[go: up one dir, main page]

WO2025226549A1 - Visualisation et planification d'arthroplastie de l'épaule - Google Patents

Visualisation et planification d'arthroplastie de l'épaule

Info

Publication number
WO2025226549A1
WO2025226549A1 PCT/US2025/025427 US2025025427W WO2025226549A1 WO 2025226549 A1 WO2025226549 A1 WO 2025226549A1 US 2025025427 W US2025025427 W US 2025025427W WO 2025226549 A1 WO2025226549 A1 WO 2025226549A1
Authority
WO
WIPO (PCT)
Prior art keywords
motion
prosthesis
joint
patient
range
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/US2025/025427
Other languages
English (en)
Inventor
Carlos O. Alva
Kevin P. Knox
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Howmedica Osteonics Corp
Original Assignee
Howmedica Osteonics Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Howmedica Osteonics Corp filed Critical Howmedica Osteonics Corp
Publication of WO2025226549A1 publication Critical patent/WO2025226549A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
    • A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
    • A61B5/4576—Evaluating the shoulder
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods
    • A61B2017/00017—Electrical control of surgical instruments
    • A61B2017/00022—Sensing or detecting at the treatment site
    • A61B2017/00084—Temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods
    • A61B2017/00017—Electrical control of surgical instruments
    • A61B2017/00115—Electrical control of surgical instruments with audible or visual output
    • A61B2017/00119—Electrical control of surgical instruments with audible or visual output alarm; indicating an abnormal situation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B17/00—Surgical instruments, devices or methods
    • A61B2017/00681—Aspects not otherwise provided for
    • A61B2017/00734—Aspects not otherwise provided for battery operated
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/101—Computer-aided simulation of surgical operations
    • A61B2034/102—Modelling of surgical devices, implants or prosthesis
    • A61B2034/104—Modelling the effect of the tool, e.g. the effect of an implanted prosthesis or for predicting the effect of ablation or burring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/101—Computer-aided simulation of surgical operations
    • A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
    • A61B2034/108—Computer aided selection or customisation of medical implants or cutting guides
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/20—Surgical navigation systems; Devices for tracking or guiding surgical instruments, e.g. for frameless stereotaxis
    • A61B2034/2046—Tracking techniques
    • A61B2034/2048—Tracking techniques using an accelerometer or inertia sensor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
    • A61B34/25—User interfaces for surgical systems

Definitions

  • a total shoulder arthroplasty involves implanting a humeral prosthesis on a proximal end of a humerus of a patient’s shoulder joint and a corresponding glenoid prosthesis on the glenoid of a scapula of the patient’s shoulder joint.
  • TSA One goal of a TSA is to restore the range of motion of the patient’s shoulder joint, which may have been diminished because of arthritis, deformation of the humerus or scapula, or other causes.
  • Humeral prostheses and glenoid prostheses having different parameters e.g., sizes, shapes, eccentricities, etc.
  • the parameters of the humeral prosthesis and glenoid prosthesis need to be carefully selected during preoperative planning of a TSA.
  • This disclosure describes techniques for using sensors included in humeral or glenoid prostheses for refining motion (RoM) prediction models for total shoulder arthroplasties.
  • a RoM prediction model generates a predicted range of motion for a particular patient given the patient’s anatomy, such as the patient’s bony or soft tissue anatomy, parameters of the humeral and glenoid prosthesis, and other parameters.
  • a surgical planning system may refine a RoM prediction model based on an actual motion of the shoulder joint as determined based on data from sensors included in glenoid and/or humeral prostheses. For instance, the surgical planning system may refine the RoM prediction model based on differences between an actual range of motion and a predicted range of motion of a shoulder joint of a patient.
  • a surgical planning system may apply a RoM prediction model to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient.
  • the surgical planning system refine the RoM prediction model so that the RoM prediction model generates better predicted ranges of motion for an individual patient.
  • the surgical planning system refines a RoM model that generates predicted ranges of motion for a population of patients.
  • the surgical planning system may determine post-operative activities and interventions based on differences between actual and predicted ranges of motion.
  • the surgical planning system may obtain joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis.
  • the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint.
  • the joint motion data provides information regarding an actual range of motion of the shoulder joint during a test of a range of motion of the shoulder joint.
  • the surgical planning system may determine, based on the joint motion data, differences between the actual range of motion and the predicted range of motion.
  • the surgical planning system may refine the RoM prediction model based on the differences.
  • the surgical planning system outputs feedback data based on the differences between the actual range of motion and the predicted range of motion.
  • Accuracy of the RoM prediction model may be important for multiple reasons.
  • the use of sensors that are included in the protheses may increase accuracy of the determination of the true range of motion, and therefore be useful in determining and resolving discrepancies between predicted ranges of motion and actual ranges of motion.
  • this disclosure describes a computer-implemented method comprising: applying, by one or more processors implemented in circuitry, a model to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient; obtaining, by the one or more processors, joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis, wherein the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint, and the joint motion data provides information regarding an actual range of motion of the shoulder joint; and refining, by the one or more processors, the model based on the joint motion data.
  • this disclosure describes a computing system comprising: a storage system; and one or more processors implemented in circuitry and communicatively coupled to the storage system, the one or more processors configured to apply a model to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient; obtain joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis, wherein the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint, and the joint motion data provides information regarding an actual range of motion of the shoulder joint; and refine the model based on the joint motion data.
  • this disclosure describes one or more non-transitory computer-readable storage media including instructions stored thereon that, when executed, cause a computing system to apply a model to generate, based on patient- specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient; obtain joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis, wherein the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint, and the joint motion data provides information regarding an actual range of motion of the shoulder joint; and refine the model based on the joint motion data.
  • FIG.1 is a conceptual diagram illustrating an example computing system in which one or more techniques of this disclosure may be performed.
  • FIG. 2 is a block diagram illustrating example components of a prosthesis, in accordance with one or more techniques of this disclosure.
  • FIG.3 is a schematic diagram of a glenoid prosthesis and a humeral prosthesis, in accordance with one or more techniques of this disclosure.
  • FIG. 13 is a schematic diagram of a glenoid prosthesis and a humeral prosthesis, in accordance with one or more techniques of this disclosure.
  • FIG. 4 is a conceptual diagram illustrating an example user interface showing a current position of a shoulder joint, in accordance with one or more techniques of this disclosure.
  • FIG. 5 is a conceptual diagram illustrating an example user interface showing a current position of a shoulder joint in which a possible dislocation has occurred, in accordance with one or more techniques of this disclosure.
  • FIG. 6 is a conceptual diagram illustrating an example user interface showing a current position of a shoulder joint in which a possible impingement has occurred, in accordance with one or more techniques of this disclosure.
  • FIG.7 is a flowchart illustrating an example operation in accordance with one or more techniques of this disclosure. [0017] FIG.
  • FIG. 8 is a conceptual diagram illustrating an example architecture of a neural network for determining a 6-degrees of freedom pose of a prosthesis, in accordance with one or more techniques of this disclosure.
  • FIG.9 is a conceptual diagram illustrating an example system for training a neural network, in accordance with one or more techniques of this disclosure.
  • DETAILED DESCRIPTION [0019] In a total shoulder arthroplasty, a surgeon replaces an articulating surface of a glenoid fossa of a scapula of a patient’s shoulder with a glenoid prosthesis and an articulating surface of a humerus of the patient’s shoulder with a humeral prosthesis.
  • a patient may undergo a total shoulder arthroplasty for a variety of reasons. For example, the patient may be experiencing pain or joint instability due to bone erosion or trauma. Bone erosion may be caused by arthritis or other processes.
  • Bone erosion may be caused by arthritis or other processes.
  • One goal of a total humeral arthroplasty is to restore a specific range of motion to the shoulder joint. Limitations on the range of motion may occur due to impingement between bones, prosthesis selection, and/or soft tissue tightness.
  • a surgical planning system may help a surgeon determine a predicted range of motion of the patient’s shoulder joint given the shape of the patient’s bones and various parameters of the humeral prosthesis and the glenoid prosthesis.
  • the surgical planning system may display an animation in which a patient-specific humeral model with a virtually implanted humeral prosthesis moves relative to a patient-specific scapula model with a virtually implanted glenoid prosthesis.
  • the animation may also show scapular motion as a bias in overall arm motion.
  • the surgical planning system may display the animation using different values of parameters of the humeral prosthesis and glenoid prosthesis. For instance, different types, sizes, and positions of the humeral prosthesis and glenoid prosthesis may be used. In this way, the surgeon can evaluate the effects of different values of the parameters of the humeral prosthesis and glenoid prosthesis on the range of motion of the shoulder joint.
  • the actual range of motion achieved by the shoulder joint of a patient may differ from the predicted range of motion.
  • the surgeon may modify the humerus or scapula in a way that differs from the surgical plan.
  • one or more characteristics of the patient’s soft tissue may differ from preoperatively assumed characteristics. Differences from the predicted range of motion may negatively impact the patient’s quality of life, the functionality of the prostheses, and may lead to higher rates of prosthesis failure. Differences from the predicted range of motion may also lead to premature wear on the protheses and loosening of the prostheses.
  • This disclosure describes computer-implemented techniques that apply a range of motion (RoM) prediction model to estimate ranges of motion of shoulder joints of patient.
  • the predicted ranges of motion may be used preoperatively, intraoperatively, and/or postoperatively.
  • a surgical planning system may apply a RoM prediction model to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient.
  • the surgical planning system may obtain joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis.
  • the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint.
  • the joint motion data provides information regarding an actual range of motion of the shoulder joint during a test of a range of motion of the shoulder joint.
  • the surgical planning system may determine, based on the joint motion data, whether the actual range of motion is consistent with the predicted range of motion.
  • the surgical planning system may refine the model based on the differences.
  • the surgical planning system may output feedback data based on the differences between the actual range of motion and the predicted range of motion.
  • FIG. 1 is a conceptual diagram illustrating an example system 100 in which one or more techniques of this disclosure may be performed.
  • system 100 includes a computing system 102, a humeral prosthesis 104, and glenoid prosthesis 106.
  • Computing system 102 is configured to assist one or more users in generating a surgical plan for an orthopedic surgery, such as a total shoulder arthroplasty (e.g., an anatomical total shoulder arthroplasty or a reverse total shoulder arthroplasty) or other type of surgery.
  • Humeral prosthesis 104 is a prosthesis configured to be implanted on a patient’s humerus.
  • Glenoid prosthesis 106 is a prosthesis configured to be implanted on a patient’s scapula.
  • Computing system 102 may include one or more computing devices.
  • computing system 102 includes a personal computer used by a surgeon. In this example, the personal computer may generate a surgical plan without interaction with other computing devices.
  • computing system 102 includes a server device and a client device (e.g., a personal computer).
  • the server device may generate a surgical plan based on input initially received via the client device.
  • one or more computing devices of computing system 102 may output user interfaces for display to a user and may receive, directly or indirectly, indications of user input.
  • Computing system 102 includes one or more processors 108, a storage system 110, a communication interface 112, and a display 114.
  • computing system 102 may include more, fewer, or different components. The components of computing system 102 may be in one or more computing devices.
  • processors 108 may be in a single computing device or distributed among multiple computing devices of computing system 102
  • storage system 110 may be in a single computing device or distributed among multiple computing devices of computing system 102, and so on.
  • computing system 102 is a personal computer, a system of computing devices, one or more server devices, or a system comprising one or more other types of computing devices.
  • Processors 108, storage system 110, communication interface 112, and display 114 are communicatively coupled.
  • Processors 108 may be implemented in circuitry and include one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), hardware, or any combinations thereof.
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • processors 108 may be implemented as fixed-function circuits, programmable circuits, or a combination thereof.
  • Fixed-function circuits refer to circuits that provide particular functionality and are preset on the operations that can be performed.
  • Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functionality in the operations that can be performed.
  • programmable circuits may execute software or firmware that cause the programmable circuits to operate in the manner defined by instructions of the software or firmware.
  • Fixed-function circuits may execute software instructions (e.g., to receive parameters or output parameters), but the types of operations that the fixed-function circuits perform are generally immutable.
  • Processors 108 may include arithmetic logic units (ALUs), elementary function units (EFUs), digital circuits, analog circuits, and/or programmable cores, formed from programmable circuits.
  • ALUs arithmetic logic units
  • EFUs elementary function units
  • storage system 110 may store the object code of the software that processors 108 receives and executes, or another memory within processors 108 (not shown) may store such instructions. Examples of the software include software designed for surgical planning.
  • Processors 108 may perform the actions ascribed in this disclosure to processors 108.
  • Processors 108 may output data (e.g., a user interface, models, etc.) for display. Outputting data for display may include one or more of processors 108 generating and sending signals to a display device (e.g., display 114) that the display device can directly use to display the data. Outputting data for display may include one or more of processors 108 outputting data for transmission to another computing device (e.g., another computing device of computing system 102) that processes the data to generate signals that a display device (e.g., display 114) may directly use to display the data.
  • Processors 108 may receive indications of user input from one or more users.
  • Processors 108 may receive an indication of user input directly from a user input device (e.g., keyboard, mouse, touchscreen, etc.). For instance, in an example where computing system 102 is implemented on a single computing device, processors 108 may receive the indications of user input from one or more user input devices of the computing device. In other examples, processors 108 may receive the indications of user input by way of one or more computing devices. For instance, in an example where computing system 102 is implemented using a server device and a client device and processors 108 are located in the server device, processors 108 may receive indications of the user input from the client device. For example, processors 108 may receive an indication from the client device that the user has selected a displayed element, typed specific text, and so on.
  • a user input device e.g., keyboard, mouse, touchscreen, etc.
  • Storage system 110 may store various types of data used by processors 108.
  • Storage system 110 may include any of a variety of memory devices, such as dynamic random access memory (DRAM), including synchronous DRAM (SDRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM), or other types of memory devices.
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • MRAM magnetoresistive RAM
  • RRAM resistive RAM
  • Examples of display 114 include a liquid crystal display (LCD), a plasma display, an organic light emitting diode (OLED) display, or another type of display device. Display device 114 may be positioned in a user’s office, an operating room, or another location.
  • Communication interface 112 allows computing system 102 to output data and instructions to and receive data and instructions from a medical imaging system, humeral prosthesis 104, glenoid prosthesis 106, or other devices via one or more communication links or networks.
  • Communication interface 112 may include hardware circuitry that enables computing system 102 to communicate (e.g., wirelessly or using wires) with other computing systems and devices.
  • Example networks may include various types of communication networks including one or more wide-area networks, such as the Internet, local area networks, and so on. In some examples, the network may include wired and/or wireless communication links.
  • storage system 110 stores a surgical planning system 116. In other examples, storage system 110 may store more, fewer, or different types of data or units.
  • Surgical planning system 116 may comprise instructions that are executable by processors 108. For ease of explanation, this disclosure may describe surgical planning system 116 as performing various actions when processors 108 execute instructions of surgical planning system 116. [0033] Surgical planning system 116 is a system that may help a surgeon plan an orthopedic surgery as part of a pre-operative planning process. Surgical planning system 116 may be an instance of a computer-assisted orthopedic surgery (CAOS) system or a computer-assisted surgical system (CASS). In some examples, surgical planning system 116 may also assist users during a surgery.
  • CAOS computer-assisted orthopedic surgery
  • CASS computer-assisted surgical system
  • surgical planning system 116 may also assist users during a surgery.
  • surgical planning system 116 may output navigation information to one or more devices (e.g., monitors, tablet computers, head-mounted displays, etc.) to a user during a surgery to help the user execute a surgical plan.
  • surgical planning system 116 may also assist users after a surgery.
  • surgical planning system 116 may provide information to assist with recovery, physical therapy, or other postoperative activities.
  • Storage system 110 may also store a training system 132.
  • Training system 132 may train ML models, such as ML models used in humeral prosthesis 104 and/or glenoid prosthesis 106, or ML models used by surgical planning system 116. In other examples, training system 132 is implemented in a different computing system from computing system 102.
  • Humeral prosthesis 104 includes an articulation element and a base element.
  • the articulation element of humeral prosthesis 104 provides an articulation surface that slides over a corresponding articulation surface of glenoid prosthesis 106.
  • the articulation surface may be convex or concave.
  • the base element of humeral prosthesis 104 may secure humeral prosthesis 104 to the patient’s humerus.
  • Glenoid prosthesis 106 includes a baseplate and an articulation element.
  • glenoid prosthesis 106 also includes an augment element.
  • the baseplate may comprise a disk-shaped metal element. In other examples, the baseplate may have other shapes.
  • the augment element may be attached to a bone-facing side of the baseplate.
  • the baseplate may define one or more screw holes. After the placement of the baseplate and augment element onto the patient’s scapula, the surgeon may fix the baseplate and augment element to the patient’s scapula by passing fixation screws into the patient’s scapula through the screw holes of the baseplate. In some instances, one or more of the fixation screws also pass through corresponding screw holes defined in the augment element.
  • a surgeon prepares the patient’s humerus and scapula to receive humeral prosthesis 104 and glenoid prosthesis 106. For example, the surgeon may resect a head of the patient’s humerus along a preplanned cutting plane. In some examples, the surgeon may sound, punch, and/or compact cancellous bone tissue within an intermedullary canal of the humerus to make room for a stem of humeral prosthesis 104.
  • the surgeon may ream one or more areas of the glenoid fossa, form a hole in the scapula for a central fixation element (e.g., a peg or keel) of glenoid prosthesis 106 or otherwise modify the scapula to receive glenoid prosthesis 106.
  • preparing the humerus or scapula may involve removing osteophytes from the humerus or scapula.
  • the parameters of humeral prosthesis 104 and glenoid prosthesis 106, as well as the actual shapes of the prepared humerus and scapula, may have effects on the range of motion that the patient will be able to achieve after completion of the total shoulder arthroplasty.
  • the range of motion of the shoulder joint refers to the range of positions within which the humerus can move relative to the scapula.
  • the range of motion of the shoulder joint may be described in terms of different types of motion of the shoulder joint, including flexion/extension, abduction/adduction, and internal/external rotation.
  • humeral prosthesis 104 and glenoid prosthesis 106 may impact whether the patient experiences impingements or dislocations of the shoulder joint. Limitations of the range of motion of the shoulder joint may cause pain, reduce the patient’s quality of life, and reduce the longevity of the prostheses. [0039] Accordingly, it is important for the surgeon to select appropriate parameters of humeral prosthesis 104 and glenoid prosthesis 106 and to prepare the humerus and scapula according to the plan.
  • the patient’s anatomy may be different than expected, the preparation of the humerus and scapula may not match the presurgical plan for preparation of the humerus and scapula, and/or the patient’s anatomy may have changed over time. Accordingly, the surgeon may test the range of motion of the patient’s shoulder joint during the surgery after implantation of humeral prosthesis 104 and glenoid prosthesis 106 (or trial components thereof). In general, the surgeon relies on the look and feel of the patient’s shoulder joint to assess the range of motion of the patient’s shoulder joint. The surgeon does not typically take precise measurements of the range of motion of the patient’s shoulder joint during the surgery.
  • the surgeon may modify one or more parameters of humeral prosthesis 104 and/or glenoid prosthesis 106 during the surgery. For example, the surgeon may change the size or eccentricity of an articulation element of glenoid prosthesis 106, change a thickness of an articulation element of humeral prosthesis 104, and so on. The surgeon can then retest the range of motion of the patient’s shoulder joint. This process may be repeated multiple times. However, limiting the amount of time the patient is in surgery is also important for positive surgical outcomes.
  • At least one of humeral prosthesis 104 or glenoid prosthesis 106 includes one or more sensors 118.
  • Sensors 118 may generate signals usable to determine a position of humeral prosthesis 104 relative to glenoid prosthesis 106.
  • sensors 118 may include a Hall sensor that generates an electrical signal having a voltage correlated with a motion of a corresponding magnetic element (i.e., a Hall element).
  • glenoid prosthesis 106 may include a Hall sensor and humeral prosthesis 104 may include a magnetic element.
  • sensors 118 include inertial measurement units (IMUs). Because the signals from sensors 118 may be used to determine the position of humeral prosthesis 104 relative to glenoid prosthesis 106, surgical planning system 116 may present information about the range of motion of the patient’s shoulder joint to a user (e.g., the surgeon) during surgery. In some examples, surgical planning system 116 may present the information about the range of motion during a post-surgical phase, e.g., during physical therapy. Furthermore, the information about the range of motion may be used to improve prediction of the range of motion of other patient’s shoulder joints.
  • IMUs inertial measurement units
  • surgical planning system 116 may include a preoperative system 120, an intraoperative system 122, and a postoperative system 124.
  • Surgical planning system 116 may also include a range of motion (RoM) prediction model 126, predicted motion data 128, and joint motion data 130.
  • RoM range of motion
  • Surgical planning system 116 may store predicted motion data 128 and/or joint motion data 130 on a local device (e.g., a device used by a surgeon), in a cloud storage system, or elsewhere.
  • Preoperative system 120 may assist a user (e.g., a surgeon) in planning a total shoulder arthroplasty for an individual patient.
  • Intraoperative system 122 may assist a user (e.g., a surgeon, nurse, product representative, etc.) during the total shoulder arthroplasty.
  • Postoperative system 124 may assist a user after completion of the total shoulder arthroplasty.
  • preoperative system 120 may help the surgeon select values of parameters of humeral prosthesis 104 and glenoid prosthesis 106.
  • preoperative system 120 may automatically design one or more patient-specific orthopedic prosthesis according to the selected parameters. In some examples, preoperative system 120 may automatically recommend parameters of humeral prosthesis 104 and glenoid prosthesis 106 based on the patient’s anatomy. [0043] Preoperative system 120 may output a user interface for display to a user. The user interface may display a virtual glenoid prosthesis model relative to a virtual scapula model. The virtual scapula model is a representation of at least a portion of a scapula of a patient.
  • the virtual glenoid prosthesis model is a representation of a glenoid prosthesis (e.g., glenoid prosthesis 106) to be implanted on the scapula.
  • the user interface may also display a virtual humeral prosthesis model relative to a virtual humerus model.
  • the virtual humerus prosthesis model is a representation of a humeral prosthesis (e.g., humeral prosthesis 104) to be implanted on the humerus.
  • the virtual glenoid prosthesis model and the virtual scapula model may be 3- dimensional (3D) models, such as a 3D mesh.
  • a 3D virtual scapula model may be generated (e.g., by surgical planning system 116 or another system) based on a computed tomography (CT) scan and/or other type of medical imaging of the scapula.
  • CT computed tomography
  • the virtual glenoid prosthesis model and the virtual scapula model may additionally or alternatively be 2-dimensional (2D) models.
  • the virtual scapula model be displayed as a 2D slice of the scapula and the 2D virtual glenoid prosthesis model may be displayed as an outline of the glenoid prosthesis.
  • Preoperative system 120 may receive indications of user input to adjust values of various parameters of humeral prosthesis 104 and glenoid prosthesis 106.
  • Example parameters may include types of prostheses, positions of prostheses, and so on. Different types of prostheses are associated with different parameters.
  • parameters of glenoid prosthesis 106 in a total shoulder arthroplasty may include one or more of a lateralization/medialization of glenoid prosthesis 106, an inclination of glenoid prosthesis 106, a version/anteversion of glenoid prosthesis 106, a size of an articulating surface (e.g., radius of a glenosphere, diameter of a concave articulating surface, etc.), eccentricity of the articulating surface, and so on.
  • an articulating surface e.g., radius of a glenosphere, diameter of a concave articulating surface, etc.
  • Example parameters of humeral prosthesis 104 may include one or more of a size of an articulation element of humeral prosthesis 104, an angle of a base of humeral prosthesis 104, a fixation type of humeral prosthesis 104 (e.g., stemmed or stemless), and so on.
  • preoperative system 120 may automatically recommend values of one or more parameters of humeral prosthesis 104 or glenoid prosthesis 106.
  • An example process for automatically recommending parameters of humeral prosthesis 104 and glenoid prosthesis 106 is described in PCT publication WO 2022/169678, filed January 28, 2022, the entire content of which is incorporated by reference.
  • surgical planning system 116 may check whether a selected humeral prosthesis is compatible with a selected glenoid prosthesis.
  • Preoperative system 120 may apply RoM prediction model 126 to generate predicted motion data 128 for a patient.
  • Predicted motion data 128 describe a predicted range of motion of a shoulder joint of a patient.
  • the predicted range of motion is a range of motion of the shoulder joint of the patient that is consistent with a preoperatively defined surgical plan for a total shoulder arthroplasty on the shoulder of the patient.
  • the preoperatively defined surgical plan may specify details such as parameters of humeral prosthesis 104, parameters of glenoid prosthesis 106, locations of cut planes, reaming depths, types of reaming, whether a bone graft will be used as an augment, and so on.
  • preoperative system 120 may help a user define the surgical plan.
  • predicted motion data 128 may specify a range of motion in terms of degrees of flexion/extension, abduction/adduction, interior/exterior rotation, or in other ways.
  • predicted motion data 128 may also specify an expected width of a gap between humeral prosthesis 104 and glenoid prosthesis 106.
  • RoM prediction model 126 may be implemented in various ways.
  • RoM prediction model 126 is based only on the patient’s bony anatomy and parameters of humeral prosthesis 104 and glenoid prosthesis 106. In such examples, RoM prediction model 126 may perform an analysis in which RoM prediction model 126 positions a 3D virtual model of humeral prosthesis 104 and a 3D virtual model of glenoid prosthesis 106 according to their respective parameters relative to 3D models of the patient’s humerus and scapula.
  • RoM prediction model 126 rotates the 3D virtual model of the patient’s humerus (along with the 3D virtual model of humeral prosthesis 104) relative to the 3D virtual model of glenoid prosthesis 106 and detects points at the 3D virtual model of humeral prosthesis 104 and the 3D model of the patient’s humerus collide with the 3D virtual model of glenoid prosthesis 106 and the patient’s scapula.
  • the collision points represent theoretical limits on the range of motion of the patient’s shoulder joint.
  • the collision points also correspond to locations or regions where impingement may occur.
  • RoM prediction model 126 is based on the patient’s bony anatomy, the patient’s soft tissue anatomy, and parameters of humeral prosthesis 104 and glenoid prosthesis 106.
  • RoM prediction model 126 may perform a similar analysis as described above may further limit the range of motion based on the expected aspects (e.g., strength, fatty infiltration, stretch limitations, etc.) of individual muscles.
  • RoM prediction model 126 may simulate motion of the 3D virtual model of humeral prosthesis and the 3D model of the patient’s humerus relative to the 3D models of the patient’s humerus (along with the 3D virtual model of humeral prosthesis 104).
  • RoM prediction model 126 may detect points at which the 3D virtual model of humeral prosthesis 104 and the 3D model of the patient’s humerus collide with the 3D virtual model of glenoid prosthesis 106 and the patient’s scapula and points at which the soft tissue structures would limit movement of the humerus.
  • RoM prediction model 126 includes one or more machine learning (ML) models that have been trained to predict limitations of extension of individual muscles.
  • a limitation of extension of a muscle may indicate a maximum comfortable amount the muscle can be stretched.
  • Input to an ML model may include the patient’s age, gender, estimated muscle mass, estimated fatty infiltration, injury history, scar tissue, estimated size of the muscle, and/or other factors.
  • the ML model is implemented as using a neural network architecture.
  • the neural network architecture may include an input layer, an output layer, and one or more hidden layers.
  • the input layer may include input neurons corresponding to different input parameters, such as the patient’s age, gender, etc.
  • the output layer may include output one or more neurons that output values indicating a limitation of extension of the muscle.
  • Surgical planning system 116 may apply the neural network architecture by performing a feed- forward operation.
  • a neuron of the neural network architecture may generate output by applying an activation function to a weighted sum of the inputs to the neuron.
  • the weights are machine trainable.
  • the activation function may be a ReLU activation function, a sigmoid activation function, or another type of activation function.
  • Preoperative system 120 may output a user interface (e.g., on display 114) that enables a user to review the predicted range of motion.
  • the user interface may indicate numerical values for the predicted range of motion.
  • the user interface may include an animation of the range of motion of the virtual scapula model, the virtual humerus model, the virtual humeral prosthesis model and the virtual glenoid prosthesis model. Since these virtual models may be represented as 3D meshes, generating the animation may involve a very large number of calculations performed on hundreds or thousands of vertices. The animation may also show scapular movement, so as to show overall arm motion relative to the patient’s body.
  • Intraoperative system 122 may assist a user during a surgery. For example, intraoperative system 122 may output guidance information that guides one or more users with respect to performing the surgery. In some examples, intraoperative system 122 outputs the guidance information for display on or more monitors positioned within an operating room. In some examples, intraoperative system 122 outputs the guidance information for display in an extended reality (e.g., augmented reality or virtual reality) headset worn by a user. Displaying the guidance information in extended reality may involve utilizing a graphics processing pipeline to render 3D meshes of the virtual models for display to the user in real time.
  • extended reality e.g., augmented reality or virtual reality
  • a user performs a test of the range of motion of the patient’s shoulder joint during a total shoulder arthroplasty and intraoperative system 122 obtains joint motion data 130 from one or more sensors 118 included in at least one of humeral prosthesis 104 or glenoid prosthesis 106.
  • Joint motion data 130 provides information regarding an actual range of motion of the shoulder joint during the test of a range of motion of the shoulder joint.
  • Intraoperative system 122 and/or the user may compare the actual range of motion to the predicted range of motion in a surgical plan for the patient.
  • joint motion data 130 may specify ranges of motion of the shoulder joint in terms of degrees of flexion/extension, abduction/adduction, interior/exterior rotation, or in other ways.
  • the actual range of motion determined during the total shoulder arthroplasty may serve as a baseline range of motion for determining subsequent changes to the patient’s range of motion after completion of the total shoulder arthroplasty.
  • Surgical planning system 116 may store a log of joint motion data 130 for subsequent analysis.
  • Joint motion data 130 may also specify a width of a gap between humeral prosthesis 104 and glenoid prosthesis 106.
  • Intraoperative system 122 may output a user interface that provides information based on joint motion data 130. [0053] In some examples, intraoperative system 122 determines, based on the joint motion data, differences between the actual range of motion and the predicted range of motion.
  • Intraoperative system 122 may output feedback data based on the differences between the actual range of motion and the predicted range of motion. For example, intraoperative system 122 may output a warning to a user that the actual range of motion does not correspond to the predicted range of motion. The user may modify one or more parameters of humeral prosthesis 104 and/or glenoid prosthesis 106 accordingly. [0054] In some examples, intraoperative system 122 may automatically determine an alternative surgical configuration based on the joint motion data.
  • the alternative surgical configuration corresponds to one or more of: a different size of at least one of the humeral prosthesis or the glenoid prosthesis, a different position of at least one of the humeral prosthesis or the glenoid prosthesis, a different eccentricity of an articulating surface of the humeral prosthesis or the glenoid prosthesis, or removal of one or more areas of bony tissue (such as osteophytes or other area on the scapula or humerus).
  • Intraoperative system 122 may output feedback data that includes an indication of the alterative surgical configuration for display.
  • intraoperative system 122 may obtain intraoperatively collected information regarding the patient’s actual anatomy (e.g., the actual shape of the bone after cutting or reshaping, shapes of the patient’s bone as gathered by use of a digitizer, and so on) and intraoperatively gathered information about the soft tissue (e.g., more or less fatty infiltration of muscle tissue than expected, more or less scar tissue than expected, more or less muscle mass than expected, and so on).
  • Intraoperative system 122 may use the intraoperatively collected information along with various combinations of parameters of humeral prosthesis 104 and glenoid prosthesis 106 as input to RoM prediction model 126.
  • the intraoperatively collected information may include position and motion information generated by one or more of sensors 118.
  • RoM prediction model 126 may output predicted range of motion data.
  • Intraoperative system 122 may compare the predicted range of motion data associated with the different combinations to select a combination of parameters associated with the predicted range of motion or another range of motion, such as a predicted range of motion for an average person, or a range of motion compatible with a particular activity that the patient wants to be able to perform.
  • Osteophytes on the patient’s scapula or humerus may be identified preoperative or intraoperatively, e.g., by a surgeon or by computerized image analysis. Osteophytes are bony projections that form along joint margins. Such osteophytes may interfere with the patient achieving a full range of motion.
  • preoperative system 120 and/or intraoperative system 122 may recommend removal of one or more osteophytes.
  • surgical planning system 116 may use RoM prediction model 126 to determine ranges of motion using 3D virtual models of the patient’s humerus and scapula still having the one or more osteophytes and determine ranges of motion using 3D virtual models of the patient’s humerus and scapula without the one or more osteophytes. If there are multiple osteophytes, surgical planning system 116 may determine the ranges of motion with different combinations of the osteophytes removed.
  • Surgical planning system 116 may compare the ranges of motion to determine whether removal of one or more of the osteophytes (or a specific combination of the osteophytes) would be advantageous, e.g., to restore a range of motion.
  • intraoperative system 122 may determine, during surgery, whether to recommend removal of osteophytes using analysis of mesh-based 3D virtual models of the patient’s humerus and scapula (which may themselves be generated intraoperatively) may involve complex calculations on hundreds or thousands of vertexes of the meshes.
  • intraoperative system 122 may determine osteophytes for removal based on joint motion data 130. For instance, the actual range of motion as indicated by joint motion data 130 may be less than the predicted range of motion.
  • intraoperative system 122 may determine a predicted range of motion of the patient’s shoulder joint if one or more of the osteophytes were removed. Intraoperative system 122 may output feedback data indicating whether to remove the one or more osteophytes. In other words, intraoperative system 122 may determine, based on the differences between the actual range of motion and the predicted range of motion, whether to recommend removal of one or more osteophytes of the humerus or the scapula. For instance, based on there being differences between the actual range of motion and the predicted range of motion, intraoperative system 122 may perform a process to determine whether to recommend removal of the one or more osteophytes.
  • Intraoperative system 122 may output feedback data that includes a recommendation to remove the one or more osteophytes.
  • preoperative system 120 or intraoperative system 122 may suggest one or more soft tissue releases that may improve range of motion.
  • a soft tissue release involves making small incisions into soft tissue, such as muscles, tendons, or ligaments, to release the soft tissues from joints.
  • RoM prediction model 126 may include ML models trained to predict limitations of extension of individual muscles.
  • Preoperative system 120 or intraoperative system 122 may determine whether the predicted limitation of extension of a muscle is a limitation on the range of motion. For example, preoperative system 120 or intraoperative system 122 may determine that the predicted range of motion in a direction associated with the muscle is less than a predefined threshold range of motion for the direction.
  • preoperative system 120 or intraoperative system 122 may determine an effect on the predicted range of motion of a soft tissue release of the muscle. Preoperative system 120 or intraoperative system 122 may determine the effect of the soft tissue release based on a statistical average of increases in ranges of motion when soft tissue releases are performed on the muscle. If the effect of the soft tissue release is significant enough (e.g., greater than a particular threshold), preoperative system 120 or intraoperative system 122 may output a recommendation to perform the soft tissue release.
  • Postoperative system 124 may assist a user after a surgery. For example, postoperative system 124 may output guidance information regarding physical therapy of a patient.
  • postoperative system 124 may obtain joint motion data 130 indicating an actual range of motion of the shoulder joint of the patient.
  • the range of motion of the shoulder joint of the patient may be determined during a physical therapy session, at the patient’s home, or at another time after surgery.
  • Postoperative system 124 may determine, based on joint motion data 130, differences between the actual range of motion and the predicted range of motion.
  • Postoperative system 124 may output feedback data based on the differences between the actual range of motion and the predicted range of motion. For example, postoperative system 124 may output feedback data indicating that the range of motion is excessive in one or more directions and that the patient should perform specific exercises to strengthen muscles to compensate.
  • postoperative system 124 may output feedback data indicating that the range of motion is limited in one or more directions and that the patient should perform specific stretching exercises to reduce tightness of one or more muscles.
  • postoperative system 124 may output feedback data indicating that a gap between humeral prosthesis 104 and glenoid prosthesis 106 indicates potential impingement or risk of dislocation.
  • postoperative system 124 may provide other information that helps the patient during the postoperative period. For example, the feedback generated by postoperative system 124 may indicate that the patient is working the shoulder joint too much or too little.
  • postoperative system 124 may be able to determine, based on the gap between humeral prosthesis 104 and glenoid prosthesis 106, that the patient is carrying too much weight through the patient’s shoulder and therefore an adverse event (e.g., a dislocation, premature prosthesis failure, or loss of function) is occurring or likely to occur. That is, if the gap between the humeral prosthesis 104 and the glenoid prosthesis 106 exceeds a threshold during movement, one or more of the patient’s rotator cuff muscles are likely not strong enough to support a weight carried by the patient.
  • an adverse event e.g., a dislocation, premature prosthesis failure, or loss of function
  • postoperative system 124 may analyze joint motion data 130 to determine the frequency of exercise, duration of exercise, and types of exercise. Based on this information, postoperative system 124 may determine that the patient exercising too much or too little. Since surgical planning system 116 stores data, postoperative system 124 may use joint motion data 130 to track the patient’s range of motion as recovery progresses. [0060] In some examples, surgical planning system 116 may refine RoM estimation model 126 based on joint motion data 130 generated intraoperatively or postoperatively.
  • RoM estimation model 126 is a neural network model
  • surgical planning system 116 may refine RoM estimation model 126 (e.g., by performing a backpropagation/gradient-descent process) to adjust weights of inputs to artificial neurons intraoperatively.
  • RoM prediction model 126 is based only on the patient’s bony anatomy and parameters of humeral prosthesis 104 and glenoid prosthesis 106.
  • RoM prediction model 126 may perform an analysis in which RoM prediction model 126 positions a 3D virtual model of humeral prosthesis 104 and a 3D virtual model of glenoid prosthesis 106 according to their respective parameters relative to 3D models of the patient’s humerus and scapula.
  • RoM prediction model 126 rotates the 3D virtual model of the patient’s humerus (along with the 3D virtual model of humeral prosthesis 104) relative to the 3D virtual model of glenoid prosthesis 106 and detects points at the 3D virtual model of humeral prosthesis 104 and the 3D model of the patient’s humerus collide with the 3D virtual model of glenoid prosthesis 106 and the patient’s scapula.
  • the collision points represent theoretical limits on the range of motion of the patient’s shoulder joint.
  • Surgical planning system 116 may display an animation of the motion of the patient’s shoulder joint.
  • surgical planning system 116 may refine RoM prediction model 126 to limit the range of motion based on the actual range of motion represented by joint motion data 130.
  • the animation may show the actual range of motion instead of, or in addition, to the theoretical range of motion. In this way, the user may be better able to visualize the movement of the humerus relative to scapula.
  • the animation may also show scapular motion relative to the patient’s body so that the user may be better able to visualize the overall motion of the patient’s arm.
  • RoM prediction model 126 may perform a similar analysis as described above but may further limit the range of motion based on the expected aspects (e.g., strength, fatty infiltration, stretch limitations, etc.) of individual muscles.
  • RoM prediction model 126 includes one or more machine learning (ML) models that have been trained to predict limitations of extension of individual muscles.
  • the one or more ML models may include multilevel perceptron (MLPs) for individual muscles.
  • MLPs multilevel perceptron
  • the MLP for a muscle may have an input layer, one or more fully connected hidden layers, and an output layer.
  • a ReLU activation function, or another type of activation function, may be used with hidden layers.
  • Input to an MLP for a muscle may indicate a measured strength of the muscle, a fatty infiltration of the muscle, an age of the patient, injury history of the muscle, and so on.
  • Output generated by an output layer of an MLP may indicate the expected limitation of extension of the muscle.
  • Surgical planning system 116 may determine observed limitations of individual muscles based on joint motion data 130 derived from sensors 118. Surgical planning system 116 may use an error function (e.g., sum of absolute differences, mean squared error, etc.) to derive a difference between an expected limitation of a muscle and the observed limitation of the muscle. Surgical planning system 116 may use a backpropagation process to modify parameters of the neural network architecture (e.g., the one or more MLPs) based on joint motion data 130 (e.g., based on the difference between the expected limitation of the muscle and the observed limitation of the muscle).
  • an error function e.g., sum of absolute differences, mean squared error, etc.
  • Surgical planning system 116 may use a backpropagation process to modify parameters of the neural network architecture (e.g., the one or more MLPs) based on joint motion data 130 (e.g., based on the difference between the expected limitation of the muscle and the observed limitation of the muscle).
  • surgical planning system 116 may apply a model that predicts the predicted range of motion based on patient-specific anatomy of the shoulder joint and based on parameters of the humeral prosthesis and the glenoid prosthesis and may refine the model based on the feedback data.
  • the ML models for the individual muscles may be reused for future patients.
  • surgical planning system 116 uses joint motion data 130 in a finite element analysis (FEA) to estimate safe loads for humeral prosthesis 104 and glenoid prosthesis 106.
  • FEA finite element analysis
  • humeral prosthesis 104, glenoid prosthesis 106, and supporting muscles may be represented as a system of finite elements.
  • Surgical planning system 116 may use the FEA to estimate displacement of humeral prosthesis 104 relative to glenoid prosthesis 106 when various forces (loads) are applied to the humerus when the humerus is at various positions. If such loads result in impingement or dislocation, surgical planning system 116 may run the FEA again with different parameters of the muscles (e.g., a particular muscle being stronger) and determine again whether the impingement or dislocation occurs. Through repeatedly adjusting parameters of the muscles, surgical planning system 116 may determine which of the muscles should be strengthened through exercise. Similarly, if the FEA may be used to determine parameters of muscles to stretch to achieve a range of motion. Surgical planning system 116 may use the joint motion information to validate the FEA system.
  • loads result in impingement or dislocation
  • FIG.2 is a block diagram illustrating example components of a prosthesis 200, in accordance with one or more techniques of this disclosure.
  • Prosthesis 200 may be one of humeral prosthesis 104 or glenoid prosthesis 106 (FIG. 1).
  • Prosthesis 200 may be a glenoid prosthesis, a humeral prosthesis, or another type of orthopedic prosthesis.
  • prosthesis 200 includes a power source 202, a Hall sensor array 204, an inertial measurement sensor (IMU) 206, a memory 208, one or more processors 210, and a communication unit 212.
  • prosthesis 200 may include one or more additional components.
  • prosthesis 200 may include a temperature sensor configured to measure a body temperature of a patient.
  • one or more components shown in FIG. 2 are omitted.
  • prosthesis 200 does not include IMU 206 or processors 210.
  • Hall sensor array 204, IMU 206, memory 208, processors 210, and/or communication unit 212 may be communicatively coupled directly or indirectly such that information may be communicated between such components.
  • Power source 202 includes one or more batteries or other devices configured to store energy. Power source 202 is configured to provide electrical energy to Hall sensor array 204, IMU 206, memory 208, processors 210, communication unit 212, and/or other components of prosthesis 200 via power distribution channels (not shown).
  • Hall sensor array 204 is a sensor that incorporates one or more Hall elements, each of which produces a voltage proportional to one axial component of a magnetic field vector using the Hall effect.
  • the voltages may represent a magnetic field intensity observed in the x, y, and z axes, e.g., in milli-Tesla (mT).
  • Hall sensor array 204 is configured to generate Hall signals based on the voltages caused by magnetic flux. Each respective Hall sensors of Hall sensor array 204 may generate a respective Hall signal.
  • the Hall signals generated by Hall sensor array 204 may represent movement of a humeral prosthesis relative to a glenoid prosthesis.
  • Hall sensor array 204 may output data via a data interface, such as a SPI interface, a I 2 C interface, or another type of interface.
  • IMU 206 is configured to measure a specific force and angular rate of prosthesis 200.
  • IMU 206 may include one or more accelerometers and gyroscopes. IMU 206 is configured to generate one or more IMU signals that represent humeral-glenoid bias from scapular motion. For example, the IMU signals may indicate acceleration of the shoulder superiorly or inferiorly independent of rotation of the humerus relative to the scapula. For instance, the IMU signals may provide pitch and roll angular rates which may be relevant to determination of the scapular contribution to motion of the patient’s arm. The use of such IMU signals may enable surgical planning system 116 (and users thereof) to have more complete information about the movement of the patient’s shoulder.
  • Memory 208 is configured to store data, such as data representing the Hall signals and the IMU signals.
  • Processors 210 are configured to process data, such as data representing the Hall signals and the IMU signals. Processors 210 may be implemented in any of the ways described above with respect to processors 108 (FIG. 1). Processors 210 are configured to generate position information based on the data representing the Hall signal and/or the IMU signals. In other examples, processors 108 (FIG.1) may generate joint motion data 130 based on the data representing the Hall signal and/or the IMU signals. In various examples, processors 210 may generate joint motion data 130 in different ways. In the example of FIG.2, processors 210 implement a ML model 214, such as a neural network, that is configured to generate joint motion data 130.
  • ML model 214 such as a neural network
  • the neural network may include an input layer, an output layer, and one or more hidden layers between the input layer and the output layer. For each layer of the input layer and hidden layers, output of the layer is input to the next layer of the neural network.
  • Individual neurons generate output based on application of an activation function to a weighted sum of input values.
  • the activation function may be a ReLU activation function, a sigmoid activation function, or another type of activation function.
  • Output of the output layer may indicate a current angle of the humerus relative to the scapula, a distance between the humerus and scapula, or other values.
  • FIG.8 provides an example architecture of a neural network that may implement ML model 214.
  • the neural network may take data representing the Hall signals as input.
  • the neural network may output a predicted position in 6 degrees of freedom.
  • the neural network may be trained based on simulation data from finite element analysis (FEA).
  • FEA finite element analysis
  • the FEA simulations may be performed in which models of the humeral prosthesis and glenoid prosthesis are moved relative to one another and Hall signals are estimated.
  • the estimated Hall signals can be provided as input to the neural network and the output of the neural network can be compared to the corresponding ground truth positions of the humeral prosthesis and glenoid prosthesis.
  • Joint motion data 130 provides information about a position of prosthesis 200.
  • joint motion data 130 may include information about a position of the glenoid prosthesis relative to a humeral prosthesis.
  • joint motion data 130 may provide information about the position of the patient’s scapula.
  • joint motion data 130 may include information indicative of a position of the scapula relative to the patient’s torso.
  • joint motion data 130 may include information indicating one or more of degrees of forward extension of the shoulder joint, degrees of abduction/adduction of the shoulder joint, or degrees of internal/external rotation of the shoulder joint.
  • joint motion data 130 may indicate the position and motion of the glenoid prosthesis and humeral prosthesis in 6 degrees of freedom (e.g., 3 spatial translation dimensions, anterior/posterior rotation, superior/inferior rotation, and axial rotation).
  • joint motion data 130 may include information indicating a distance between prosthesis 200 and a corresponding prosthesis (e.g., between a glenoid prosthesis and a humeral prosthesis).
  • Communication unit 212 is configured to transmit joint motion data 130 to one or more computing devices, such as a computing device of computing system 102 (FIG.1).
  • Communication unit 212 may be configured to communicate joint motion data 130 using one or more types of wireless communication.
  • communication unit 212 may communicate joint motion data 130 using a BLUETOOTH LOW ENERGY TM wireless communication protocol.
  • communication unit 212 may use near field magnetic induction to communicate joint motion data 130.
  • communication unit 212 is configured to transmit other information, such as the status of power source 202, maximum and minimum positions, information about the time of motion, body temperature, and so on.
  • FIG.3 is a schematic diagram of a glenoid prosthesis 300 and a humeral prosthesis 302, in accordance with one or more techniques of this disclosure.
  • glenoid prosthesis 300 includes an articulation element 304, a baseplate 306, and a Hall element 308.
  • Humeral prosthesis 302 includes an articulation element 310, a stem element 312, and electronic components 314.
  • Articulation element 304 is coupled to baseplate 306.
  • Articulation element 310 is coupled to stem element 312.
  • Articulation element 304 and articulation element 310 may include polyethylene articulation surfaces configured to contact and slide over one another.
  • Baseplate 306 defines one or more holes through which fixation elements (e.g., screws) may be passed in order to fix glenoid prosthesis 300 to a patient’s scapula.
  • Stem element 312 is configured to attach humeral prosthesis 302 to the patient’s humerus. In some examples, stem element 312 extends into an intermedullary canal of the patient’s humerus. In other examples, humeral prosthesis 302 is stemless and humeral prosthesis 302 includes a baseplate for attaching humeral prosthesis 302 to the patient’s humerus.
  • Electronic components 314 in humeral prosthesis 300 may include the components shown in the example of FIG.
  • FIG.4 is a conceptual diagram illustrating an example user interface 400 showing a current position of a shoulder joint, in accordance with one or more techniques of this disclosure.
  • Surgical planning system 116 may output user interface 400 for display on display 114.
  • Surgical planning system 116 may output user interface 400 for display before, during, or after surgery.
  • Surgical planning system 116 may generate information for display in user interface 400 based on position information received from a prosthesis (e.g., from humeral prosthesis 104, glenoid prosthesis 106, prosthesis 200, glenoid prosthesis 300, etc.).
  • User interface 400 includes a medial live view 402, a frontal live view 404, and position indicators 406A, 406B, 406C, and 406D (collectively, “position indicators 406”).
  • position indicators 406 may include more, fewer, or different elements. Accuracy of the displayed information may be important for making patient-care decisions. Because individual patients have different anatomies, a RoM prediction model that is accurate for one patient may not produce predictions that are as accurate as possible for another patient.
  • Medial live view 402 shows a current position of a humeral prosthesis 408 relative to glenoid prosthesis (not shown in the medial live view 402 of FIG. 4 because of the position of humeral prosthesis 408) from a lateral-to-medial direction.
  • Frontal live view 404 shows the current position of humeral prosthesis 408 relative to glenoid prosthesis 410 from an anterior-to-posterior direction.
  • Surgical planning system 116 may update medial live view 402 and frontal live view 404 in real time as the patient’s humerus moves relative to the patient’s scapula.
  • Position indicators 406A – 406D indicate positions of the patient’s humerus relative to the patient’s scapula in different directions of movement. Specifically, position indicator 406A indicates a current flexion/extension of the patient’s humerus in degrees. Position indicator 406B indicates a current abduction/adduction of the patient’s humerus in degrees.
  • Position indicator 406C indicates a current external/internal rotation of the patient’s humerus in degrees.
  • Position indicator 406D indicates a size of glenoid-humerus gap, e.g., in millimeters (mm).
  • User interface 400 also includes numerical data 412 indicating the flexion/extension (FE) angle, the abduction/adduction (AB/AD) angle, the internal/external (IE) angle, and the glenoid-humerus (GH) gap.
  • the current FE angle is -10.5°
  • the current AB/AD angle is 53.5°
  • the current IE angle is 5.7°
  • the current GH gap is 1.1 mm.
  • Surgical planning system 116 may update position indicators 406 and numerical data 412 in real time as the patient’s humerus moves relative to the patient’s scapula. Thus, surgical planning system 116 may generate, based on the joint motion data, information regarding a current angle of the shoulder joint in a direction of movement of the shoulder joint and may output the information regarding the current angle of the shoulder joint. In some examples, processors 210 in a prosthesis may generate the information regarding the current angle of the shoulder joint in the direction of movement. [0075] FIG. 5 is a conceptual diagram illustrating an example of user interface 400 showing a current position of a shoulder joint in which a possible dislocation has occurred, in accordance with one or more techniques of this disclosure.
  • User interface 400 may show when the patient is potentially experiencing or has experienced a dislocation of the shoulder joint.
  • a dislocation of the shoulder joint may occur when the humeral prosthesis is subluxed or levered out from the glenoid prosthesis.
  • Surgical planning system 116 may determine that a dislocation of the shoulder joint has occurred when the GH gap is above a specific threshold.
  • surgical planning system 116 may obtain joint distance data (e.g., included in joint motion data 130) from one or more sensors 118, where the joint distance data indicates a distance between humeral prosthesis 104 and glenoid prosthesis 106, and may determine, based on the joint distance data, whether a potential dislocation of the shoulder joint has occurred.
  • FIG. 6 is a conceptual diagram illustrating an example of user interface 400 showing a current position of a shoulder joint in which a possible impingement has occurred, in accordance with one or more techniques of this disclosure.
  • User interface 400 may show when the patient is potentially experiencing or has experienced an impingement of the shoulder joint.
  • An impingement of the shoulder joint may occur when there is a collision between the humerus (or humeral prosthesis) and the scapula (or glenoid prosthesis), or when soft tissue prevents the humerus from moving through a particular range of motion.
  • a result of such an impingement is a widening of the GH gap when the humerus is at a specific position. The widening of the GH gap may be significantly less than the widening of the GH gap during a dislocation.
  • Surgical planning system 116 may determine that an impingement is occurring or has occurred if the GH gap is above a first threshold and below a second threshold.
  • a user of surgical planning system 116 may use the information in user interface 400 for a variety of purposes.
  • surgical planning system 116 may display user interface 400 during surgery, i.e., intra-operatively.
  • the user e.g., a surgeon
  • the user may determine whether the actual range of motion of the patient’s shoulder joint is consistent with a predicted range of motion of the patient’s shoulder joint. As part of determining whether the actual range of motion of the patient’s shoulder joint is consistent with the predicted range of motion of the patient’s shoulder joint, the user may determine whether any dislocations or impingements occur. If the actual range of motion of the patient’s shoulder joint is not consistent with the predicted range of motion of the patient’s shoulder joint, the user may take corrective action. For example, one or more components of humeral prosthesis 104 or glenoid prosthesis 106 may be intraoperatively substituted.
  • humeral prosthesis 104 and glenoid prosthesis 106 may include one or more trial components (e.g., trial articulation elements) that may be substituted during the surgery. For instance, the surgeon may initially use trial articulating elements before replacing the trial articulating elements with permanent articulating elements.
  • one or more of sensors 118 may be included in a trial component of one of humeral prosthesis 104 or glenoid prosthesis 106. In some examples, one or more of sensors 118 may be included in non- trial components of humeral prosthesis. After substituting one or more different trial components, the surgeon may re-test the range of motion of the patient’s shoulder joint.
  • intraoperative system 122 may determine, based on the joint motion data, that a second trial component having one or more surgical parameters different from the first trial component would result in a better range of motion than an actual range of motion achieved while the first trial component was installed.
  • Intraoperative system 122 may use RoM prediction model 126 to determine predicted ranges of motion for multiple trial components having different surgical parameters.
  • Input to RoM prediction model 126 may include updates to a model of the patient’s anatomy (e.g., bone shape, soft tissue characteristics, actual modified bone surfaces, etc.).
  • Intraoperative system 122 may use the determined predicted ranges of motion to determine the second trial component.
  • surgical parameters may include sizes and shapes of articulation surfaces, medialization/lateralization of the articulation surface, orientation of the articulation surface, eccentricity of the articulation surface, and so on.
  • surgical planning system 116 may obtain second joint motion data that provides information regarding a second actual range of motion of the shoulder joint during a second test of the range of motion of the shoulder joint.
  • Intraoperative system 122 may repeat this process if intraoperative system 122 determines that the second actual range of motion still differs from the predicted range of motion.
  • intraoperative system 122 may obtain second joint motion data that provides information regarding a second actual range of motion of the shoulder joint during a second test of the range of motion of the shoulder joint.
  • surgical planning system 116 may display user interface 400 (or an interface similar to user interface 400) to a user prior to surgery (i.e., pre- operatively).
  • the source of information used by surgical planning system 116 to generate user interface 400 may include one or more devices other than implanted humeral or glenoid prostheses.
  • the source of the information may include one or more cameras, wearable devices, or other types of devices.
  • the user may recommend a presurgical plan for the patient.
  • the presurgical plan may involve exercises to strengthen one or more muscles (e.g., rotator cuff muscles).
  • surgical planning system 116 may display user interface 400 (or an interface similar to user interface 400) to a user after completion of the surgery (i.e., post-operatively).
  • surgical planning system 116 may display user interface 400 to a user (e.g., a practitioner or the patient) during the patient’s recovery or during physical therapy.
  • the information provided by user interface 400 may help guide the course of the patient’s recovery or physical therapy.
  • a practitioner may recommend the patient perform specific exercises to increase range of motion, decrease risk of dislocation, or prevent other adverse outcomes.
  • a user or surgical planning system 116 may detect adverse events or adverse trends based on the information or data received from the sensors after completion of the surgery. The user may then provide a recommendation on how to intervene to address the adverse event or trend. For instance, the user may use the information provided by user interface 400 to determine whether one or more of the humeral prosthesis or glenoid prosthesis has failed and a revision surgery is needed.
  • FIG.7 is a flowchart illustrating an example operation 700 in accordance with one or more techniques of this disclosure.
  • surgical planning system 116 may apply RoM estimation model 126 to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis (702).
  • the predicted range of motion is a range of motion of a shoulder joint of a patient that is consistent with a preoperatively defined surgical plan for a total shoulder arthroplasty on the shoulder of the patient.
  • surgical planning system 116 may obtain joint motion data 130 from one or more sensors 118 included in at least one of humeral prosthesis 104 or glenoid prosthesis 106 (704).
  • Humeral prosthesis 104 is implanted on a humerus of the shoulder joint and glenoid prosthesis 106 is implanted on a scapula of the shoulder joint.
  • Joint motion data 130 provides information regarding an actual range of motion of the shoulder joint during a test of a range of motion of the shoulder joint.
  • Sensors 118 may include one or more Hall sensors.
  • the test of the range of motion of the shoulder joint may occur intraoperatively during the total shoulder arthroplasty. In some examples, the test of the range of motion of the shoulder joint may occur postoperatively during physical therapy of the patient.
  • Surgical planning system 116 may refine RoM estimation model 126 based on joint motion data 130 (706).
  • surgical planning system 116 may refine RoM estimation model 126 for the patient to show actual limitations on the range of motion.
  • surgical planning system 116 (or another system) may train the ML models based on joint motion data 130. In this way, RoM estimation model 126 may be able to generate more accurate predicted ranges of motion.
  • surgical planning system 116 may apply RoM estimation model 126 to generate, based on the patient-specific anatomy of the shoulder joint and the parameters of the humeral prosthesis and the glenoid prostheses, second predicted motion data that describe a second predicted range of motion of the shoulder joint.
  • Surgical planning system 116 may output a visualization of the second predicted range of motion. For instance, surgical planning system 116 may output an animation showing the second predicted range of motion, e.g., using an interface similar to medial live view 402 and/or frontal live view 404 (FIG.4).
  • surgical planning system 116 may determine, based on joint motion data 130, differences between the actual range of motion and the predicted range of motion. For example, surgical planning system 116 may subtract differences in angles of rotation achieved in the actual range of motion from angles of rotation active in the predicted range motion in various directions of movement. Surgical planning system 116 may output feedback data based on the differences between the actual range of motion and the predicted range of motion.
  • the feedback data may include 2D or 3D models of the patient’s humerus and scapula along with features that indicate differences between the actual range of motion predicted range of motion. Such features may include an arc representing the predicted range of motion and an arc representing the actual range of motion.
  • the feedback data may include warnings, alerts, or other messages regarding the differences between the actual range of motion and the predicted range of motion.
  • the feedback data includes information such as that shown in the examples of FIG. 4 through FIG. 6.
  • the feedback data includes a recommendation to remove at least one osteophyte of the humerus or the scapula.
  • the feedback data provides information about a physical therapy plan for the patient.
  • the feedback data may indicate specific muscles to strengthen, whether the patient is exercising too much or too little, or other information about the physical therapy plan.
  • the feedback data may include information regarding an adverse trend and guidance for intervention to address the adverse trend.
  • Example adverse trends include changes over time in the glenoid-humeral gap, changes in maximum ranges of motion, changes in typical ranges of motion, changes of the humeral prostheses relative to the glenoid prosthesis at specific locations within a range of motion, and so on. Interventions may include additional imaging, physical therapy to strengthen specific muscles, revision surgery, or other actions.
  • surgical planning system 116 may obtain a series of joint motion datasets from the one or more sensors.
  • Each joint motion dataset of the series of joint motion data may provide information regarding at least one of an actual range of motion of the shoulder joint or a glenoid-humeral distance at a different time.
  • Surgical planning system 116 may predict, based on the series of joint motion datasets, an occurrence of a future adverse event. For example, surgical planning system 116 may identify a class of a patient based on the joint motion datasets. The classes may include a class associated with healthy conditions and one or more classes associated with adverse trends. Surgical planning system 116 may automatically recommend an intervention associated with an identified adverse trend. For instance, different classes of adverse trends may be mapped to associated interventions. Surgical planning system 116 may use one or more techniques to identify a class of the patient.
  • surgical planning system 116 may perform a regression on time-series datapoints (e.g., datapoints representing ranges of motion, datapoints glenoid-humeral gap distance, datapoints indicating differences between predicted ranges of motion and actual ranges of motion, datapoints indicating differences between predicted glenoid-humeral gap distances and actual glenoid-humeral gap distances, datapoints indicating differences between initial ranges of motion/glenoid-humeral gap distances and actual ranges of motion/glenoid- humeral gap distances, etc.) to generate a trendline.
  • Initial datapoints may be gathered by intraoperative system 122 during a test of a range of motion during the surgery.
  • Surgical planning system 116 may then identify a class based on a slope of the trendline.
  • surgical planning system 116 may extrapolate the trendline and identify a class based on whether the extrapolated trendline reaches a specific threshold value.
  • the threshold value may correspond to a point at which a likelihood of impingement or dislocation reaches a threshold.
  • decreases in distances of the glenoid- humeral gap over time relative to a distance of an initial glenoid-humeral gap may be associated with wear on the articulating surfaces of the humeral prosthesis and/or glenoid prosthesis.
  • surgical planning system 116 may output a graph of the trendline for display.
  • surgical planning system 116 may identify an adverse trend based on combinations of two or more trendlines. For instance, if the glenoid-humeral gap is increasing and the range of motion in a specific direction is also increasing, surgical planning system 116 may determine that the patient is likely to experience a dislocation.
  • FIG. 8 is a conceptual diagram illustrating an example architecture of a neural network 800 for determining a 6-degrees of freedom pose of a prosthesis and associated processing steps, in accordance with one or more techniques of this disclosure.
  • Neural network 800 may an example of ML model 214, which is configured to generate joint motion data 130.
  • processors 210 receive Hall sensor data 802.
  • Hall sensors data 802 may include data representing the Hall signals. As discussed above, the Hall signals may represent a magnetic field intensity observed in the x, y, and z axes. Processors 210 may then process Hall sensor data 802 prior to providing input to neural network 800. In the example of FIG. 8, processors 210 may cut off bits of (e.g., less significant bits) of Hall sensor data 802. This reduces the number of bits that represent Hall sensor data 802. Additionally, processors 210 may decompose the Hall sensor data into magnitude data and direction data.
  • processors 210 may decompose the Hall sensor data into magnitude data and direction data.
  • processors 210 may separate the Hall sensor data by which of the Hall sensors generated portions of the Hall sensor data (which correspond to different directions) as well as the magnitudes (e.g., indications of acceleration and duration) of the magnetic field intensity in the different directions.
  • the magnitude data and the direction data may be used as input to a series of layers of neural network 800.
  • neural network 800 includes a series of alternating batch normalization layers and dense leaky ReLU layers and ends with a dense linear layer.
  • Output of the dense linear layer of neural network 800 includes scaled translation data 808 and scaled modified Rodrigues parameters 810.
  • the scaled translation data 808 indicates a translation of the prosthesis in a 3-dimensional space.
  • the scaled modified Rodrigues parameters 810 are a minimal parameterization for representing rotation in the 3-dimensional space.
  • Processors 210 may un-scale the scaled translation data (812). Additionally, processors 210 may un-scale the scaled modified Rodrigues parameters and convert the unscaled modified Rodrigues parameters to an anatomical representation of the rotation (814).
  • Un-scaling data, such as the translation data and modified Rodrigues parameters may involve multiplying the data by a scaling factor to convert the data to a different scale.
  • the anatomical representation may indicate degrees of rotation relative to anatomical planes of the patient’s body.
  • FIG. 9 is a conceptual diagram illustrating an example system 900 for training neural network 800, in accordance with one or more techniques of this disclosure.
  • training system 132 may train a kinematics estimation model 902 to generate 6-degrees of freedom patient kinematic data 904, such as kinematic data 816 (FIG. 8).
  • ML model 214 and neural network 800 may be examples of kinematics estimation model 902.
  • training system 132 may obtain sets of training examples.
  • Each training example includes ground-truth kinematics data 906.
  • the ground-truth kinematics data may indicate a position the position of a prosthesis of a prosthesis system, a velocity of the prosthesis, and an acceleration of the prosthesis.
  • training system 132 may use a finite element model of a prosthesis system to generate a set of estimated Hall signals associated with the training example based on the ground-truth kinematics data of the training example.
  • Training system 132 may then use the sets of estimated Hall signals associated with the training examples to train kinematics estimation model 902.
  • Training system 132 may perform a plurality of training iterations to train kinematics estimation model 902. During each training iteration, training system 132 may preprocess a set of estimated Hall signals associated with a training example (e.g., as described with respect to FIG. 8), apply kinematics estimation model 902 to generate output (e.g., scaled translation data and scaled modified Rodrigues parameters), and then convert the output to 6-degrees of freedom patient kinematics data (e.g., as described above with respect to FIG. 8) associated with the training example. Training system 132 may apply a loss function to the resulting patient kinematics data associated with the training example and the ground- truth kinematics data associated with the training example to generate a loss value.
  • output e.g., scaled translation data and scaled modified Rodrigues parameters
  • Training system 132 may apply a loss function to the resulting patient kinematics data associated with the training example and the ground- truth kinematics data associated with
  • Training system 132 may perform a backpropagation process that updates parameters (e.g., weights) of neurons of kinematics estimation model 902 based on a gradient of the loss function. In this way, kinematics estimation model 902 may be trained to generate accurate patient kinematics data 904. [0094] Different kinematics estimation models may be trained for different prosthesis systems. Each different prosthesis system may have a different combination of prosthesis parameters (e.g., size, shape, eccentricity, lateralization/medialization, etc. Training of kinematics estimation model 902 may be performed by a computing system separate from a prosthesis in which kinematics estimation model 902 is used to generate patient kinematics data for a patient.
  • parameters e.g., weights
  • a computer-implemented method comprising: applying, by one or more processors implemented in circuitry, a model to generate, based on patient-specific anatomy of a shoulder joint of a patient and based on parameters of a humeral prosthesis and a glenoid prosthesis, predicted motion data that describe a predicted range of motion of the shoulder joint of a patient; obtaining, by the one or more processors, joint motion data from one or more sensors included in at least one of a humeral prosthesis or a glenoid prosthesis, wherein the humeral prosthesis is implanted on a humerus of the shoulder joint and the glenoid prosthesis is implanted on a scapula of the shoulder joint, and the joint motion data provides information regarding an actual range of motion of the shoulder joint; and
  • Clause 2 The computer-implemented method of clause 1, further comprising: determining, by the one or more processors, based on the joint motion data, differences between the actual range of motion and the predicted range of motion; and outputting, by the one or more processors, feedback data based on the differences between the actual range of motion and the predicted range of motion.
  • Clause 3 The computer-implemented method of any of clauses 1-2, wherein the feedback data provides information about a physical therapy plan for the patient.
  • the computer-implemented method further comprises determining, by the one or more processors, an alternative surgical configuration based on the joint motion data, wherein the alternative surgical configuration corresponds to one or more of: a different size of at least one of the humeral prosthesis or the glenoid prosthesis, a different position of at least one of the humeral prosthesis or the glenoid prosthesis, a different eccentricity of an articulating surface of the humeral prosthesis or glenoid prosthesis, or removal of one or more areas of bony tissue, and outputting, by the one or more processors, an indication of the alterative surgical configuration for display.
  • the method further comprises: determining, by the one or more processors, based on the first joint motion data, that a second trial component having one or more surgical parameters different from the first trial component would result in a better range of motion than the first actual range of motion; and after the second trial component is installed, obtaining, by the one or more processors, second joint motion data that provides information regarding a second actual range of motion of the shoulder joint during a second test of the range of motion of the shoulder joint.
  • the model includes an artificial neural network trained to generate the predicted motion data based at least in part on the patient-specific anatomy of the shoulder joint and the parameters of the humeral prosthesis and the glenoid prosthesis, and refining the model comprises performing a backpropagation process that updates parameters of the artificial neural network based on the joint motion data.
  • the joint motion data includes joint distance data indicating a distance between the humeral prosthesis and the glenoid prosthesis, and the method further comprises determining, by the one or more processors, based on the joint distance data, whether a potential dislocation of the shoulder joint has occurred.
  • Clause 15 The computer-implemented method of any of clauses 1-14, the one or more sensors include a Hall sensor.
  • Clause 16 The computer-implemented method of any of clauses 1-15, wherein the joint motion data provides information regarding the motion of the shoulder joint with 6 degrees of freedom. [0112] Clause 17.
  • the method further comprises, after refining the model based on the joint motion data: applying the model to generate, based on the patient-specific anatomy of the shoulder joint and the parameters of the humeral prosthesis and the glenoid prostheses, second predicted motion data that describe a second predicted range of motion of the shoulder joint; and outputting, by the one or more processors, a visualization of the second predicted range of motion.
  • a computing system comprising: a storage system; and one or more processors implemented in circuitry and communicatively coupled to the storage system, the one or more processors configured to perform the methods of any of clauses 1-19.
  • Clause 21 A computing system comprising means for performing the methods of any of clauses 1-19.
  • Clause 22 One or more non-transitory computer-readable storage media including instructions stored thereon that, when executed, cause a computing system to perform the methods of any of clauses 1-19.
  • Computer-readable media may include computer-readable storage media, which corresponds to a tangible medium such as data storage media, or communication media including any medium that facilitates transfer of a computer program from one place to another, e.g., according to a communication protocol.
  • computer-readable media generally may correspond to (1) tangible computer-readable storage media which is non-transitory or (2) a communication medium such as a signal or carrier wave.
  • Data storage media may be any available media that can be accessed by one or more computers or one or more processors to retrieve instructions, code and/or data structures for implementation of the techniques described in this disclosure.
  • a computer program product may include a computer-readable medium.
  • computer-readable storage media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage, or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer- readable medium.
  • coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave are included in the definition of medium.
  • DSL digital subscriber line
  • computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but are instead directed to non-transitory, tangible storage media.
  • Disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.
  • processors which may be implemented as fixed-function processing circuits, programmable circuits, or combinations thereof, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuitry.
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • Fixed-function circuits refer to circuits that provide particular functionality and are preset on the operations that can be performed.
  • Programmable circuits refer to circuits that can programmed to perform various tasks and provide flexible functionality in the operations that can be performed. For instance, programmable circuits may execute instructions specified by software or firmware that cause the programmable circuits to operate in the manner defined by instructions of the software or firmware.
  • Fixed-function circuits may execute software instructions (e.g., to receive parameters or output parameters), but the types of operations that the fixed-function circuits perform are generally immutable. Accordingly, the terms “processor” and “processing circuity,” as used herein may refer to any of the foregoing structures or any other structure suitable for implementation of the techniques described herein.

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Animal Behavior & Ethology (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Pathology (AREA)
  • Rheumatology (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Dentistry (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Robotics (AREA)
  • Prostheses (AREA)

Abstract

La présente invention concerne une méthode qui consiste à appliquer, au moyen d'un ou de plusieurs processeurs mis en œuvre dans un ensemble de circuits, un modèle pour générer, sur la base de l'anatomie spécifique au patient d'une articulation d'épaule d'un patient et sur la base de paramètres d'une prothèse humérale et d'une prothèse glénoïde, des données de mouvement prédites qui décrivent une plage prédite de mouvement de l'articulation d'épaule d'un patient ; à obtenir des données de mouvement d'articulation à partir d'un ou de plusieurs capteurs inclus dans au moins une prothèse humérale ou une prothèse glénoïde, la prothèse humérale étant implantée sur un humérus de l'articulation d'épaule et la prothèse glénoïde étant implantée sur une omoplate de l'articulation d'épaule, et les données de mouvement d'articulation fournissent des informations concernant une plage réelle de mouvement de l'articulation d'épaule pendant un test d'une plage de mouvement de l'articulation d'épaule ; et à affiner le modèle sur la base des données de mouvement d'articulation.
PCT/US2025/025427 2024-04-23 2025-04-18 Visualisation et planification d'arthroplastie de l'épaule Pending WO2025226549A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202463637720P 2024-04-23 2024-04-23
US63/637,720 2024-04-23

Publications (1)

Publication Number Publication Date
WO2025226549A1 true WO2025226549A1 (fr) 2025-10-30

Family

ID=95784002

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2025/025427 Pending WO2025226549A1 (fr) 2024-04-23 2025-04-18 Visualisation et planification d'arthroplastie de l'épaule

Country Status (1)

Country Link
WO (1) WO2025226549A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170007330A1 (en) * 2015-07-08 2017-01-12 Zimmer, Inc. Sensor-based shoulder system and method
WO2020261249A1 (fr) * 2019-06-28 2020-12-30 Formus Labs Limited Système de planification pré-opératoire orthopédique
WO2022169673A1 (fr) 2021-02-04 2022-08-11 Kla Corporation Amélioration de sensibilité d'inspection de défauts optique et meb
US20240008926A1 (en) * 2022-07-08 2024-01-11 Orthosoft Ulc Computer-assisted shoulder surgery and method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170007330A1 (en) * 2015-07-08 2017-01-12 Zimmer, Inc. Sensor-based shoulder system and method
WO2020261249A1 (fr) * 2019-06-28 2020-12-30 Formus Labs Limited Système de planification pré-opératoire orthopédique
WO2022169673A1 (fr) 2021-02-04 2022-08-11 Kla Corporation Amélioration de sensibilité d'inspection de défauts optique et meb
US20240008926A1 (en) * 2022-07-08 2024-01-11 Orthosoft Ulc Computer-assisted shoulder surgery and method

Similar Documents

Publication Publication Date Title
US11938030B1 (en) Artificial neural network for aligning joint replacement implants
US20250169885A1 (en) Orthopaedic pre-operative planning system
AU2018233036B2 (en) A method incorporating computerimplemented steps, for providing alignment information data for the alignment of an orthopaedic implant for a joint of a patient
US10789858B2 (en) Method for creating a computer model of a joint for treatment planning
US20150106024A1 (en) Systems and methods for determining implant position and orientation
US20230085093A1 (en) Computerized prediction of humeral prosthesis for shoulder surgery
AU2013210797A1 (en) Method and system for human joint treatment plan and personalized surgery planning using 3-D kinematics, fusion imaging and simulation
US20240008925A1 (en) Apparatus, system, and method for determining an alignment of a knee prosthesis in a bone of a patient
KR20240091287A (ko) 환자-특정 관절 성형 디바이스들 및 연관된 시스템들 및 방법들
WO2020261249A1 (fr) Système de planification pré-opératoire orthopédique
WO2023200562A1 (fr) Évaluation d'implant orthopédique spécifique à un patient
US20240293182A1 (en) Surgical system
WO2025226549A1 (fr) Visualisation et planification d'arthroplastie de l'épaule
US20240315603A1 (en) Patient Morphology-Driven Knee Kinematics
WO2025080516A1 (fr) Systèmes de planification d'alignement d'articulation dans des interventions orthopédiques
Zhang et al. [Retracted] Spinal Biomechanical Modelling in the Process of Lumbar Intervertebral Disc Herniation in Middle‐Aged and Elderly
Winslow et al. Analysis of Variation in Sagittal Curvature of the Femoral Condyles
Crespo Finite Element Modeling of Patient-Specific Total Shoulder Arthroplasty
US20240087716A1 (en) Computer-assisted recommendation of inpatient or outpatient care for surgery
EP4382065A2 (fr) Systèmes et procédés pour éviter l'incisure trochléaire
Rodrigo de Marinis et al. JSES Reviews, Reports, and Techniques
Denton et al. Novel radiographic stem version predictor from anterior-posterior radiographs
Rivero Crespo Finite Element Modeling of Patient-Specific Total Shoulder Arthroplasty

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25727048

Country of ref document: EP

Kind code of ref document: A1