WO2025229561A1

WO2025229561A1 - Systems and methods for detecting and visualizing implanted devices in image volumes

Info

Publication number: WO2025229561A1
Application number: PCT/IB2025/054510
Authority: WO
Inventors: Rasika A. PARKAR; Shreya SRIDHAR; Michael D. Ketcha; Mehdi Rahman; Andre D. SOUZA; Elizabeth R. ROONEY; Amir EFTEKHAR; Rejeesh Radhakrishnan
Original assignee: Medtronic Navigation Inc
Current assignee: Medtronic Navigation Inc
Priority date: 2024-05-03
Filing date: 2025-04-30
Publication date: 2025-11-06
Anticipated expiration: 2026-11-03

Abstract

A system according to at least one embodiment of the present disclosure includes: a processor; and a memory coupled with the processor and storing data thereon that, when processed by the processor, enable the processor to: provide an input associated with a surgical image to a data model; receive, from the data model as a result of the data model processing the input associated with the surgical image, a segmented image that depicts at least one implanted device; and render, to a display, a depiction of the at least one implanted device in the segmented image.

Description

SYSTEMS AND METHODS FOR DETECTING AND VISUALIZING IMPLANTED DEVICES IN IMAGE VOLUMES

BACKGROUND

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/642,400, filed 3 May 2024, the entire content of which is incorporated herein by reference. [0002] The present disclosure is generally directed to surgeries or surgical procedures and relates more particularly to identifying and confirming implant placement in surgeries or surgical procedures.

[0003] Surgical robots may assist a surgeon or other medical provider in carrying out a surgical procedure, or may complete one or more surgical procedures autonomously. Imaging may be used by a medical provider for diagnostic and/or therapeutic purposes. Patient anatomy can change over time, particularly following placement of a medical implant in the patient anatomy.

BRIEF SUMMARY

[0004] During the course of a surgery or surgical procedure, a physician may desire to identify and confirm the placement of surgical screws, implanted medical devices, and/or the like after such devices have been implanted, such as when the physician wishes to confirm that there have been no breaches in patient anatomy as a result of introducing the implant. Such a confirmation process may involve capturing a three-dimensional (3D) scan of the patient and verifying, by reviewing the scan, that there have been no breaches to patient anatomy. However, the large number of two-dimensional (2D) slices within the 3D scan that require review may increase operating room times and overall cost. According to at least one embodiment of the present disclosure, one or more data models receive the 3D scan as an input and output information about an identified implant (e.g., an output containing information about the tip location of the screw and an implant trajectory of the screw). The output information can then be rendered to a display, facilitating quicker review of the 3D scan. According to at least one embodiment of the present disclosure, planning and navigation data are leveraged to perform an auto-registration between the 3D scan and a prior scan of patient anatomy to enable the implanted device depicted in the 3D scan to be identified and information associated therewith to be rendered to a display for review.

[0005] Example aspects of the present disclosure include: [0006] A system according to at least one embodiment of the present disclosure comprises: a processor; and a memory coupled with the processor and storing data thereon that, when processed by the processor, enable the processor to: provide an input associated with a surgical image to a data model; receive, from the data model as a result of the data model processing the input associated with the surgical image, a segmented image that depicts at least one implanted device; and render, to a display, a depiction of the at least one implanted device in the segmented image.

[0007] Any of the aspects herein, wherein the data model comprises at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network.

[0008] Any of the aspects herein, wherein the input comprises a reconstructed image volume associated with image data captured by an imaging device.

[0009] Any of the aspects herein, wherein the data model is trained with training data comprising information about a center of mass of a simulated implantable device.

[0010] Any of the aspects herein, wherein the data model is trained with training data comprising labeled training data.

[0011] Any of the aspects herein, wherein the at least one implanted device comprises a surgical screw.

[0012] Any of the aspects herein, wherein the data, when processed by the processor, further enable the processor to: determine, based on the segmented image, location information associated with the at least one implanted device.

[0013] Any of the aspects herein, wherein the data, when processed by the processor, further enable the processor to: render, to the display, the location information.

[0014] Any of the aspects herein, wherein the location information comprises information about a trajectory along which the at least one implanted device was implanted.

[0015] Any of the aspects herein, wherein the data, when processed by the processor, further enable the processor to: render, to the display, a depiction of a planned implant location of the at least one implanted device.

[0016] Any of the aspects herein, wherein the depiction of the planned implant location is rendered next to the depiction of the at least one implanted device in the segmented image.

[0017] A system according to at least one embodiment of the present disclosure comprises: a processor; and a memory coupled with the processor and storing data thereon that, when processed by the processor, enables the processor to: provide an input associated with a surgical image into a first data model; receive, from the first data model as a result of the first data model processing the input associated with the surgical image, a segmented image that depicts at least one implanted device; provide the segmented image into a second data model; and receive, from the second data model as a result of the second data model processing the segmented image, an output including information about a center of mass and a location of an end of the at least one implanted device depicted in the segmented image.

[0018] Any of the aspects herein, wherein at least one of the first data model and the second data model comprise at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network.

[0019] Any of the aspects herein, wherein the surgical image comprises a reconstructed image volume.

[0020] Any of the aspects herein, wherein the second data model is trained using training data that comprises information about one or more parameters of a simulated implantable device.

[0021] Any of the aspects herein, wherein the training data comprise information about a center of mass and an end location of the simulated implantable device.

[0022] Any of the aspects herein, wherein the training data comprises labeled training data.

[0023] Any of the aspects herein, wherein the at least one implanted device comprises a surgical screw.

[0024] A system according to at least one embodiment of the present disclosure comprises: a processor; and a memory coupled with the processor and storing data thereon that, when processed by the processor, enable the processor to: segment a reconstructed image volume into at least two segments, wherein at least one segment of the at least two segments comprises a depiction of an implanted device; determine, based on navigation information associated with the implanted device, a location of the implanted device; and render, to a display, a depiction of the location of the implanted device.

[0025] Any of the aspects herein, wherein the data, when processed by the processor, further enable the processor to: register the reconstructed image volume with a scan of a patient captured before the implanted device is implanted.

[0026] Any of the aspects herein, wherein the depiction of the location of the implanted device comprises information about a trajectory along which the implanted device was implanted.

[0027] Any of the aspects herein, wherein the implanted device comprises a surgical screw.

[0028] Any of the aspects herein, wherein the data, when processed by the processor, further enable the processor to: render, to the display, a depiction of a planned implant location of the implanted device. [0029] Any of the aspects herein, wherein the depiction of the planned implant location is rendered next to the depiction of the location of the implanted device.

[0030] Any aspect in combination with any one or more other aspects.

[0031] Any one or more of the features disclosed herein.

[0032] Any one or more of the features as substantially disclosed herein.

[0033] Any one or more of the features as substantially disclosed herein in combination with any one or more other features as substantially disclosed herein.

[0034] Any one of the aspects/features/embodiments in combination with any one or more other aspects/features/ embodiments .

[0035] Use of any one or more of the aspects or features as disclosed herein.

[0036] It is to be appreciated that any feature described herein can be claimed in combination with any other feature(s) as described herein, regardless of whether the features come from the same described embodiment.

[0037] The details of one or more aspects of the disclosure are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the techniques described in this disclosure will be apparent from the description and drawings, and from the claims. [0038] The phrases “at least one”, “one or more”, and “and/or” are open-ended expressions that are both conjunctive and disjunctive in operation. For example, each of the expressions “at least one of A, B and C”, “at least one of A, B, or C”, “one or more of A, B, and C”, “one or more of A, B, or C” and “A, B, and/or C” means A alone, B alone, C alone, A and B together, A and C together, B and C together, or A, B and C together. When each one of A, B, and C in the above expressions refers to an element, such as X, Y, and Z, or class of elements, such as XI -Xn, Yl-Ym, and Zl-Zo, the phrase is intended to refer to a single element selected from X, Y, and Z, a combination of elements selected from the same class (e.g., XI and X2) as well as a combination of elements selected from two or more classes (e.g., Y1 and Zo).

[0039] The term “a” or “an” entity refers to one or more of that entity. As such, the terms “a” (or “an”), “one or more” and “at least one” can be used interchangeably herein. It is also to be noted that the terms “comprising”, “including”, and “having” can be used interchangeably.

[0040] The preceding is a simplified summary of the disclosure to provide an understanding of some aspects of the disclosure. This summary is neither an extensive nor exhaustive overview of the disclosure and its various aspects, embodiments, and configurations. It is intended neither to identify key or critical elements of the disclosure nor to delineate the scope of the disclosure but to present selected concepts of the disclosure in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other aspects, embodiments, and configurations of the disclosure are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.

[0041] Numerous additional features and advantages of the present disclosure will become apparent to those skilled in the art upon consideration of the embodiment descriptions provided hereinbelow.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0042] The accompanying drawings are incorporated into and form a part of the specification to illustrate several examples of the present disclosure. These drawings, together with the description, explain the principles of the disclosure. The drawings simply illustrate preferred and alternative examples of how the disclosure can be made and used and are not to be construed as limiting the disclosure to only the illustrated and described examples. Further features and advantages will become apparent from the following, more detailed, description of the various aspects, embodiments, and configurations of the disclosure, as illustrated by the drawings referenced below. [0043] Fig. 1 is a block diagram of aspects of a system according to at least one embodiment of the present disclosure;

[0044] Fig. 2 is a block diagram of aspects of a memory according to at least one embodiment of the present disclosure;

[0045] Fig. 3A is a schematic of aspects of an imaging device according to at least one embodiment of the present disclosure;

[0046] Fig. 3B is a schematic of additional aspects of the imaging device according to at least one embodiment of the present disclosure;

[0047] Fig. 4 is a block diagram of an example input image and an output image generated by an analysis engine based on the input image according to at least one embodiment of the present disclosure;

[0048] Fig. 5 is a flowchart according to at least one embodiment of the present disclosure; and

[0049] Fig. 6 is a flowchart according to at least one embodiment of the present disclosure.

DETAILED DESCRIPTION

[0050] It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example or embodiment, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, and/or may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the disclosed techniques according to different embodiments of the present disclosure). In addition, while certain aspects of this disclosure are described as being performed by a single module or unit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units or modules associated with, for example, a computing device and/or a medical device.

[0051] In one or more examples, the described methods, processes, and techniques may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer-readable medium and executed by a hardware-based processing unit. Alternatively or additionally, functions may be implemented using machine learning models, neural networks, artificial neural networks, or combinations thereof (alone or in combination with instructions). Computer-readable media may include non-transitory computer-readable media, which corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, 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).

[0052] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors (e.g., Intel Core i3, i5, i7, or i9 processors; Intel Celeron processors; Intel Xeon processors; Intel Pentium processors; AMD Ryzen processors; AMD Athlon processors; AMD Phenom processors; Apple A10 or 10X Fusion processors; Apple Al l, A12, A12X, A12Z, or A13 Bionic processors; or any other general purpose microprocessors), graphics processing units (e.g., Nvidia GeForce RTX 2000-series processors, Nvidia GeForce RTX 3000-series processors, AMD Radeon RX 5000-series processors, AMD Radeon RX 6000-series processors, or any other graphics processing units), application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor” as used herein may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. Also, the techniques could be fully implemented in one or more circuits or logic elements.

[0053] Before any embodiments of the disclosure are explained in detail, it is to be understood that the disclosure is not limited in its application to the details of construction and the arrangement of components set forth in the following description or illustrated in the drawings. The disclosure is capable of other embodiments and of being practiced or of being carried out in various ways. Also, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. The use of “including,” “comprising,” or “having” and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Further, the present disclosure may use examples to illustrate one or more aspects thereof. Unless explicitly stated otherwise, the use or listing of one or more examples (which may be denoted by “for example,” “by way of example,” “e.g.,” “such as,” or similar language) is not intended to and does not limit the scope of the present disclosure.

[0054] Surgeries or surgical procedures can include implanting surgical devices or other objects, such as surgical screws, into a patient. The procedure may include capturing an initial 3D scan of the patient. Following the placement of the surgical screws and other instrumentation in, for example, the spine of the patient, surgeons may capture a follow-up 3D scan to confirm the placement of the screw(s) and/or to identify any breaches in the vertebra (e.g., a lateral breach, a medial breach, etc.). This confirmation step includes an image review step where the surgeon or other user visually reviews and verifies the placement of each screw. This confirmation step may require the surgeon or other user to navigate through the series of images (e.g., by pressing up/down or left/right arrow keys on a keyboard). This confirmation step can take significant time. For example, an 0-arm imaging system capturing a 0.83 slice of a thoracic vertebra (which is approximately 25mm in thickness), the user must navigate through approximately 30 views to move from pedicle to pedicle. Thus, in a 3D volume comprising 5 pedicles, the user must navigate through approximately 150 images. Additionally, the surgeon may need to view oblique and sagittal adjustments for two screws in each pedicle. Such viewing may add significant time and costs to the operating room that can be reduced or minimized.

[0055] According to at least one embodiment of the present disclosure, an artificial intelligence (Al) or machine learning (ML) data model (e.g., a neural network) processes data to locate placed screws in the 3D volume and displays information about the screw location (e.g., screw tip and screw trajectory) to the surgeon. The data model may be trained using simulated screws in cadaver datasets. For example, Computer Aided Design (CAD) models of the screws may be used to simulate metal and metal artifacts in the 0-arm scans. The data model may be trained to perform screw segmentation in the reconstructed volume. From the segmentation, the tip and trajectory of the screw may be extracted by identifying the tip point of the screw shaft and the center point of the screw shaft ball. The definitions of the point locations in the simulated data may be based on the CAD models of the screws. The data model may take the segmented volume (whether generated by a data model or other computer vision techniques) as an input and output information about the screw (e.g., the screw tip location and trajectory of the screw). In some cases, the user may be able to select a screw from a list of detected screws (which may be provided, for example, by a navigation system), and the system may automatically slice the oblique planes along the computed screw trajectory for visualization on a display.

[0056] According to at least one embodiment of the present disclosure, planning and navigation data may be used to register the patient with the 0-arm (or other imaging device) through autoregistration. The initial scan may be captured intra-operatively prior to placing screws into vertebral bodies. Once the 0-arm exam is registered to the patient anatomy, the surgeon may place the screws by navigating on the auto-registered exam. The navigation system may track the navigated components and may store the type, location, and trajectory of the navigated screws as coordinate data in a log file associated with the patient exam. After the screws have been placed into the anatomy using navigation, the surgeon may choose to intra-operatively assess the screw (or other spinal hardware) placement and identify if there are breaches by taking a second, confirmation scan. For example, the surgeon may view a list of the navigated screws provided by the navigation system and select one or more screws that the surgeon wishes to review. A combination of the screw coordinate information saved in the log file and auto-registration data associated with the second, confirmation scan can then be used by the system to detect the screws and align crosshairs to the screw trajectory without significant intervention or action from the surgeon. The auto-registration data may also include camera coordinate locations of the patient reference frame, 0-arm tracker(s), and geometric calibration data.

[0057] Embodiments of the present disclosure provide technical solutions to one or more of the problems of time-intensive and/or inaccurate review of implant location and/or trajectory of implanted devices, among other technical problems.

[0058] Turning first to Fig. 1, a block diagram of aspects of a system 100 according to at least one embodiment of the present disclosure are shown. The system 100 may be used to identify and confirm the implant location and trajectory of one or more implantable devices; control, pose, and/or otherwise manipulate a surgical mount system, a surgical arm, and/or surgical tools or implantable devices attached thereto; and/or carry out one or more other aspects of one or more of the methods disclosed herein. The system 100 comprises a computing device 102, one or more imaging devices 112, a robot 114, a navigation system 118, a database 130, and/or a cloud or other network 134. Systems according to other embodiments of the present disclosure may comprise more or fewer components than the system 100. For example, the system 100 may not include one or more components of the computing device 102, the database 130, and/or the cloud 134. [0059] The computing device 102 comprises a processor 104, a memory 106, a communication interface 108, and a user interface 110. Computing devices according to other embodiments of the present disclosure may comprise more or fewer components than the computing device 102.

[0060] The processor 104 of the computing device 102 may be any processor described herein or any similar processor. The processor 104 may be configured to execute instructions stored in the memory 106, which instructions may cause the processor 104 to carry out one or more computing steps utilizing or based on data received from the imaging device 112, the robot 114, the navigation system 118, the database 130, and/or the cloud 134.

[0061] The memory 106 may be or comprise RAM, DRAM, SDRAM, other solid-state memory, any memory described herein, or any other tangible, non-transitory memory for storing computer- readable data and/or instructions. The memory 106 may store information or data useful for completing, for example, any step of the methods 500 and/or 600 described herein, or of any other methods. The memory 106 may be configured to store a variety of operational parameters, weights, training data, analysis applications, and/or the like. In the example of Fig. 2, memory 106 may store or comprise image processing 208, segmentation 212, one or more data models 216, output data 220, one or more pre-processing engines 224, one or more post-processing engines 228, transformation 232, and registration 236. In other examples, the memory 106 may act as a temporary buffer for storing data until such data can be uploaded to the database 130 and/or other data repository.

[0062] The content of the memory 106, if provided as an instruction, may, in some embodiments, be organized into one or more applications, modules, packages, layers, or engines. Although various contents of memory 106 may be described as instructions, it should be appreciated that functionality described herein can be achieved through use of instructions, algorithms, and/or Al or ML data models. The data, algorithms, and/or instructions may cause the processor 104 to manipulate data stored in the memory 106 and/or received from or via the imaging device 112, the robot 114, the database 130, and/or the cloud 134.

[0063] The image processing 208 enables the processor 104 to process image data of an image (received from, for example, the imaging device 112, an imaging device of the navigation system 118, or any imaging device) for the purpose of, for example, identifying information about a patient and/or an object such as an implanted device depicted in the image. “Image data” as used herein refers to the data generated or captured by an imaging device 112, including in a machine- readable form, a graphical/visual form, and in any other form. The information may comprise, for example, a pose of the patient, a pose of the implanted device, a boundary of the reference marker(s) proximate the patient, etc. The information obtained from the image processing 208 may enable, for example, determining of the pose of the patient, the pose of reference markers or localizers positioned proximate the patient in a surgical environment, combinations thereof, and/or the like. The information may also enable registration of the patient to a common coordinate frame of the imaging device 112, and/or registration of the elements depicted in the image data to the common coordinate frame of the imaging device 112. The image processing 208 may use segmentation 212 to identify the patient and/or the one or more objects, as described below.

[0064] The segmentation 212 enables the processor 104 to segment the image data so as to identify the patient and/or one or more objects such as, for example, the an implanted device in the image data. The segmentation 212 may enable the processor 104 to identify a boundary of an object or the patient by using, for example, feature recognition. For example, the segmentation 212 may enable the processor 104 to identify one or more vertebrae of the patient and/or one or more devices (e.g., surgical screws) implanted in the vertebrae of the patient in the image data. In other instances, the segmentation 212 may enable the processor 104 to identify a boundary of an object (e.g., a surgical screw) by determining a difference in or contrast between colors or grayscales of image pixels.

[0065] In some examples, the segmentation 212 may comprise one or more data models (e.g., neural networks) trained to segment the image data into a plurality of segments. For example, the segmentation may comprise a first neural network trained on image data that enables the first neural network to receive the image data such as a 3D volume reconstruction of the patient as an input and output the output data 220 that comprises a segmented version of the 3D volume reconstruction.

Additionally or alternatively, the first neural network may receive other input data, such as data from the navigation system 118. For instance, information about the type, location, and/or trajectory of screws or other implanted devices that have been tracked by the navigation system 118 during the surgery or surgical procedure and stored in the memory 106 and/or the database 130 may be input into the first neural network to facilitate the segmentation 212. One or more of the segments in the 3D volume may correspond to one or more metal objects (e.g., surgical screws or other implanted devices). In some examples, the training data may comprise labeled data (such as when the first neural network receives supervised training), unlabeled data (such as when the first neural network receives unsupervised training), or a combination of labeled data and unlabeled data (such as when the neural network receives semi-supervised learning).

[0066] The transformation 232 enables the processor 104 to transform one coordinate system into another coordinate system. In other words, the transformation 232 enables the processor 104 to transform the first coordinate system (e.g., the patient coordinate system) into the second coordinate system (e.g., the reference frame coordinate system) based on, for example, the registration of the first coordinate system and the third coordinate system and the registration of the second coordinate system and the third coordinate system.

[0067] The registration 236 enables the processor 104 to correlate one coordinate system with another coordinate system. For example, the registration 236 may enable the processor 104 to correlate or map a first coordinate system (e.g., a patient coordinate system) with a third coordinate system (e.g., an imaging device coordinate system) and a second coordinate system (e.g., a reference frame coordinate system) with the third coordinate system (e.g., the imaging device coordinate system).

[0068] The processor 104 may utilize data stored in the memory 106 as one or more neural networks. In some examples, the data model 216 may be or comprise the one or more neural networks. In some other examples, the neural network may be or include any machine learning network such as a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Deep Reinforcement Network (DRN), a Transformer Network, or any other neural network capable of accomplishing functions of the system 100 described herein. Some elements stored in the memory 106 may be described as instructions or instruction sets, data or data sets, and/or the like. Additionally or alternatively, some functions of the system 100 may be implanted using machine learning techniques. An Al or ML system, such as a neural network, may support various inputs supportive of implementing aspects of the present disclosure. For example, a neural network may support generating outputs based on model inputs including, but not limited to, image data (e.g., provided by the imaging device 112, image sensor, or the like). The neural network may support providing outputs such as classifications (e.g., whether or not a pixel in an image corresponds to a surgical implant) and predictions (e.g., a heatmap or other indicator of surgical implant location).

[0069] The data model 216 may comprise a neural network that supports supervised learning machine learning algorithms and semi-supervised machine learning algorithms. The neural network may support locked execution modes (e.g., changes or updates to the neural network occur only when the neural network is retrained, and the neural network does not continue to learn and modify its algorithm when processing non-training data).

[0070] The data model 216 may support segmentation of a medical image and/or identification of surgical implant location, and may be trained and/or updated based on data (e.g., training data 206) provided or accessed by the computing device 102, the imaging device 112, the database 130, and/or the like. The data model 216 may be built and updated by the system 100 (or operator thereof) based on the training data 206. [0071] The training data 206 may be or comprise sets of training data that includes simulated metal objects (e.g., surgical screws) or other simulated implantable devices in a patient environment (e.g., in cadaver datasets) with annotations that indicate the aspects or parameters of the simulated metal object. For example, the simulated data may comprise CAD models of surgical screws with the shaft of the screw labeled with a first number and the tulip of the screw labeled with a second number. The simulated data may comprise information about one or more parameters of the simulated metal object, such as a border or shape (e.g., tip or end locations relative to another point on the simulated metal object), a center of mass, one or more dimensions (e.g., length, width, height, etc.), combinations thereof, and/or the like. In some cases, the data model 216 may be trained using multiple different data sets of the training data 206. The data model 216 may be trained to identify metal objects (e.g., surgical screws) in a surgical image and output the output data 220. The output data 220 may be or comprise information associated with the identified metal objects, such as the location of the tip of the surgical screw, a center of mass of the surgical screw, an implant trajectory of the screw, combinations thereof, and/or the like.

[0072] In some examples, prior to being input into the data model 216, images may undergo one or more pre-processing steps performed using the pre-processing engine 224. Such pre-processing steps may include normalization, augmentation, and resolution adjustment. For example, images may be resized to a consistent dimension, ensuring that the data model 216 receives inputs of uniform size. Additionally or alternatively, pixel values of input images may be normalized, such as ranging between 0 and 1. The pre-processing may include one or more data augmentation techniques. Such techniques may include rotation, zooming, cropping, flipping, etc. of the original images.

[0073] The outputs of the data model 216 may be further processed and/or interpreted by software or other content of the memory 106. For example, the outputs of the data model 216 may be postprocessed by the post-processing engine 228. Post-processing procedures may include performing morphological operations to smooth segmented regions, fill holes or other missing data, or remove small noise artifacts. The post-processing may be applied to map the output of the data model 216 to clinically relevant metrics or visual representations, facilitating easier interpretation by the user of the system 100. For example, the post-processing engine 228 may receive an output from the data model 216 indicative of the position of the tip of an implanted surgical screw. The post-processing engine 228 may then render a depiction of a surgical scan of the patient’s anatomy and the surgical screw to a display, and introduce a visual marker or other indicator to the tip of the implanted surgical screw. [0074] The communication interface 108 may be used for receiving image data or other information from an external source (such as the imaging device 112, the robot 114, the navigation system 118, the database 130, the cloud 134, and/or any other system or component not part of the system 100), and/or for transmitting instructions, images, or other information to an external system or device (e.g., another computing device 102, the imaging device 112, the robot 114, the navigation system 118, the database 130, the cloud 134, and/or any other system or component not part of the system 100). The communication interface 108 may comprise one or more wired interfaces (e.g., a USB port, an Ethernet port, a Firewire port) and/or one or more wireless transceivers or interfaces (configured, for example, to transmit and/or receive information via one or more wireless communication protocols such as 802.11a/b/g/n, Bluetooth, NFC, ZigBee, and so forth). In some embodiments, the communication interface 108 may be useful for enabling the device 102 to communicate with one or more other processors 104 or computing devices 102, whether to reduce the time needed to accomplish a computing-intensive task or for any other reason.

[0075] The user interface 110 may be or comprise a keyboard, mouse, trackball, monitor, television, screen, touchscreen, and/or any other device for receiving information from a user and/or for providing information to a user. The computing device 102 may comprise one or more user interfaces 110. The user interface 110 may be used, for example, to receive a user selection or other user input regarding any step of any method described herein. Notwithstanding the foregoing, any required input for any step of any method described herein may be generated automatically by the system 100 (e.g., by the processor 104 or another component of the system 100) or received by the system 100 from a source external to the system 100. In some embodiments, the user interface 110 may be useful to allow a surgeon or other user to modify instructions to be executed by the processor 104 according to one or more embodiments of the present disclosure, and/or to modify or adjust a setting of other information displayed on the user interface 110 or corresponding thereto.

[0076] Although the user interface 110 is shown as part of the computing device 102, in some embodiments, the computing device 102 may utilize a user interface 110 that is housed separately from one or more remaining components of the computing device 102. In some embodiments, the user interface 110 may be located proximate one or more other components of the computing device 102, while in other embodiments, the user interface 110 may be located remotely from one or more other components of the computing device 102.

[0077] The imaging device 112 may be operable to image anatomical feature(s) (e.g., a bone, veins, tissue, etc.) and/or other aspects of patient anatomy to yield image data (e.g., image data depicting or corresponding to a bone, veins, tissue, etc.). In various examples, the image data may comprise data corresponding to an anatomical feature of a patient, or to a portion thereof. The image data may be or comprise a preoperative image, an intraoperative image, a postoperative image, or an image taken independently of any surgical procedure. In some embodiments, a first imaging device 112 may be used to obtain first image data (e.g., a first image) at a first time, and a second imaging device 112 may be used to obtain second image data (e.g., a second image) at a second time after the first time. The imaging device 112 may be capable of taking a 2D image or a 3D image to yield the image data. The imaging device 112 may be or comprise, for example, an ultrasound scanner (which may comprise, for example, a physically separate transducer and receiver, or a single ultrasound transceiver), an O-arm, a C-arm, a G-arm, or any other device utilizing X-ray-based imaging (e.g., a fluoroscope, a CT scanner, or other X-ray machine), a magnetic resonance imaging (MRI) scanner, an optical coherence tomography (OCT) scanner, an endoscope, a microscope, an optical camera, a thermographic camera (e.g., an infrared camera), a radar system (which may comprise, for example, a transmitter, a receiver, a processor, and one or more antennae), or any other imaging device 112 suitable for obtaining images of an anatomical feature of a patient. For purposes of the present disclosure, unless specified otherwise, image data may be considered to be continuous and/or provided as an image data stream if the image data represents two or more frames per second.

[0078] With reference to Figs. 3A-3B, aspects of the imaging device 112 according to at least one embodiment of the present disclosure are shown. The imaging device 112 may include one or more imaging components that enables generation of one or more images of patient anatomy. For example, the imaging device 112 depicted in Figs. 3A-3B comprises an upper wall or member 304, a lower wall or member 308, and a pair of sidewalls or members 312A, 312B. In some embodiments, the imaging device 112 is fixed securable to an operating room wall 316 (such as, for example, a ground surface of an operating room or other room). In other embodiments, the imaging device 112 may be releasably securable to the operating room wall 316 or may be a standalone component that is simply supported by the operating room wall 316.

[0079] A table 324 configured to support a patient 320 may be positioned orthogonally to the imaging device 112, such that the table 324 extends in a first direction from the imaging device 112. In some embodiments, the table 324 may be mounted to the imaging device 112. In other embodiments, the table 324 may be releasably mounted to the imaging device 112. In still other embodiments, the table 324 may not be attached to the imaging device 112. In such embodiments, the table 324 may be supported and/or mounted to an operating room wall, for example. In embodiments where the table 324 is mounted to the imaging device 112 (whether detachably mounted or permanently mounted), the table 324 may be mounted to the imaging device 112 such that a pose of the table 324 relative to the imaging device 112 is selectively adjustable.

[0080] The table 324 may be any operating table configured to support the patient 320 during a surgical procedure. The table 324 may include any accessories mounted to or otherwise coupled to the table 324 such as, for example, a bed rail, a bed rail adaptor, an arm rest, an extender, or the like. The table 324 may be stationary or may be operable to maneuver the patient 320 (e.g., the table 324 may be able to move). In some embodiments, the table 324 has two positioning degrees of freedom and one rotational degree of freedom, which allows positioning of the specific anatomy of the patient anywhere in space (within a volume defined by the limits of movement of the table 324). For example, the table 324 can slide forward and backward and from side to side, and can tilt (e.g., around an axis positioned between the head and foot of the table 324 and extending from one side of the table 324 to the other) and/or roll (e.g., around an axis positioned between the two sides of the table 324 and extending from the head of the table 324 to the foot thereof). In other embodiments, the table 324 can bend at one or more areas (which bending may be possible due to, for example, the use of a flexible surface for the table 324, or by physically separating one portion of the table 324 from another portion of the table 324 and moving the two portions independently). In at least some embodiments, the table 324 may be manually moved or manipulated by, for example, a surgeon or other user, or the table 324 may comprise one or more motors, actuators, and/or other mechanisms configured to enable movement and/or manipulation of the table 324 by a processor such as the processor 104.

[0081] The imaging device 112 comprises a gantry. The gantry may be or comprise a substantially circular, or “O-shaped,” housing that enables imaging of objects placed into an isocenter of the housing. In other words, the gantry may be positioned around the object being imaged. In some embodiments, the gantry may be disposed at least partially within the upper wall 304, the sidewalls 312A, 312B, and the lower wall 308 of the imaging device 112.

[0082] The imaging device 112 also comprises a source 138 and a detector 140. The source 138 may be a device configured to generate and emit radiation, and the detector 140 may be a device configured to detect the emitted radiation. In some embodiments, the source 138 and the detector 140 may be or comprise an imaging source and an imaging detector (e.g., the source 138 and the detector 140 are used to generate data useful for producing images). The source 138 may be positioned in a first position and the detector 140 may be positioned in a second position opposite the source 138. In some embodiments, the source 138 comprises an X-ray source such as, for example, a thermionic emission tube, a cold emission x-ray tube, and/or the like. The source 138 may project a radiation beam that passes through the patient 320 and onto the detector 140 located on the opposite side of the imaging device 112. The detector 140 may be or comprise one or more sensors that receive the radiation beam (e.g., once the radiation beam has passed through the patient 320) and transmit information related to the radiation beam to one or more other components of the system 100 for processing, such as to the processor 104. In some embodiments, the detector 140 may comprise an array. For example, the detector 140 may comprise three 2D flat panel solid-state detectors arranged side-by-side, and angled to approximate the curvature of the imaging device 112. It will be understood, however, that various detectors and detector arrays can be used with the imaging device 112, including any detector configurations used in typical diagnostic fan-beam or cone-beam CT scanners. The source 138 and/or the detector 140 may comprise a collimator 144. The collimator 144 may be configured to confine or shape the radiation beam as the radiation beam is emitted from the source 138 and/or as it is received by the detector 140.

[0083] The source 138 and the detector 140 may be attached to the gantry and configured to rotate 360 degrees around the patient 320 in a continuous or step- wise manner so that the radiation beam can be projected through the patient 320 at various angles. In other words, the source 138 and the detector 140 may rotate, spin, or otherwise revolve about an axis that passes through the top and bottom of the patient, with the volume of interest positioned at the isocenter of the imaging device 112. The imaging device 112 comprises a drive mechanism capable of causing the gantry to move such that the source 138 and the detector 140 encircle the patient 320 on the table 324. Additionally or alternatively, the source 138 and the detector 140 may move along a length of the patient 320. For example, the table 324 holding the patient 320 may move in the direction of arrow 328 while the source 138 and detector 140 remain in a fixed location, such that the length of the patient can be scanned. At each projection angle in the revolution, the radiation beam passes through and is attenuated by the patient 320. The attenuated radiation is then detected by the detector 140. The detected radiation from each of the projection angles can then be processed, using various reconstruction techniques such as image processing 208, to produce a 2D or 3D reconstruction image of the patient 320. In one example, the processor 104 may perform the image processing 208 to generate a 3D cone beam computed tomography (CBCT) reconstruction image.

[0084] Returning to Fig. 1, the robot 114 may be any surgical robot or surgical robotic system. The robot 114 may be or comprise, for example, the Mazor X™ Stealth Edition robotic guidance system. The robot 114 may be configured to position a surgical tool or other component coupled with the robot 114 at one or more precise position(s) and orientation(s), and/or to return the surgical tool or other component coupled with the robot 114 to the same position(s) and orientation(s) at a later point in time. The robot 114 may be configured to manipulate the surgical tool based on guidance from the navigation system 118 to accomplish or to assist with a surgical task. In some embodiments, the robot 114 may be configured to hold and/or manipulate an anatomical element during or in connection with a surgical procedure. The robot 114 may comprise one or more robotic arms 116. In some embodiments, the robotic arm 116 may comprise a first robotic arm and a second robotic arm, though the robot 114 may comprise more than two robotic arms. The robot 114, together with the robotic arm 116, may have, for example, one, two, three, four, five, six, seven, or more degrees of freedom. Further, the robotic arm 116 may be positioned or positionable in any pose, plane, and/or focal point. The pose includes a position and an orientation. As a result, the surgical tool or other object held by the robot 114 (or, more specifically, by the robotic arm 116) may be precisely positionable in one or more needed and specific positions and orientations.

[0085] The robotic arm(s) 116 may comprise one or more sensors and/or reference markers that enable the processor 104 (or a processor of the robot 114) to determine a precise pose in space of the robotic arm (as well as any object or element held by or secured to the robotic arm). In some embodiments, reference markers (e.g., navigation markers) may be placed on the robot 114 (including, e.g., on the robotic arm 116), the imaging device 112, or any other object in the surgical space. The reference markers may be tracked by the navigation system 118, and the results of the tracking may be used by the robot 114 and/or by an operator of the system 100 or any component thereof.

[0086] The navigation system 118 may provide navigation for a surgeon and/or a surgical robot during an operation. The navigation system 118 may be any now-known or future-developed navigation system, including, for example, the Medtronic StealthStation™ S8 surgical navigation system or any successor thereof. The navigation system 118 may include one or more cameras or other sensor(s) for tracking one or more reference markers, navigated trackers, or other objects within the operating room or other room in which some or all of the system 100 is located. The one or more cameras may be optical cameras, infrared cameras, or other cameras. In some embodiments, the navigation system 118 may comprise one or more electromagnetic sensors.

[0087] In some examples, the navigation system 118 may include one or more of an optical tracking system, an acoustic tracking system, an electromagnetic tracking system, a radar tracking system, an inertial measurement unit (IMU) based tracking system, and a computer vision based tracking system. The navigation system 118 may include a transmission device 136 capable of transmitting signals associated with the tracking type. In some cases, the navigation system 118 may be capable of computer vision based tracking of objects present in images captured by the imaging devices 112. For example, the navigation system 118 may comprise one or more tracking devices 148 (provided as, for example, sensors, navigation markers, and/or the like) that support delivery of tracking information associated with the tracking devices 148 to the navigation system 118. The tracking devices 148 may be or comprise devices that communicate sensor information to the navigation system 118 for determining a pose of the tracking devices 148 and/or for localizing an object (e.g., an instrument, surgical tool, implantable device, anatomical element, etc.) relative to an image captured by the imaging device 112. The tracking devices 148 may be active (e.g., by emitting signals), passive (e.g., physical objects seen by the navigation system 118 through use of computer vision), or a combination of active and passive.

[0088] In various embodiments, the navigation system 118 may be used to track a position and orientation (e.g., a pose) of the imaging device 112, the robot 114 and/or robotic arm 116, one or more surgical tools, and/or one or more implantable devices (or, more particularly, to track a pose of a navigated tracker attached, directly or indirectly, in fixed relation to the one or more of the foregoing). The navigation system 118 may include a display for displaying one or more images from an external source (e.g., the computing device 102, imaging device 112, or other source) or for displaying an image and/or video stream from the one or more cameras or other sensors of the navigation system 118. The navigation system 118 may be configured to provide guidance to a surgeon or other user of the system 100 or a component thereof, to the robot 114, or to any other element of the system 100 regarding, for example, a pose of one or more anatomical elements, whether or not a tool is in the proper trajectory, and/or how to move a tool into the proper trajectory to carry out a surgical task according to a preoperative or other surgical plan.

[0089] The database 130 may store information that correlates one coordinate system to another (e.g., one or more robotic coordinate systems to a patient coordinate system and/or to a navigation coordinate system). The database 130 may additionally or alternatively store, for example, one or more surgical plans (including, for example, pose information about a target and/or image information about a patient’s anatomy at and/or proximate the surgical site, for use by the robot 114, the navigation system 118, and/or a user of the computing device 102 or of the system 100); one or more images useful in connection with a surgery to be completed by or with the assistance of one or more other components of the system 100; information associated with one or more elements of the memory 106 (e.g., data sets associated with the training data 206, output data 220 from the data model 216, etc.); and/or any other useful information. The database 130 may be configured to provide any such information to the computing device 102 or to any other device of the system 100 or external to the system 100, whether directly or via the cloud 134. In some embodiments, the database 130 may be or comprise part of a hospital image storage system, such as a picture archiving and communication system (PACS), a health information system (HIS), and/or another system for collecting, storing, managing, and/or transmitting electronic medical records including image data. [0090] The cloud 134 may be or represent the Internet or any other wide area network. The computing device 102 may be connected to the cloud 134 via the communication interface 108, using a wired connection, a wireless connection, or both. In some embodiments, the computing device 102 may communicate with the database 130 and/or an external device (e.g., a computing device) via the cloud 134.

[0091] The system 100 or similar systems may be used, for example, to carry out one or more aspects of any of the methods 500 and/or 600 described herein. The system 100 or similar systems may also be used for other purposes.

[0092] As illustrated in Fig. 4, an analysis application 204 may receive input data 402 and generate output data 404. In some implementations, the input data 402 may be or comprise one or more images generated by the imaging device 112. The imaging device 112 may image the patient to capture a 3D scan of one or more vertebrae of the patient and output a greyscale images depicting the vertebrae as well as one or more metal objects (e.g., surgical screws or other implanted medical devices). In the example shown in Fig. 4, the input data 402 comprises a reconstructed CBCT volume scan that includes a plurality of different views (e.g., an anteroposterior (AP) view, a sagittal view, and an oblique view) depicting a surgical screw 408 implanted in a vertebra 412. The screw tip 416 of the surgical screw 408 is also depicted. It is to be understood that in other examples, additional or alternative implants may be used, such as non-metal objects.

[0093] The analysis application 204 may take the input data 402 as an input and pass the input data 402 through one or more data models 216, such as through one or more neural networks. In one example, the data model 216 may comprise a neural network trained to segment the input data 402 into a segmented image volume. For example, the neural network may receive a CBCT volume scan of a patient after one or more surgical screws have been implanted into the patient. In other examples, additional or alternative data may be input into the one or more data models 216. For instance, geometric information associated with one or more implanted devices (e.g., CAD models or other hardware logs) and/or location information about the one or more implanted devices (e.g., type, location, and/or trajectory of the one or more implanted devices that were tracked by the navigation system 118 while being implanted) may be passed as input data into the one or more data models 216. The neural network may be trained to receive the volume scan and segment the image to identify the one or more surgical screws. In other examples, the data model 216 may use segmentation 212 or other computer vision techniques (e.g., edge-detection algorithms) to identify the surgical screws.

[0094] Once the input data 402 has been segmented (whether by the use of computer vision techniques or by a neural network), the segmented input data may be passed through a second neural network that outputs information about the location of the surgical screw and/or information about an implant trajectory of the surgical screw (e.g., the trajectory along which the surgical screw was implanted into the patient’s anatomy). The information about the location of the surgical screw may be or comprise information about the location of the screw tip, information about the center of mass of the surgical screw, combinations thereof, and/or the like. For example, the segmented input data may be passed through the second neural network, which may label or otherwise identify the segments of the input data as whether or not the segmented is associated with the surgical screw (e.g., a binary labeling of the segments where a “1” indicates the segment is associated with the surgical screw and a “0” indicates the segment is not associated with the surgical screw). In some embodiments, the input data 402 may comprise the segmented input data, the input data 402, or a combination thereof.

[0095] In some embodiments, the output data 404 of the analysis application 204 may comprise an updated image of the input data 402 with crosshairs or other visual indicators of the location of the surgical screw 408, the vertebra 412, etc. overlaid on the input data 402. As depicted in the output data 404 in Fig. 4, the output data 404 may comprise crosshairs aligned with the screw tip 416 of the surgical screw 408. In some embodiments, the output data 404 may depict the screw tip 416 of the surgical screw 408 in a plurality of different views. In other words, the analysis application 204 may automatically slice the input data 402 to oblique planes along the computed screw trajectory for visualization, such that a depiction of the screw tip 416 in multiple different views can be rendered to a display. In one example, a surgeon or other user may be able to select (e.g., via the user interface 110) one or more identified surgical screws, and the processor 104 may render one or more depictions (e.g., oblique plane views) of the selected surgical screws. Such actions by the analysis application 204 may provide automatic oblique slicing, such that a user of the system 100 need not scan through all slices of the input data 402 to locate the screw tip 416.

[0096] Fig. 5 depicts a method 500 that may be used, for example, to determine location information of at least one implanted device.

[0097] The method 500 (and/or one or more steps thereof) may be carried out or otherwise performed, for example, by at least one processor. The at least one processor may be the same as or similar to the processor(s) 104 of the computing device 102 described above. The at least one processor may be part of a robot (such as a robot 114) or part of a navigation system (such as a navigation system 118). A processor other than any processor described herein may also be used to execute the method 500. The at least one processor may perform the method 500 by executing elements stored in a memory such as the memory 106. The elements stored in memory and executed by the processor may cause the processor to execute one or more steps of a function as shown in method 500. One or more portions of a method 500 may be performed by the processor executing any of the contents of memory, such as training data 206, image processing 208, segmentation 212, data model 216, output data 220, pre-processing engine 224, post-processing engine 228, transformation 232, and/or registration 236.

[0098] The method 500 comprises training, using training data, a data model (step 504). The training data may be similar to or the same as the training data 206, and the data model may be similar to or the same as the data model 216. In some embodiments, the data model may be trained using simulated implantable devices (e.g., simulated surgical screws based on CAD models) on medical image datasets (e.g., cadaver datasets) to detect metal objects and/or non-metal objects in a medical image.

[0099] The method 500 also comprises providing an input associated with a surgical image to the data model (step 508). After the data model has been trained, one or more surgical images may be passed into the data model. In some embodiments, the surgical images may comprise CBCT image reconstruction models. In one embodiment, the input may comprise input data 402.

[0100] The method 500 also comprises receiving, from the data model, a segmented image that depicts at least one implanted device (step 512). The data model may output a segmented version of the surgical image that segments the surgical image into a plurality of segments. The segments may separate out at least one implanted device (e.g., a surgical screw, a surgical device, etc.) from other elements depicted in the surgical image (e.g., patient anatomy). In some embodiments, the segmented version of the surgical image may be rendered to a display, stored in the memory 106 and/or the database 130, combinations thereof, and/or the like.

[0101] The method 500 also comprises determining, based on the segmented image, location information associated with the at least one implanted device (step 516). The analysis application 204 (e.g., using the data model 216) may determine the location information associated with the at least one implanted device by passing the segmented image into a neural network that identifies location information of the at least one implanted device. For example, the location information may comprise information about a screw tip of a surgical screw, an implant trajectory associated with the surgical screw, a center of mass of the surgical screw, a location of a tulip of the surgical screw, combinations thereof, and/or the like. In some embodiments, the location information may be saved in the database 130.

[0102] The method 500 also comprises rendering, to a display, a depiction of at least one of the segmented image, the location information, and the at least one implanted device (step 520). One or more depictions of the segmented image, the location information, and/or at least one implanted device may be rendered to the display (e.g., user interface 110) to enable an operator of the system 100 (e.g., a surgeon) to view the depictions. In some embodiments, the depiction may comprise output data from the analysis application 204, such as the output data 404.

[0103] The present disclosure encompasses embodiments of the method 500 that comprise more or fewer steps than those described above, and/or one or more steps that are different than the steps described above.

[0104] Fig. 6 depicts a method 600 that may be used, for example, to track an implanted device and render depictions of the implanted device to a display.

[0105] The method 600 (and/or one or more steps thereof) may be carried out or otherwise performed, for example, by at least one processor. The at least one processor may be the same as or similar to the processor(s) 104 of the computing device 102 described above. The at least one processor may be part of a robot (such as a robot 114) or part of a navigation system (such as a navigation system 118). A processor other than any processor described herein may also be used to execute the method 600. The at least one processor may perform the method 600 by executing elements stored in a memory such as the memory 106. The elements stored in memory and executed by the processor may cause the processor to execute one or more steps of a function as shown in method 600. One or more portions of a method 600 may be performed by the processor executing any of the contents of memory, such as training data 206, image processing 208, segmentation 212, data model 216, output data 220, pre-processing engine 224, post-processing engine 228, transformation 232, and/or registration 236.

[0106] The method 600 comprises receiving a first image depicting a patient’s anatomy (step 604). The first image may be captured intraoperatively before one or more implantable devices are implanted in the patient’s anatomy. In one embodiment, the first image may be or comprise information associated with a CBCT volume scan of the patient captured by the imaging device 112. In some embodiments, the first image may be saved or stored in the database 130.

[0107] The method 600 also comprises registering the first image and an implantable device (step 608). The first image may be registered to the implantable device using, for example, transformation 232 and registration 236. For example, the navigation system 118 may track localizers and/or tracking devices (e.g., tracking device 148), including a tracking device associated with the implantable device. The processor 104 may use the tracking information provided by the navigation system 118 along with known locations of objects within the surgical environment (e.g., a known pose of the implantable device relative to the localizers and/or tracking devices, etc.) to map the location of the implantable device into a known coordinate system. The processor 104 may also use the transformation 232 and the registration 236 to map the location of patient anatomy in the first image to the known coordinate system (e.g., based on the tracking of localizers on or near the patient, based on the known or calculated pose of the patient relative to the imaging device 112, etc.). The processor 104 may then use registration 236 to correlate the first image (and components depicted therein such as patient anatomy) to the implantable device.

[0108] The method 600 also comprises tracking the implantable device as the device is implanted during a surgical procedure (step 612). Once the implantable device is registered with the first image, the surgical procedure may proceed with the implantable device being implanted into the patient anatomy. As the implantable device is implanted along an implant trajectory, the navigation system 118 may track the implantable device (or more specifically, the localizer or other tracker attached to or associated with the implantable device). Such tracking information may be saved as a log file and sent and stored in the memory 106 and/or the database 130.

[0109] The method 600 also comprises receiving a second image depicting the patient’s anatomy and the implanted device (step 616). After the implantable device has been implanted, a second intraoperative image may be captured that depicts the patient’s anatomy. In one embodiment, the second image may be or comprise information associated with a CBCT volume scan of the patient captured by the imaging device 112. In some embodiments, the second image may be saved or stored in the database 130.

[0110] The method 600 also comprises segmenting the second image into at least two segments, where at least one segment comprises a depiction of an implanted device (step 620). The second image may be segmented using the data model 216. The data model 216 may output a segmented version of the second image that segments the surgical image into a plurality of segments. The data model 216 may use a neural network or segmentation 212 (e.g., a computer vision algorithm) to segment the second image. The segments may separate out the implanted device (e.g., a surgical screw) from other elements depicted in the surgical image (e.g., patient anatomy). In some embodiments, the segmented version of the second image may be rendered to a display, stored in the memory 106 and/or the database 130, combinations thereof, and/or the like. [oni] The method 600 also comprises determining, based on navigation information associated with the implanted device, a location of the implanted device (step 624). The processor 104 may use transformation 232 and registration 236 to register the second segmented image with the first image. The processor 104 may then use the navigation information generated by the navigation system 118 when the implantable device was implanted to determine the location of the implanted device or a portion thereof. The location of the implanted device may comprise information about the location of an end of the implanted device, a center of mass of the implanted device, an implant trajectory associated with the implanted device, combinations thereof, and/or the like.

[0112] The method 600 also comprises rendering, to a display, a depiction of the location of the implanted device (step 628). The processor 104 may cause the depiction of the location of the implanted device to be rendered to the display (e.g., user interface 110). In some embodiments, the depiction may include one or more visual markers (e.g., crosshairs, highlights, etc.) that indicate the location of the implanted device. In some embodiments, such as when a second image comprises a 3D scan, the depiction may be a 2D slice of the 3D scan corresponding to the oblique plane along the implant trajectory of the implanted device such that the physician or surgeon can verify the implanted device.

[0113] In some cases, additional information may be rendered to the display. For instance, a depiction of the planned implant location (e.g., the implant location according to a surgical plan) may also be rendered to the display. The planned implant location may be rendered next to the implanted device location, which in turn may enable the surgeon or other user to determine whether the implanted device has been correctly implanted. In some examples, the planned implant location may be overlaid with the depiction of the location of the implanted device, such that the surgeon can visually determine any discrepancies between the planned location of the implanted device and the actual location of the implanted device.

[0114] The present disclosure encompasses embodiments of the method 600 that comprise more or fewer steps than those described above, and/or one or more steps that are different than the steps described above.

[0115] As noted above, the present disclosure encompasses methods with fewer than all of the steps identified in Figs. 5 and 6 (and the corresponding description of the methods 500 and 600), as well as methods that include additional steps beyond those identified in Figs. 5 and 6 (and the corresponding description of the methods 500 and 600). The present disclosure also encompasses methods that comprise one or more steps from one method described herein, and one or more steps from another method described herein. Any correlation described herein may be or comprise a registration or any other correlation.

[0116] The foregoing is not intended to limit the disclosure to the form or forms disclosed herein. In the foregoing Detailed Description, for example, various features of the disclosure are grouped together in one or more aspects, embodiments, and/or configurations for the purpose of streamlining the disclosure. The features of the aspects, embodiments, and/or configurations of the disclosure may be combined in alternate aspects, embodiments, and/or configurations other than those discussed above. This method of disclosure is not to be interpreted as reflecting an intention that the claims require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects he in less than all features of a single foregoing disclosed aspect, embodiment, and/or configuration. Thus, the following claims are hereby incorporated into this Detailed Description, with each claim standing on its own as a separate preferred embodiment of the disclosure.

[0117] Moreover, though the foregoing has included description of one or more aspects, embodiments, and/or configurations and certain variations and modifications, other variations, combinations, and modifications are within the scope of the disclosure, e.g., as may be within the skill and knowledge of those in the art, after understanding the present disclosure. It is intended to obtain rights which include alternative aspects, embodiments, and/or configurations to the extent permitted, including alternate, interchangeable and/or equivalent structures, functions, ranges or steps to those claimed, whether or not such alternate, interchangeable and/or equivalent structures, functions, ranges or steps are disclosed herein, and without intending to publicly dedicate any patentable subject matter.

[0118] A set of example statements are provided below:

[0119] Example 1: A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to: provide an input (402) associated with a surgical image to a data model (216); receive, from the data model (216) as a result of the data model (216) processing the input (402) associated with the surgical image, a segmented image that depicts at least one implanted device (408); and render, to a display, a depiction of the at least one implanted device (408) in the segmented image.

[0120] Example 2: The system of Example 1, wherein the data model (216) comprises at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network. [0121] Example 3: The system of any of Examples 1-2, wherein the input (402) comprises a reconstructed image volume associated with image data captured by an imaging device.

[0122] Example 4: The system of any of Examples 1-3, wherein the data model (216) is trained with training data (206) comprising information about a center of mass of a simulated implantable device.

[0123] Example 5: The system of any of Examples 1-4, wherein the data model (216) is trained with training data (206) comprising labeled training data.

[0124] Example 6: The system of any of Examples 1-5, wherein the at least one implanted device (408) comprises a surgical screw.

[0125] Example 7: The system of any of Examples 1-6, wherein the data, when processed by the processor (104), further enable the processor (104) to: determine, based on the segmented image, location information associated with the at least one implanted device (408).

[0126] Example 8: The system of Example 7, wherein the data, when processed by the processor (104), further enable the processor (104) to: render, to the display, the location information.

[0127] Example 9: The system of Example 7, wherein the location information comprises information about a trajectory along which the at least one implanted device (408) was implanted. [0128] Example 10: The system of any of Examples 1-9, wherein the data, when processed by the processor (104), further enable the processor (104) to: render, to the display, a depiction of a planned implant location of the at least one implanted device (408).

[0129] Example 11 : The system of Example 10, wherein the depiction of the planned implant location is rendered next to the depiction of the at least one implanted device (408) in the segmented image.

[0130] Example 12: A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enables the processor (104) to: provide an input (402) associated with a surgical image into a first data model (216); receive, from the first data model (216) as a result of the first data model (216) processing the input (402) associated with the surgical image, a segmented image that depicts at least one implanted device (408); provide the segmented image into a second data model (216); and receive, from the second data model (216) as a result of the second data model (216) processing the segmented image, an output (404) including information about a center of mass and a location of an end of the at least one implanted device (408) depicted in the segmented image. [0131] Example 13: The system of Example 12, wherein at least one of the first data model (216) and the second data model (216) comprise at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network.

[0132] Example 14: The system of any of Examples 12-13, wherein the surgical image comprises a reconstructed image volume.

[0133] Example 15: The system of any of Examples 12-14, wherein the second data model (216) is trained using training data (206) that comprises information about one or more parameters of a simulated implantable device.

[0134] Example 16: The system of Example 15, wherein the training data (206) comprise information about a center of mass and an end location of the simulated implantable device.

[0135] Example 17: The system of Example 15, wherein the training data (206) comprises labeled training data.

[0136] Example 18: The system of any of Examples 12-17, wherein the at least one implanted device (408) comprises a surgical screw.

[0137] Example 19: A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to: segment a reconstructed image volume into at least two segments, wherein at least one segment of the at least two segments comprises a depiction of an implanted device (408); determine, based on navigation information associated with the implanted device (408), a location of the implanted device (408); and render, to a display, a depiction of the location of the implanted device (408).

[0138] Example 20: The system of Example 19, wherein the data, when processed by the processor (104), further enable the processor (104) to: register the reconstructed image volume with a scan of a patient captured before the implanted device (408) is implanted.

[0139] Example 21: The system of any of Examples 19-20, wherein the depiction of the location of the implanted device (408) comprises information about a trajectory along which the implanted device (408) was implanted.

[0140] Example 22: The system of any of Examples 19-21, wherein the implanted device (408) comprises a surgical screw.

[0141] Example 23: The system of any of Examples 19-22, wherein the data, when processed by the processor (104), further enable the processor (104) to: render, to the display, a depiction of a planned implant location of the implanted device (408). [0142] Example 24: The system of Example 23, wherein the depiction of the planned implant location is rendered next to the depiction of the location of the implanted device (408).

Claims

CLAIMS What is claimed is:

1. A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to: provide an input (402) associated with a surgical image to a data model (216); receive, from the data model (216) as a result of the data model (216) processing the input (402) associated with the surgical image, a segmented image that depicts at least one implanted device (408); and render, to a display, a depiction of the at least one implanted device (408) in the segmented image.

2. The system of claim 1, wherein the data model (216) comprises at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network.

3. The system of any of claims 1-2, wherein the input (402) comprises a reconstructed image volume associated with image data captured by an imaging device.

4. The system of any of claims 1-3, wherein the data model (216) is trained with training data (206) comprising information about a center of mass of a simulated implantable device.

5. The system of any of claims 1-4, wherein the data model (216) is trained with training data (206) comprising labeled training data.

6. The system of any of claims 1-5, wherein the at least one implanted device (408) comprises a surgical screw.

7. The system of any of claims 1 -6, wherein the data, when processed by the processor (104), further enable the processor (104) to: determine, based on the segmented image, location information associated with the at least one implanted device (408).

8. The system of claim 7, wherein the data, when processed by the processor (104), further enable the processor (104) to: render, to the display, the location information.

9. The system of claim 7, wherein the location information comprises information about a trajectory along which the at least one implanted device (408) was implanted.

10. The system of any of claims 1-9, wherein the data, when processed by the processor (104), further enable the processor (104) to: render, to the display, a depiction of a planned implant location of the at least one implanted device (408).

11. The system of claim 10, wherein the depiction of the planned implant location is rendered next to the depiction of the at least one implanted device (408) in the segmented image.

12. A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enables the processor (104) to: provide an input (402) associated with a surgical image into a first data model (216); receive, from the first data model (216) as a result of the first data model (216) processing the input (402) associated with the surgical image, a segmented image that depicts at least one implanted device (408); provide the segmented image into a second data model (216); and receive, from the second data model (216) as a result of the second data model (216) processing the segmented image, an output (404) including information about a center of mass and a location of an end of the at least one implanted device (408) depicted in the segmented image.

13. The system of claim 12, wherein at least one of the first data model (216) and the second data model (216) comprise at least one of a convolutional neural network, a recurrent neural network, a deep reinforcement network, and a transformer network.

14. The system of any of claims 12-13, wherein the surgical image comprises a reconstructed image volume.

15. A system, comprising: a processor (104); and a memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to: segment a reconstructed image volume into at least two segments, wherein at least one segment of the at least two segments comprises a depiction of an implanted device (408); determine, based on navigation information associated with the implanted device (408), a location of the implanted device (408); and render, to a display, a depiction of the location of the implanted device (408).