implant components, tibial implant components, and/or the like. In some examples, patella information 1304 may include virtual models and/or model information of a patient femur, tibia, knee joint, tendons, ligaments, muscles, and/or the like. In general, patella information 1304 may include any information relevant to evaluating a patella according to some examples.

[0173] In various examples, patient information 1304 may be input into the patella evaluation system 1301 and provided to computational model 1302. In general, patient information 1304 may include any information associated with the subject patient that may be relevant to evaluating the patient’s patella, surgical outcomes, and/or the like. Non-limiting examples of patient information 1304 may include age, gender, physical characteristics (e.g., height, weight, etc.), medical history, knee condition (e.g., patient medical evaluation), injuries, surgeries, and/or the like.

[0174] Computational model 1302 may be trained via computational model training module 1320 to receive patella information 1304 and patient information 1306 of a patient and generate a patella classification 1308. In general, patella classification 1308 includes a prediction, estimation, recommendation, and/or the like of one or more optimal preparations for the patella for the subject knee arthroplasty procedure. Patella classification 1308 indicates a recommendation for the optimal outcome for the arthroplasty procedure and the patient with respect to the patella, and preparation of the patella in particular. [0175] Preparation of the patella is an important consideration for the successful outcome of a knee arthroplasty procedure. As a non-limiting example, referring to graphs 1210 and 1211 of FIG. 12, patella 1201 was an outlier and potentially a painful unresurfaced patella in its native state, however, as shown in graph 1211, prepared with a lateral facetectomy is similar to patellae 1202 and 1203 and thus more likely to be a successful unresurfaced patella.

[0176] Accordingly, the output of evaluation system 1301, particularly using a trained computational model 1302, may provide a practical application and real -world results for patients. In addition, evaluation system 1301 provides an improvement in the field of knee arthroplasty, and in particular, computer-based surgical systems through the ability of evaluation system 1301 to provide patella classifications 1308 in a manner that is not possible using conventional computing systems. Existing computer-based surgical systems, simulation systems (including systems that simulate the patella), and/or the like are not capable of providing a patella classification 1308 according to some examples. [0177] Computational model training 1320 may be or may include a computer-based process for training computational model 1302 using training data 1332. Training data 1332 may include labelled and/or unlabeled data. Training data 1332 may receive and/or transform medical information 1330 into training data for training computational model 1302. Medical information 1330 may include computer-generated data (e.g., predictions, recommendations, classifications, etc.) such as patella classifications 1308, preparation information 1310, simulation data 1312 (for instance, from simulation platform 705) modified by real-world outcomes based on real patients and/or labeled by medical professionals.

[0178] For example, training data 1332 may be generated pairing patella classifications 1308 of one or more populations of patients with corresponding real-world patient outcomes (for instance, in a medical database of medical information 1330) indicating the accuracy of the patella classifications 1308. Training data 1332 may be used to train computational model 1302 to accurately predict patella classifications 1308 for particular patella information 1304 and/or patient information 1306. Accordingly, computational model 1302 can “learn” via AI/ML processes combined with training data 1332 to correctly or substantially correctly diagnose a patient and provide a recommended patella classification.

[0179] The foregoing description has broad application. While the present disclosure refers to certain some examples, numerous modifications, alterations, and changes to the described examples are possible without departing from the sphere and scope of the present disclosure, as defined in the appended claim(s). Accordingly, it is intended that the present disclosure not be limited to the described examples. Rather these examples should be considered as illustrative and not restrictive in character. All changes and modifications that come within the spirit of the disclosure are to be considered within the scope of the disclosure. The present disclosure should be given the full scope defined by the language of the following claims, and equivalents thereof. The discussion of any example is meant only to be explanatory and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples. In other words, while illustrative examples of the disclosure have been described in detail herein, it is to be understood that the inventive concepts may be otherwise variously embodied and employed, and that the appended claims are intended to be construed to include such variations, except as limited by the prior art. Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the disclosure belongs.

[0180] Directional terms such as top, bottom, superior, inferior, medial, lateral, anterior, posterior, proximal, distal, upper, lower, upward, downward, left, right, longitudinal, front, back, above, below, vertical, horizontal, radial, axial, clockwise, and counterclockwise) and the like may have been used herein. Such directional references are only used for identification purposes to aid the reader’s understanding of the present disclosure. For example, the term “distal” may refer to the end farthest away from the medical professional/operator when introducing a device into a patient, while the term “proximal” may refer to the end closest to the medical professional when introducing a device into a patient. Such directional references do not necessarily create limitations, particularly as to the position, orientation, or use of this disclosure. As such, directional references should not be limited to specific coordinate orientations, distances, or sizes, but are used to describe relative positions referencing particular examples. Such terms are not generally limiting to the scope of the claims made herein. Any example or feature of any section, portion, or any other component shown or particularly described in relation to any preceding or subsequent example of similar sections, portions, or components herein may be interchangeably applied to any other similar example or feature shown or described herein.

[0181] It should be understood that, as described herein, an “example” (such as illustrated in the accompanying Figures) or “example” (such as “in some examples”) may refer to an illustrative representation of an environment or article or component in which a disclosed concept or feature may be provided or embodied, or to the representation of a manner in which just the concept or feature may be provided or embodied. However, such illustrated examples are to be understood as examples (unless otherwise stated), and other manners of embodying the described concepts or features, such as may be understood by one of ordinary skill in the art upon learning the concepts or features from the present disclosure, are within the scope of the disclosure. Furthermore, references to “one example” of the present disclosure are not intended to be interpreted as excluding the existence of additional examples that also incorporate the recited features.

[0182] In addition, it will be appreciated that while the Figures may show one or more examples of concepts or features together in a single example of an environment, article, or component incorporating such concepts or features, such concepts or features are to be understood (unless otherwise specified) as independent of and separate from one another and are shown together for the sake of convenience and without intent to limit to being present or used together. For instance, features illustrated or described as part of one example can be used separately, or with another example to yield a still further example. Thus, it is intended that the present subject matter covers such modifications and variations as come within the scope of the appended claims and their equivalents. [0183] As used herein, an element or step recited in the singular and proceeded with the word “a” or “an” should be understood as not excluding plural elements or steps, unless such exclusion is explicitly recited. It will be further understood that the terms “comprises” and/or “comprising,” or “includes” and/or “including” when used herein, specify the presence of stated features, regions, steps, elements and/or components, but do not preclude the presence or addition of one or more other features, regions, integers, steps, operations, elements, components and/or groups thereof.

[0184] The phrases “at least one”, “one or more”, and “and/or”, as used herein, are open- ended expressions that are both conjunctive and disjunctive in operation. The terms “a” (or “an”), “one or more” and “at least one” can be used interchangeably herein.

[0185] Connection references (e.g., engaged, attached, coupled, connected, and joined) are to be construed broadly and may include intermediate members between a collection of elements and relative to movement between elements unless otherwise indicated. As such, connection references do not necessarily infer that two elements are directly connected and in fixed relation to each other. Identification references (e.g., primary, secondary, first, second, third, fourth, etc.) are not intended to connote importance or priority but are used to distinguish one feature from another. The drawings are for purposes of illustration only and the dimensions, positions, order and relative to sizes reflected in the drawings attached hereto may vary.

[0186] The foregoing discussion has been presented for purposes of illustration and description and is not intended to limit the disclosure to the form or forms disclosed herein. For example, various features of the disclosure are grouped together in one or more examples or configurations for the purpose of streamlining the disclosure.

However, it should be understood that various features of the certain some examples or configurations of the disclosure may be combined in alternate examples or configurations. Moreover, the following claims are hereby incorporated into this Detailed Description by this reference, with each claim standing on its own as a separate example of the present disclosure.

Claims

CLAIMS What is claimed is:

1. A computer-implemented method for planning a knee arthroplasty procedure, comprising, via a processor of a computing device: accessing anatomical information of a knee joint of a patient, the anatomical information comprising patella information of a patella of the patient and femoral information of a femur of the patient; generating a virtual model of the knee joint based on the anatomical information, the virtual model comprising a patella model and a femur model; generating a simulated post-surgical knee via performing a simulated knee arthroplasty procedure on the virtual model; determining simulation results via emulating performance of the simulated post- surgical knee; and determining a patella classification based on the simulation results, the patella classification comprising a patella preparation indicator of whether the patella should be resurfaced as part of the knee arthroplasty procedure.

2. The computer-implemented method of claim 1, the patella classification determined based on one or more patella factors, the patella factors comprising one or more of patella size, patella shape, and patella thickness.

3. The computer-implemented method of claim 1, the virtual model generated based on at least one patient factor, the at least one patient factor comprising at least one of varus/valgus knee alignmentjoint line information, quadriceps angle (Q-angle) information, native femur anatomy, femoral trochlear groove information, or native tibia anatomy.

4. The computer-implemented method of claim 1, the virtual model including virtual knee tendon, ligament, and muscle elements comprising at least one of anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), lateral collateral ligament (LCL), quadriceps tendon patellar tendon, and quadriceps femoris.

5. The computer-implemented method of claim 1, further comprising determining patella resurfacing parameters responsive to the patella classification indicating patella resurfacing, the patella resurfacing parameters indicating surgical characteristics of a patella resurfacing procedure.

6. The computer-implemented method of claim 5, the patella resurfacing parameters comprising one or more of bone removal amount, reshaping location, bone cut angle, bone cut radii, or retained thickness.

7. The computer-implemented method of claim 1, the patella classification comprising at least one of facetectomy, denervation, or reshaping.

8. The computer-implemented method of claim 1, the simulated post-surgical model comprising at least one of a femoral implant or a tibial implant having implant characteristics, the implant characteristics comprising at least one of a size and a position, the simulation results determined based on the implant characteristics of the femoral implant or the tibial implant.

9. The computer-implemented method of claim 1, the patella information comprising a condition factor indicating pre-surgical patella issues, the patella classification biased toward stricter criteria for patella resurfacing based on the condition factor.

10. The computer-implemented method of claim 1, further comprising characterizing a knee morphology of the knee joint, the knee morphology comprising a patella morphology of the patella and a femur morphology of the femur, the virtual model generated based on the knee morphology.

11. A computer-assisted surgical system for planning a knee arthroplasty procedure, comprising, the system comprising: a computing device comprising at least one processor and a storage device in communication with the at least one processor, the storage device storing instructions that, when executed by the at least one processor, cause the at least one processor to: access patella information of a patient, the patella information comprising: anatomical information of a patella of a knee joint of the patient; a virtual model of the knee joint based on the anatomical information, the virtual model comprising a patella model and a femur model; execute a machine learning (ML) model to determine a patella classification, the ML model trained: using training data comprising patella classifications of a population of patients, to receive the patella information as input, and to generate a patella classification as output, the patella classification comprising a patella preparation indicator of whether the patella should be resurfaced as part of the knee arthroplasty procedure.

12. The computer-assisted surgical system of claim 11, the patella classification determined based on one or more patella factors, the patella factors comprising one or more of patella size, patella shape, and patella thickness.

13. The computer-assisted surgical system of claim 11, the patella information comprising a virtual model of the knee joint generated based on the anatomical information and at least one patient factor, the at least one patient factor comprising at least one of varus/valgus knee alignmentjoint line information, quadriceps angle (Q- angle) information, native femur anatomy, femoral trochlear groove information, or native tibia anatomy.

14. The computer-assisted surgical system of claim 11, the virtual model including virtual knee tendon, ligament, and muscle elements comprising at least one of anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), lateral collateral ligament (LCL), quadriceps tendon patellar tendon, and quadriceps femoris.

15. The computer-assisted surgical system of claim 11, the ML model further trained to generate patella resurfacing parameters as output responsive to the patella classification indicating patella resurfacing, the patella resurfacing parameters indicating surgical characteristics of a patella resurfacing procedure.

16. The computer-assisted surgical system of claim 15, the patella resurfacing parameters comprising one or more of bone removal amount, reshaping location, bone cut angle, bone cut radii, or retained thickness.

17. The computer-assisted surgical system of claim 11, the patella classification comprising at least one of facetectomy, denervation, or reshaping.

18. The computer-assisted surgical system of claim 11, the patella information comprising a simulated post-surgical model generated via performing a simulated knee arthroplasty procedure on a virtual model of the knee joint, the post-surgical model comprising at least one of a femoral implant or a tibial implant having implant characteristics, the implant characteristics comprising at least one of a size and a position, the simulation results determined based on the implant characteristics of the femoral implant or the tibial implant.

19. The computer-assisted surgical system of claim 11, the patella information comprising a condition factor indicating pre-surgical patella issues, the patella classification biased toward stricter criteria for patella resurfacing based on the condition factor.

20. The computer-assisted surgical system of claim 11, the patella information comprising a knee morphology of the knee joint, the knee morphology comprising a patella morphology of the patella and a femur morphology of the femur, the virtual model generated based on the knee morphology.