Systems and methods for collision prevention using multi-dimensional mapped hardware

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: determine, based on image information generated by an imaging device, a pose of a medical component in a surgical environment relative to a surgical robot, where determining the pose includes: determining a coarse registration between the medical component and the surgical robot; and refining the coarse registration by performing template matching between a first mask that is generated by a data model and a second mask that is based on a depiction of the medical component in the image information; and navigate, based on the pose of the medical component, the surgical robot.

Description

A0012895W001SYSTEMS AND METHODS FOR COLLISION PREVENTION USING MULTI-DIMENSIONAL MAPPED HARDWARE

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No.63 / 759,932, filed 18 February 2025, the entire content of which is incorporated herein by reference.BACKGROUND

[0002] The present disclosure is generally directed to robotic navigation, and relates more particularly to registering surgical robots and surgical components to facilitate robotic navigation.

[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. Providing controllable linked articulating members allows a surgical robot to reach areas of a patient anatomy during various medical procedures.BRIEF SUMMARY

[0004] Example aspects of the present disclosure include:

[0005] 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: determine, based on image information generated by an imaging device, a pose of a medical component in a surgical environment relative to a surgical robot, wherein determining the pose comprises: determining a coarse registration between the medical component and the surgical robot; and refining the coarse registration by performing template matching between a first mask that is generated by a data model and a second mask that is based on a depiction of the medical component in the image information; and navigate, based on the pose of the medical component, the surgical robot.

[0006] A system according to at least one embodiment of the present disclosure comprises: a robotic arm; a processor; and a memory coupled with the processor and storing data thereon that, when processed by the processor, enable the processor to: determine, based on image information generated by an imaging device, a pose of a medical component in a surgical environment relative to the robotic arm, wherein determining the pose comprises: determining a coarse registration between the medical component and the robotic arm; and refining the coarse registration by performing template matching between a first mask that is generated by a data model and a second mask that isA0012895W001based on a depiction of the medical component in the image information; and navigate, based on the pose of the medical component, the robotic arm.

[0007] 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: train a data model to process an image as an input and output a mask of a medical component used in template matching to perform a fine registration between the medical component and a surgical robot.

[0008] Any aspect in combination with any one or more other aspects.

[0009] Any one or more of the features disclosed herein.

[0010] Any one or more of the features as substantially disclosed herein.

[0011] Any one or more of the features as substantially disclosed herein in combination with any one or more other features as substantially disclosed herein.

[0012] Any one of the aspects / features / embodiments in combination with any one or more other aspects / features / embodiments .

[0013] Use of any one or more of the aspects or features as disclosed herein.

[0014] 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.

[0015] 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.

[0016] 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).

[0017] 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.A0012895W001

[0018] 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.

[0019] 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

[0020] 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.

[0021] Fig. 1A is a block diagram of aspects of a system according to at least one embodiment of the present disclosure;

[0022] Fig. IB is a diagram of additional aspects of the system according to at least one embodiment of the present disclosure;

[0023] Fig. 2 is an illustration of a medical component depicted in a plurality of image planes according to at least one embodiment of the present disclosure;

[0024] Fig. 3 is a conceptual diagram of a neural network according to at least one embodiment of the present disclosure;

[0025] Fig. 4 is a flowchart according to at least one embodiment of the present disclosure; and

[0026] Fig. 5 is a flowchart according to at least one embodiment of the present disclosure.DETAILED DESCRIPTION

[0027] It should be understood that various aspects disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanyingA0012895W001drawings. 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.

[0028] 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.

[0029] When performing robotic guided actions or automated actions within the context of a robot-assisted surgery or surgical procedure, there is a need to avoid interference (e.g., collisions) between the robot and hardware that is placed on the patient. As an example, medical clamps may be placed in the surgical environment that could interfere with trajectory -based tasks and / or prevent the insertion of implants. The likelihood of such interference may be lower when the surgeon manually completes the surgical task and can identify the interference beforehand. But when the surgical task is semi-automatic (e.g., the surgeon is assisted by the robot) or automatic (e.g., the robot performs the surgical task), plastic or metal portions of the hardware may be inadvertently machined through (e.g., cut) by the robot. The likelihood of collision may increase in instances where the hardware is partially implanted into the patient at an angle or is otherwise obscured. The collision may additionally or alternatively disrupt the registration between the robot and patient anatomy, which may in turn expose the patient to additional harm.

[0030] According to at least one embodiment of the present disclosure, a three-dimensional (3D) imaging device such as a scanner may be provided to enable hardware in the surgical environmentA0012895W001(e.g., mounted on the patient) to be detected and identified to facilitate collision avoidance between the hardware and a surgical robot. The 3D imaging device may detect hardware in the surgical environment using computer vision techniques. Additionally or alternatively, fluoroscopic images may be captured and used to detect the hardware. In some cases, the detected hardware may be compared with Computer Aided Design (CAD) models or other models of the hardware (e.g., a library of known CAD models stored in memory and / or a database) to identify the hardware.

[0031] According to at least one embodiment of the present disclosure and after the hardware has been detected, information associated with the detected hardware (e.g., the pose the hardware, the CAD model(s) associated with the hardware, etc.) may be integrated with a surgical plan. In some cases, the detected hardware may comprise identified hardware (e.g., hardware with corresponding CAD models or other models) and / or unidentified hardware (e.g., hardware that does not have a corresponding CAD model or other model). The integration of the hardware information with the surgical plan may enable for planning of surgical trajectories that avoid collisions between the surgical robot (and / or components thereof such as surgical tools held by the surgical robot) and the hardware.

[0032] The integration may include registering the robotic arm to the hardware. The registration may include calibrating the imaging device to the robotic arm. After calibration, a kinematic chain between the imaging device and the robotic arm may be determined. The kinematic chain may take into account the forward kinematics and the range of motion of the robotic arm. The registration may also comprise a coarse registration (e.g., an iterative closest point algorithm) using, for example, depth data and point to point initialization. The registration may also comprise a fine registration that refines the coarse registration. The fine registration may include template matching between a projected produced mask and a mask generated by a neural network or other machine learning model. For example, the neural network may comprise a convolutional neural network trained on a plurality of images depicting hardware to take an image of the surgical environment including hardware as an input and output a mask that includes a depiction of the hardware. The mask output from the convolution neural network may be used in template matching to refine the registration between the hardware and the robotic arm.

[0033] Embodiments of the present disclosure provide technical solutions to one or more of the problems of (1) collisions between surgical robots and hardware mounted on or near a patient, (2) patient harm as a result of collisions between the surgical robots and the hardware (e.g., particulates entering the patient as a result of the surgical robot machining a portion of the hardware), and (3) medical component damage as a result of collisions between the surgical robots and the hardware.A0012895W001

[0034] Turning first to Fig. 1A, a block diagram of aspects of a system 100 according to at least one embodiment of the present disclosure is shown. The system 100 may be used to register a robotic arm to hardware; to control, pose, and / or otherwise manipulate (e.g., navigate) a surgical mount system, a surgical arm, and / or surgical tools attached thereto based on the registration of the robotic arm and the hardware; 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 with one or more robotic arms 116, a navigation system 118 with a depth camera 144, 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.

[0035] 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.

[0036] The processor 104 of the computing device 102 may be any processor described herein or any similar processor. For example, the processor 104 may be or comprise 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 All, 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. 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.

[0037] The memory 106 may be coupled with the processor 104 and may be or comprise RAM, DRAM, SDRAM, other solid-state memory, any memory described herein, or any other tangible,A0012895W001non-transitory memory for storing computer-readable data and / or 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). The memory 106 may store, for example, instructions, algorithms, and / or machine learning models that support one or more functions of the imaging device 112, the robot 114, the navigation system 118, the depth camera 144, combinations thereof, and / or the like. The memory 106 may store information or data useful for completing, for example, any step of the methods 400 and / or 500 described herein, or of any other methods. 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.

[0038] 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). Such content, if provided as an instruction, may, in some embodiments, be organized into one or more applications, modules, packages, layers, or engines. Alternatively or additionally, the memory 106 may store other types of content or data (e.g., machine learning models, artificial neural networks, deep neural networks, etc.) that can be processed by the processor 104 to carry out the various methods and features described herein. Thus, 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 machine learning 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, the cloud 134, and / or the depth camera 144.

[0039] The memory 106 is depicted to include medical component information 120, image information 122, one or more registration algorithms 124, training data 128, one or more masks 136, and a data model 140. However, additional or alternative contents of the memory 106 may be present or omitted.

[0040] The medical component information 120 may comprise data related to medical components (e.g., a medical component 160) used in a surgery or surgical procedure. The medical component information 120 may comprise information related to the physical characteristics (e.g., dimensions, material composition, contours, etc.) of medical components used in the surgery or surgicalA0012895W001procedure. In some cases, the medical component information 120 may be additionally or alternatively stored in the database 130.

[0041] The image information 122 may be or comprise images and / or image data of patient anatomy (e.g., anatomical features such as bones, soft tissues, etc.) and / or of hardware components proximate the patient anatomy (e.g., medical component 160). “Image data” as used herein refers to the data generated or captured by the imaging device 112 or other imaging device (e.g., the depth camera 144), including in a machine- readable form, a graphical / visual form, and in any other form. 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 one example, the image information 122 comprises a plurality of images depicting a medical component (e.g., medical component 160) proximate an anatomical element (e.g., a vertebra) from a variety of different image planes (e.g., angles).

[0042] The registration algorithm 124 may enable registration between two or more images in different coordinate spaces. For instance, the registration algorithm 124 may determine a mapping to transform coordinates associated with features depicted in an image (e.g., hardware) from the image coordinate system to a coordinate system associated with, for example, the robotic arm, the patient, etc. In some examples, the registration algorithm 124 may perform a coarse registration between hardware and the robotic arm and then refine the coarse registration using one or more masks output from the data model 140.

[0043] The training data 128 may comprise data useful for training one or more data models discussed herein such as the data model 140. The training data 128 may comprise, for example, multi-dimensional images of medical component(s) in a surgical environment that can be used to train one or more data models. In one example, the image data of the surgical environment may comprise depictions of patient spines or other anatomical elements and hardware (e.g., the medical component 160) proximate the anatomical elements. In some cases, the training data 128 may be additionally or alternatively stored in the database 130.

[0044] The masks 136 may be or comprise masks that filter data in images or image data to which the masks 136 are applied. For example, the masks 136 may comprise a segmentation mask that segments a hardware component when the masks 136 are applied to an image depicting the hardware component in a surgical context (e.g., the hardware component positioned next to a vertebra). In some cases, the masks 136 may be additionally or alternatively stored in the database 130.A0012895W001

[0045] The data model 140 may be or comprise a neural network (e.g., a convolution neural network, a deep neural network, a recurrent neural network, combinations thereof, etc.) that is trained to receive an image including a depiction of hardware component(s) as input and to output a mask associated with the image that segments the hardware component(s) from the image data. As an example, the data model 140 may receive an image of the medical component 160 within a surgical environment as an input and output a mask (e.g., mask 136) that segments the medical component 160 from the image data.

[0046] 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 and / or components thereof such as the depth camera 144, 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 and / or components thereof such as the depth camera 144, 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.

[0047] 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 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.A0012895W001

[0048] 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.

[0049] 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 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 0-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. The imaging device 112 may be contained entirely within a single housing, or may comprise a transmitter / emitter and a receiver / detector that are in separate housings or are otherwise physically separated.

[0050] In some embodiments, the imaging device 112 may comprise more than one imaging device 112. For example, a first imaging device may provide first image data and / or a first image, and a second imaging device may provide second image data and / or a second image. In still other embodiments, the same imaging device may be used to provide both the first image data and the second image data, and / or any other image data described herein. The imaging device 112 may be operable to generate a stream of image data. For example, the imaging device 112 may be configured to operate with an open shutter, or with a shutter that continuously alternates between open and shut so as to capture successive images. 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.A0012895W001

[0051] 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 the imaging device 112 at one or more precise position(s) and orientation(s), and / or to return the imaging device 112 to the same position(s) and orientation(s) at a later point in time. The robot 114 may additionally or alternatively be configured to manipulate a surgical tool 168 (whether based on guidance from the navigation system 118 or not) 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. In some embodiments, one or more of the robotic arms 116 may be used to hold and / or maneuver the imaging device 112. In embodiments where the imaging device 112 comprises two or more physically separate components (e.g., a transmitter and receiver), one robotic arm 116 may hold one such component, and another robotic arm 116 may hold another such component. Each robotic arm 116 may be positionable independently of the other robotic arm. The robotic arms 116 may be controlled in a single, shared coordinate space, or in separate coordinate spaces.

[0052] 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, an imaging device 112, 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.

[0053] The robotic arm(s) 116 may comprise one or more sensors 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 176A-176N) 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.

[0054] 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 navigationA0012895W001system or any successor thereof. The navigation system 118 may include one or more cameras such as the depth camera 144 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. 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, and / or one or more surgical tools (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. In some embodiments, the system 100 can operate without the use 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, the pose of one or more medical components 160 (e.g., by rendering a map or other visual depiction of the medical components 160 to a display), 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.

[0055] 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; Computer Aided Design (CAD) models or other models of one or more medical components (e.g., surgical hardware) used in the surgery or surgical procedure; maps of surgical hardware based on one or more registrations; 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 healthA0012895W001information system (HIS), and / or another system for collecting, storing, managing, and / or transmitting electronic medical records including image data.

[0056] 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.

[0057] With reference to Fig. IB, additional aspects of the system 100 in accordance with at least one embodiment of the present disclosure are shown. During a surgery or surgical procedure, a patient 152 may be positioned on a table 148 and the robot 114 may be used to perform one or more surgical tasks.

[0058] In some cases, one or more medical components 160 (e.g., surgical clamps, surgical retractors, etc.) may be positioned proximate anatomy (e.g., vertebra 156A, vertebra 156B, etc.) of the patient 152. The positioning of the medical components 160 may interfere with the surgical trajectories planned by the robotic arm 116. For instance, a medical component 160 may be mounted to both the robotic arm 116 and the patient 152 such that the medical component 160 is positioned along a trajectory 172. The trajectory 172 may correspond to a path along which a surgical tool 168 or implant is navigated, such that there is a possibility of collision between the medical component 160 and the surgical tool 168 if the surgical tool 168 is navigated along the trajectory 172. In another example, the surgical tool 168 may be a passive guide and the trajectory 172 may correspond to a path navigated by a different surgical tool (e.g., a surgical drill manually operated by the surgeon or navigated by a second, different robotic arm). In this example, the medical component 160 may obstruct the path of the surgical tool such that, if the surgical tool were navigated along the path, the surgical tool would machine the medical component 160 (e.g., cut through plastic, metal, etc. of the medical component 160).

[0059] To account for and reduce the likelihood of collisions between the hardware component and the robotic arm 116 and / or components thereof (e.g., the surgical tool 168 connected to an end effector 164 of the robotic arm 116), embodiments of the present disclosure may detect the medical component 160 in, for example, image data captured by the depth camera 144 and navigate the robotic arm 116 and / or components thereof based on the detected medical component 160. In one example, the medical component 160 may be passed into the data model 140 to generate a mask that identifies the medical component 160 in the image data. Such mask may then be used in template matching for the purposes of registering the medical component 160 to the robotic arm 116 and / orA0012895W001components thereof. The registration may then be used to navigate the robotic arm 116 to avoid or reduce the likelihood of collisions between the robotic arm 116 and the medical component 160.

[0060] The system 100 or similar systems may be used, for example, to carry out one or more aspects of any of the methods 400 and / or 500 described herein. The system 100 or similar systems may also be used for other purposes.

[0061] With reference to Fig. 2, an illustration of a medical component 204 in a plurality of image planes 208A-208N in accordance with embodiments of the present disclosure is shown. The medical component 204 may be similar to or the same as the medical component 160 in some examples. The plurality of image planes 208A-208N is depicted to comprise a first image plane 208A, a second image plane 208B, a third image plane 208C, a fourth image plane 208D, and a fifth image plane 208E. However, an additional or alternative number of image planes may be present. The plurality of plane views 208A-208N of the medical component 204 in a surgical environment may correspond to image data captured by a 3D scanner, depth camera, or other imaging device (e.g., the depth camera 144). Each image plane of the plurality of image planes 208A-208N may depict the medical component 204 at a different angle or view, which may enable image processing of the plurality of image planes 208A-208N to identify the medical component 204 (e.g., based on masks output by one or more neural networks such as the data model 140).

[0062] In some examples, each of the depictions of the medical component 204 may be used as a mask in template matching to register the medical component 204 and the robotic arm 116. For example, each image plane view of the plurality of image planes 208A-208N may be processed to generate a mask that segments the medical component 204 from the image data. Masks may then be matched with a mask generated by the data model 140 to register the medical component 204 to the robotic arm 116 to help facilitate collision avoidance between the medical component 204 and the robotic arm 116.

[0063] In some examples, the medical component 204 may be or comprise a known or identifiable medical component. In other words, information associated with the medical component 204 such as a 3D CAD model may be stored in the medical component information 120 and / or the database 130 or may otherwise be accessible by the processor 104. Additionally or alternatively, the medical component 204 may initially be unknown, such that information about the medical component 204 is not initially available to the processor 104 (e.g., a hardware component for which the memory 106 or the database 130 does not initially store information about the hardware component).

[0064] In cases where the medical component 204 is not initially known, the system 100 may be capable of capturing and adding information associated with the medical component 204 to theA0012895W001memory 106 and / or the database 130. In one example, the 3D scanner, the depth camera, or other imaging device may be used to capture images of the medical component 204. The captured images of the medical component 204 may then be used by the processor 104 to generate a multidimensional volume reconstruction of the medical component 204. The processor 104 may use filtered back projection (FBP) techniques, iterative reconstruction techniques, algebraic reconstruction technique (ART) techniques, etc. to generate the multidimensional volume reconstruction. The volume reconstruction may be used as a representation of a 3D CAD model or similar model in implementing the techniques discussed herein.

[0065] In some examples when the medical component 204 is not initially known, the captured images of the medical component 204 may be used to determine the identity of the medical component 204. For example, the captured images may depict a type of clamp that is unknown to the system 100. To determine the identity of the medical component, the processor 104 may compare the images of the medical component 204 to a library of 3D CAD models or other models to identify the component. In some cases, the library of models may be stored in the memory 106, the database 130, or any other storage device. In comparing the images of the medical component 204 to the library, the processor 104 compare the shape of the medical component 204 (e.g., the outline of the medical component 204) and / or the shape of specific features (e.g., metallic pins, a clamp tooth or teeth, fasteners, combinations thereof, etc.) on the medical component 204 to corresponding shapes and / or features of the 3D models stored in the library. For example, the unknown clamp may comprise a plurality of fasteners, and the processor 104 may identify the fasteners (using, for example, edge detection algorithms or other known image segmentation techniques) and compare the identified fasteners to corresponding fasteners of the models in the library. When the processor 104 identifies a match (e.g., the difference between the shape of the fasteners of the medical component 204 and the shape of the fasteners in a model falls below a predetermined error threshold), the processor 104 may identify the medical component 204 as corresponding to the medical component of the matched 3D model.

[0066] In some embodiments, the medical component 204 may comprise internal degrees of freedom, such as when a retractor can open at different lengths. When identifying a medical component with internal degrees of freedom, the processor 104 may use the shape of specific features (e.g., pins, teeth, fasteners, etc.) to identify the medical component. Such an approach may enable the processor 104 to identify the medical component 204 independent of the internal degrees of freedom of the medical component 204. Additionally or alternatively, the processor 104 may compare the images of the medical component 204 with multiple variations of each 3D model thatA0012895W001have been modified to account for the internal degrees of freedom. In the retractor example above, the retractor may be configured to open to three different lengths. The processor 104 may then access 3D models of medical components and, for each 3D model, compare the images of the retractor to the 3D model as the 3D model is modulated over the internal degrees of freedom (e.g., the 3D model that ultimately matches the retractor may be modified to appear opened to each of the three different lengths, with the images of the retractor compared to the modified 3D model at each length). In other words, the processor 104 may take into account the internal degrees of freedom of the medical component when determining the identity of the medical component via comparison to a library of 3D models.

[0067] With reference to Fig. 3, a conceptual diagram of a neural network 304 in accordance with embodiments of the present disclosure is shown. The neural network 304 may in some cases be similar to or the same as the data model 140.

[0068] The neural network 304 may comprise a plurality of layers (e.g., convolution layers, pooling layers, upsampling layers, dropout layers, etc.) and may be trained to receive an input 308 and generate an output 312. The input 308 may be or comprise image data captured by the depth camera 144 such as an image of a medical component (e.g., medical component 160, medical component 204, etc.) in a surgical environment (e.g., the medical component is attached one or more anatomical elements of a patient and / or to the robotic arm 116). The output 312 may comprise a mask 316 that identifies a medical component 320 in the input 308. In one example, the medical component 320 may be similar to or the same as the medical component 160, the medical component 204, etc. In other words, the input 308 may correspond to an image of the medical component 320 in a surgical environment (e.g., attached to the robotic arm 116 and the vertebra 156A of the patient 152), and the neural network 304 may process the image of the medical component 320 to generate the output 312 which may correspond to the mask 316 that identifies the medical component 320. For example, the mask 316 may depict the medical component 320 with a first pixel intensity and may depict the remainder of the image data in a second, different pixel intensity when rendered to a display to visually indicate the location of the medical component 320 in the surgical environment. In some examples, the output 312 of the neural network 304 may be used in template matching for the purposes of registering the medical component 320 to the robotic arm 116 and / or components thereof. In one example, the template matching may correspond to a refinement of a coarse registration between the medical component 320 and the robotic arm 116.

[0069] The training data used to train the neural network 304 may be or comprise image data that depicts medical component in a surgical environment such as historical data from previous surgeriesA0012895W001or surgical procedures and / or information related to one or more hardware components (e.g., medical component information 120 such as CAD models of the one or more hardware components). As part of the training of the neural network 304, the training data may pass through the neural network 304, and the output of the neural network 304 may be labeled for error (e.g., a user such as a physician labels the medical component, a processor compares the output mask to a ground truth mask and generates an indicator of the error, etc.). The error may then backpropagated through the neural network 304 to iteratively train the neural network 304 to generate the output 312.

[0070] In some cases, the input 308 may comprise image data for more than one medical component (e.g., more than one type of surgical clamp, more than one type of surgical retractor, etc.). In such cases, the neural network 304 may be trained to identify a particular medical component in the image data. For instance, the neural network 304 may be trained to identify only medical components within a threshold distance from an anatomical element (e.g., vertebra 156A), such as when medical components outside the threshold distance from the anatomical element pose a smaller likelihood of collision between the medical components outside the threshold distance and the robotic arm 116 and / or components thereof as determined, for example, by system safety tolerances.

[0071] Additionally or alternatively, the neural network 304 may be trained to identify some or all of the medical components in the image data. In such examples, the output 312 of the neural network 304 may comprise one or more masks that identify the medical components in the image data. In one example, the output 312 may comprise a single mask that identifies all medical components in the image data.

[0072] Fig. 4 depicts a method 400 that may be used, for example, to register and navigate a surgical robot to hardware in a surgical environment.

[0073] The method 400 (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 400. The at least one processor may perform the method 400 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 400. One or more portions of a method 400 may be performed by the processor executing any of the contents of memory, such as the medical component information 120, the imageA0012895W001information 122, the registration algorithm 124, the training data 128, the one or more masks 136, and / or the data model 140.

[0074] The method 400 comprises receiving image information of a medical component in a surgical environment (step 404). The image information may correspond to one or more images captured by a 3D scanner, depth camera (e.g., the depth camera 144), and / or other imaging device (e.g., the imaging device 112). The medical component (e.g., medical component 160, medical component 204, medical component 320, etc.) may correspond to hardware positioned within the surgical environment, such as one or more medical clamps, one or more surgical retractors, etc. In some cases, the medical component may comprise hardware mounted to both the patient and the surgical robot that may interfere with the surgical robot’s performance of one or more surgical tasks (e.g., the hardware may be positioned along a surgical trajectory to be navigated by the surgical robot). In some cases, the image information may comprise information about some or all medical components (e.g., some or all of the hardware) within the surgical environment and within view of the imaging device(s) that capture the image information.

[0075] The method 400 also comprises determining, based on the image information, a pose of the medical component relative to a surgical robot using a coarse registration and a fine registration (step 408). The pose of the medical component relative to the surgical robot may be determined and used to register the medical component and the surgical robot.

[0076] Determining the pose of the medical component relative to the surgical robot may begin by calibrating the imaging device(s) that captured the image information to the surgical robot. After calibration, a kinematic chain between the imaging device and the surgical robot may be determined. Information useful for establishing the kinematic chain (e.g., dimensions and contour information about the imaging device and the surgical robot, degrees of freedom of the surgical robot, etc.) may be stored in the memory 106 and / or the database 130 and accessed by the processor 104 to determine the kinematic chain. The kinematic chain may take into account the one or more physical components of the imaging device (e.g., the location of the focal point of the imaging device) and the surgical robot (e.g., the linkages of a robotic arm of the surgical robot) to determine a transform that maps coordinates in a coordinate system associated with the imaging device into a coordinate system associated with the surgical robot (and vice versa). In some cases, the transform may comprise kinematic restraints (e.g., based on the possible mechanical movements and / or mechanical constraints on the imaging device and / or the surgical robot) that can be used during registration. In some examples, information associated with the kinematic chain (e.g., coordinates, kinematic restraints, etc.) may be stored in the memory 106 and / or the database 130.A0012895W001

[0077] The step 408 may additionally or alternatively comprise performing a coarse registration between the imaging device and the surgical robot. The coarse registration may use one or more algorithms (e.g., registration algorithm 124) to generate a registration between the imaging device and the surgical robot. In one example, the registration algorithm 124 implements an iterative closest point algorithm or other known algorithm. The iterative closest point algorithm is an algorithm that minimizes the difference between data in two different point clouds (e.g., point cloud data associated with the medical component and point cloud data associated with the surgical robot). The iterative closest point algorithm may in some cases receive as input one or more kinematic restraints from the kinematic chain transforms to constrain the solution(s) of the iterative closest point algorithm. The iterative closest point algorithm may output a coarse registration that may comprise one or more transforms that map coordinates associated with the medical device into a coordinate system associate with the surgical robot (and vice versa).

[0078] After the coarse registration is performed, the coarse registration may be refined using, for example, template matching. The template matching may comprise matching a mask associated with the medical component and generated by a data model (e.g., data model 140, neural network 304, etc.) with one or more other masks. The one or more other masks may be based on the depiction of the medical component in the image information generated by the imaging device. The one or more other masks may be or comprise, for example, masks of the medical component as depicted in one or more image planes (e.g., plurality of image planes 208A-208N). In other words, for each image plane, a mask associated with the depiction of the medical component in the image plane is matched with a mask of the medical component output by the data model based on an input of the image plan. The template matching of the masks for each image plane may then be used to perform a multidimensional reconstruction of the medical component (e.g., using RANSAC or other iterative methods) in a known coordinate system. The reconstructions may then be used to update or refine the coarse registration between the medical component and the surgical robot.

[0079] In some embodiments, the step 408 may be repeated for one or more other medical components depicted in the image data. In cases where the imaging device generates image data that includes a plurality of medical components, the pose of one or more of the plurality of medical components relative to the surgical robot may be determined.

[0080] The method 400 also comprises navigating, based on the pose of the medical component, the surgical robot (step 412). Once the pose of the medical component is known, the surgical robot may be navigated to avoid collision with the medical component. For example, the step 412 may comprise updating one or more trajectories of the surgical robot to account for the pose of theA0012895W001medical component (e.g., trajectories that would result in a collision between the surgical robot and the medical component are changed, trajectories where the surgical robot moves within a threshold distance of the medical component are changed, etc.). In some examples, information related to the pose of the medical component is rendered to a display (e.g., user interface 110) to enable a user (e.g., a physician) to review the current pose of the medical component. In one example, a map depicting the locations of one or more of the medical components may be rendered to the display to enable the user (e.g., a surgeon) to adjust a surgical plan. Additionally or alternatively, the processor 104 may automatically integrate the determined pose of the medical component(s) into the surgical plan (e.g., by updating the one or more trajectories).

[0081] In some examples, the steps 404 and 408 may be repeated in real time or near real time during the course of a portion or the entirety of the surgery or surgical procedure to, for example, account for any changes in pose of the medical component(s) in the surgical environment. For example, the imaging device may provide a live feed of the patient and any medical hardware proximate the patient. If medical hardware moves, the imaging device may capture such image information and, through the process of steps 404 and 408, a new pose of the medical hardware relative to the surgical robot may be determined and one or more trajectories of the surgical robot may be updated accordingly.

[0082] The present disclosure encompasses embodiments of the method 400 that comprise more or fewer steps than those described above, and / or one or more steps that are different than the steps described above.

[0083] Fig. 5 depicts a method 500 that may be used, for example, train and use a data model to generate a mask used in template matching to register a medical component to a robotic arm.

[0084] 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 the medical component information 120, the imageA0012895W001information 122, the registration algorithm 124, the training data 128, the one or more masks 136, and / or the data model 140.

[0085] The method 500 comprises training a data model to process an image as an input and output a mask of a medical component (step 504). The data model (e.g., data model 140, neural network 304, etc.) may be trained using training data (e.g., training data 128) that include multidimensional images that depict medical component(s) (e.g., medical component 160, medical component 204, medical component 320, etc.) in a surgical environment. Additionally or alternatively, the training data may comprise medical component information (e.g., medical component information 120) such as CAD models of the medical component(s). In some examples, the data model may be trained to generate a mask of multiple different medical components (e.g., a mask of a surgical clamp, a mask of a surgical retractor, etc.). In other examples, the data model may be trained to generate a mask of a single medical component, and multiple different trained data models may be available depending on the type of medical component(s) used in the surgery or surgical procedure. The input (e.g., input 308) to the data model may comprise an image (e.g., an image generated by the imaging device 112, by the depth camera 144, etc.) of a patient and medical components attached to the patient.

[0086] The method 500 also comprises calibrating an imaging device to a robotic arm (step 508). The imaging device may be in some cases similar to or the same as the imaging device 112 and / or the depth camera 144. The robotic arm may be similar to or the same as the robotic arm 116.

[0087] The method 500 also comprises determining a kinematic chain between the imaging device and the robotic arm (step 512). Information useful for establishing the kinematic chain (e.g., dimensions and contour information about the imaging device and the robotic arm, degrees of freedom of the robotic arm, etc.) may be stored in the memory 106 and / or the database 130 and accessed by the processor 104 to determine the kinematic chain between the imaging device and the robotic arm. The kinematic chain may take into account the one or more physical components of the imaging device (e.g., the location of the focal point of the imaging device) and the robotic arm (e.g., the linkages that form the robotic arm, the base of the robotic arm, etc.) to determine a transform that maps coordinates in a coordinate system associated with the imaging device into a coordinate system associated with the robotic arm (and vice versa). In some cases, the transform may comprise kinematic restraints (e.g., based on the possible mechanical movements and / or mechanical constraints on the imaging device and / or the robotic arm) that can be used during registration. In some examples, information associated with the kinematic chain (e.g., coordinates, kinematic restraints, etc.) may be stored in the memory 106 and / or the database 130.A0012895W001

[0088] The method 500 also comprises determining a coarse registration between the medical component and the robotic arm (step 516). The coarse registration may use one or more algorithms (e.g., registration algorithm 124) to generate a registration between the imaging device and the robotic arm. In one example, the registration algorithm 124 implements an iterative closest point algorithm or other known algorithm. The iterative closest point algorithm is an algorithm that minimizes the difference between data in two different point clouds (e.g., point cloud data associated with the medical component and point cloud data associated with the robotic arm). The iterative closest point algorithm may in some cases receive as input one or more kinematic restraints from the kinematic chain transforms that constrain the solution(s) of the iterative closest point algorithm. The iterative closest point algorithm may output a coarse registration that may comprise one or more transforms that map coordinates associated with the medical device into a coordinate system associate with the robotic arm (and vice versa).

[0089] The method 500 also comprises refining the coarse registration by performing template matching between the mask that is generated by the data model and a second mask that is based on a depiction of the medical component in the image information (step 520). The template matching may comprise matching a mask associated with the medical component and generated by a data model (e.g., data model 140, neural network 304, etc.) with one or more masks associated with a second mask based on the depiction of the medical component in the image information generated by the imaging device. The second mask may be or comprise, for example, masks of the medical component as depicted in one or more image planes (e.g., plurality of image planes 208A-208N). In other words, for each image plane, a mask associated with the depiction of the medical component in the image plane is matched with a mask of the medical component generated by the data model that is trained to detect the medical component in the image plane. The template matching of the masks for each image plane may then be used to perform a multi-dimensional reconstruction of the medical component (e.g., using RANSAC or other iterative methods) in a known coordinate system. The reconstructions may then be used to update the coarse registration between the medical component and the robotic arm.

[0090] In some embodiments, the steps 516 and 520 may be repeated for one or more other medical components depicted in the image data. In other words, in cases where the imaging device generates image data that includes a plurality of medical components, each medical component may be registered to the robotic arm.A0012895W001

[0091] 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.

[0092] As noted above, the present disclosure encompasses methods with fewer than all of the steps identified in Figs. 4 and 5 (and the corresponding description of the methods 400 and 500), as well as methods that include additional steps beyond those identified in Figs. 4 and 5 (and the corresponding description of the methods 400 and 500). 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.

[0093] 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.

[0094] 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.

[0095] The techniques of this disclosure may also be described in the following examples.

[0096] 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 theA0012895W001processor (104) to: determine, based on image information (122) generated by an imaging device (112), a pose of a medical component (160, 204) in a surgical environment relative to a surgical robot (114), wherein determining the pose comprises: determining a coarse registration between the medical component (160, 204) and the surgical robot (114); and refining the coarse registration by performing template matching between a first mask that is generated by a data model (140) and a second mask that is based on a depiction of the medical component (160, 204) in the image information (122); and navigate, based on the pose of the medical component (160, 204), the surgical robot (114).

[0097] Example 2: The system according to example 1, wherein the coarse registration is performed using an iterative closest point algorithm.

[0098] Example 3: The system according to example 2, wherein the iterative closest point algorithm uses at least one kinematic constraint.

[0099] Example 4: The system according to any of example 1-3, wherein the data model (140) comprises a convolutional neural network, a deep neural network, a recurrent neural network, or a combination thereof.

[0100] Example 5: The system according to any of examples 1-4, wherein the data model (140) is trained on multi-dimensional images of medical components (160, 204).

[0101] Example 6: The system according to any of examples 1-5, wherein the medical component (160, 204) comprises hardware attached to a patient (152).

[0102] Example 7: The system according to any of examples 1-6, wherein the imaging device (112) comprises a depth camera (144).

[0103] Example 8: The system according to any of examples 1-7, wherein determining the pose further comprises: determining a kinematic chain between the imaging device (112) and the surgical robot (114).

[0104] Example 9: A system, comprising: a robotic arm (116); 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: determine, based on image information (122) generated by an imaging device (112), a pose of a medical component (160, 204) in a surgical environment relative to the robotic arm (116), wherein determining the pose comprises: determining a coarse registration between the medical component (160, 204) and the robotic arm (116); and refining the coarse registration by performing template matching between a first mask that is generated by a data model (140) and a second mask that is based on a depiction of the medicalA0012895W001component (160, 204) in the image information (122); and navigate, based on the pose of the medical component (160, 204), the robotic arm (116).

[0105] Example 10: The system according to example 9, wherein the coarse registration is performed using an iterative closest point algorithm.

[0106] Example 11 : The system according to example 10, wherein the iterative closest point algorithm uses at least one kinematic constraint.

[0107] Example 12: The system according to any of examples 9-11, wherein the data model (140) comprises a convolutional neural network, a deep neural network, a recurrent neural network, or a combination thereof.

[0108] Example 13: The system according to any of examples 9-12, wherein the data model (140) is trained on multi-dimensional images of medical components (160, 204).

[0109] Example 14: The system according to any of examples 9-13, wherein the medical component (160, 204) comprises hardware attached to a patient (152).

[0110] Example 15: The system according to any of examples 9-14, wherein the imaging device (112) comprises a depth camera (144).

[0111] Example 16: The system according to any of examples 9-15, wherein determining the pose further comprises: determining a kinematic chain between the imaging device (112) and the robotic arm (116).

[0112] Example 17: 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: train a data model (140) to process an image as an input and output a mask of a medical component (160, 204) used in template matching to perform a fine registration between the medical component (160, 204) and a surgical robot (114).

[0113] Example 18: The system according to example 17, wherein the data model (140) comprises a convolutional neural network, a deep neural network, a recurrent neural network, or a combination thereof.

[0114] Example 19: The system according to example 18, wherein the data model (140) is trained on multi-dimensional images of medical components (160, 204).

[0115] Example 20: The system according to any of examples 17-19, wherein the fine registration is a refined registration of a coarse registration between the medical component (160, 204) and the surgical robot (114).A0012895W001

[0116] Example 21: The system according to any of examples 1-8, wherein the memory (106) stores additional data that, when processed by the processor (104), further enable the processor (104) to: determine an identity of the medical component (160, 204).

[0117] Example 22: The system according to Example 21, wherein determining the identity of the medical component (160, 204) comprises comparing at least one of a shape of the medical component (160, 204) and a feature of the medical component (160, 204) to a library of known medical components (160, 204).

[0118] Example 23: The system according to example 22, wherein the feature of the medical component (160, 204) comprises at least one of a pin, a clamp tooth, and a fastener.

Claims

A0012895W001CLAIMSWhat is claimed is:

1. A system, comprising:a processor (104); anda memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to:determine, based on image information (122) generated by an imaging device (112), a pose of a medical component (160, 204) in a surgical environment relative to a surgical robot (114), wherein determining the pose comprises:determining a coarse registration between the medical component (160, 204) and the surgical robot (114); andrefining the coarse registration by performing template matching between a first mask that is generated by a data model (140) and a second mask that is based on a depiction of the medical component (160, 204) in the image information (122); andnavigate, based on the pose of the medical component (160, 204), the surgical robot (H4).

2. The system according to claim 1, wherein the coarse registration is performed using an iterative closest point algorithm.

3. The system according to claim 2, wherein the iterative closest point algorithm uses at least one kinematic constraint.

4. The system according to any of claims 1-3, wherein the data model (140) comprises a convolutional neural network, a deep neural network, a recurrent neural network, or a combination thereof.

5. The system according to any of claims 1-4, wherein the data model (140) is trained on multi-dimensional images of medical components (160, 204).

6. The system according to any of claims 1-5, wherein the medical component (160, 204) comprises hardware attached to a patient (152).A0012895W0017. The system according to any of claims 1-6, wherein the imaging device (112) comprises a depth camera (144).

8. The system according to any of claims 1-7, wherein determining the pose further comprises:determining a kinematic chain between the imaging device (112) and the surgical robot (H4).

9. The system according to any of claims 1-8, wherein the memory (106) stores additional data that, when processed by the processor (104), further enable the processor (104) to:determine an identity of the medical component (160, 204).

10. The system according to claim 9, wherein determining the identity of the medical component (160, 204) comprises comparing at least one of a shape of the medical component (160, 204) and a feature of the medical component (160, 204) to a library of known medical components (160, 204).

11. The system according to claim 10, wherein the feature of the medical component (160, 204) comprises at least one of a pin, a clamp tooth, and a fastener.

12. A system, comprising:a robotic arm (116);a processor (104); anda memory (106) coupled with the processor (104) and storing data thereon that, when processed by the processor (104), enable the processor (104) to:determine, based on image information (122) generated by an imaging device (112), a pose of a medical component (160, 204) in a surgical environment relative to the robotic arm (116), wherein determining the pose comprises:determining a coarse registration between the medical component (160, 204) and the robotic arm (116); andA0012895W001refining the coarse registration by performing template matching between a first mask that is generated by a data model (140) and a second mask that is based on a depiction of the medical component (160, 204) in the image information (122); andnavigate, based on the pose of the medical component (160, 204), the robotic arm (H6).

13. The system according to claim 12, wherein the coarse registration is performed using an iterative closest point algorithm.

14. The system according to claim 13, wherein the iterative closest point algorithm uses at least one kinematic constraint.

15. The system according to any of claims 12-14, wherein the data model (140) comprises a convolutional neural network, a deep neural network, a recurrent neural network, or a combination thereof.

Images