Spine deformation induced by rigid bodies: synthetic long scan imaging for artificial intelligence (AI) methods

Abstract

A system may generate a transformation of a multidimensional bone model. The multidimensional bone model corresponds to one or more anatomical elements included in a captured image of a subject, and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model. The system may generate a deformation image including the one or more anatomical elements based on the transformation and the captured image. The system may generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

Description

SPINE DEFORMATION INDUCED BY RIGID BODIES: SYNTHETIC LONG SCAN IMAGING FOR ARTIFICIAL INTELLIGENCE (Al) METHODSFIELD OF INVENTION

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 523,254, filed 26 June 2023, the entire content of which is incorporated herein by reference.BACKGROUND

[0002] 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.BRIEF SUMMARY

[0003] Example aspects of the present disclosure include:

[0004] A system including: a processor; and a memory storing data thereon that, when processed by the processor, causes the processor to: generate a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements included in a captured image of a subject; and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model; generate a deformation image including the one or more anatomical elements based on the transformation and the captured image; and generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0005] Any of the aspects herein, wherein the data is further executable by the processor to: compute a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image includes applying the deformation field to the captured image.

[0006] Any of the aspects herein, wherein computing the deformation field includes applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0007] Any of the aspects herein, wherein generating the transformation includes positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0008] Any of the aspects herein, wherein the data is further executable by the processor to generate one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0009] Any of the aspects herein, wherein: generating the deformation image includes correlating a first set of coordinates of one or more points of interest included in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image includes correlating the second set of coordinates to a third set of coordinates associated with the simulated multidimensional image.

[0010] Any of the aspects herein, wherein the data is further executable by the processor to transfer annotation information associated with one or more points of interest included in the captured image to at least one of the deformation image and the simulated multidimensional image.

[0011] Any of the aspects herein, wherein the simulated multidimensional image includes a digitally reconstructed radiograph including the one or more anatomical elements.

[0012] Any of the aspects herein, wherein: the captured image includes a computed tomography (CT) image; and the simulated multidimensional image includes a cone beam computed tomography (CBCT) image including the one or more anatomical elements.

[0013] Any of the aspects herein, wherein the captured image includes a preoperative multidimensional image.

[0014] A system including: a processor; and a memory storing data thereon that, when processed by the processor, cause the processor to: generate, based on a reference image associated with a medical condition and including one or more anatomical elements, a deformation image including the one or more anatomical elements; generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image; generate a second deformation image in association the medical condition, based on: a captured image including one or more target anatomical elements; and a learning model trained based at least in part on the reference image, the deformation image, and the simulated multidimensional image; and generate a second simulated multidimensional image in association with the medical condition, based on the second deformation image and the learning model.

[0015] Any of the aspects herein, wherein the data is further executable by the processor to: apply a deformation field associated with profile information included in the learning model to the one or more target anatomical elements in the captured image, wherein the profile information is associated with the medical condition, wherein generating the second deformation image is based on applying the deformation field.

[0016] Any of the aspects herein, wherein the data is executable by the processor to train the learning model in association with at least the medical condition based on: a first training dataset including at least the reference image; a second training dataset including at least the deformationimage and the second deformation image; and a third training dataset including at least the simulated multidimensional image and the second simulated multidimensional image.

[0017] Any of the aspects herein, wherein the simulated multidimensional image includes a digitally reconstructed radiograph or a cone beam computed tomography (CBCT) image.

[0018] A method including: generating a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements included in a captured image of a subject; and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model; generating a deformation image including the one or more anatomical elements based on the transformation and the captured image; and generating a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0019] Any of the aspects herein, further including: computing a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image includes applying the deformation field to the captured image.

[0020] Any of the aspects herein, wherein computing the deformation field includes applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0021] Any of the aspects herein, wherein generating the transformation includes positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0022] Any of the aspects herein, further including: generating one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0023] Any of the aspects herein, wherein: generating the deformation image includes correlating a first set of coordinates of one or more points of interest included in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image includes correlating the second set of coordinates to a third set of coordinates in associated with the simulated multidimensional image.

[0024] Any aspect in combination with any one or more other aspects.

[0025] Any one or more of the features disclosed herein.

[0026] Any one or more of the features as substantially disclosed herein.

[0027] Any one or more of the features as substantially disclosed herein in combination with any one or more other features as substantially disclosed herein.

[0028] Any one of the aspects / features / implementations in combination with any one or more other aspects / features / implementations.

[0029] Use of any one or more of the aspects or features as disclosed herein.

[0030] 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 implementation.

[0031] 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.

[0032] 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, implementations, 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, implementations, 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.

[0033] Numerous additional features and advantages of the present disclosure will become apparent to those skilled in the art upon consideration of the implementation descriptions provided hereinbelow.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0034] 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, implementations, and configurations of the disclosure, as illustrated by the drawings referenced below.

[0035] Fig. 1 illustrates an example of a system that supports aspects of the present disclosure.

[0036] Fig. 2A illustrates an example block diagram that supports aspects of the present disclosure. Fig. 2B illustrates an example block diagram that supports aspects of the present disclosure.

[0037] Fig. 3 illustrates an example process flow in accordance with aspects of the present disclosure.

[0038] Fig. 4 illustrates an example diagram in accordance with aspects of the present disclosure.

[0039] Fig. 5 illustrates an example diagram in accordance with aspects of the present disclosure.

[0040] Fig. 6 illustrates an example process flow in accordance with aspects of the present disclosure.

[0041] Fig. 7 illustrates an example process flow in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0042] 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 implementation, 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 implementations 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.

[0043] 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). 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).

[0044] 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 A 10 or 10X Fusion processors; Apple Al l, A 12, A12X, A12Z, or Al 3 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.

[0045] Before any implementations 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 implementations 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.

[0046] The terms proximal and distal are used in this disclosure with their conventional medical meanings, proximal being closer to the operator or user of the system, and further from the region of surgical interest in or on the patient, and distal being closer to the region of surgical interest in or on the patient, and further from the operator or user of the system.

[0047] Some imaging systems may support capturing images of a patient anatomy using an imaging device. In some radiological imaging workflows associated with taking images of a patient anatomy, the workflow includes acquiring capturing 2D “scout images” (also referred to herein as “localization images”) prior to a subsequent scan for capturing a subsequent image. For example, based on the 2D scout images, a user (e.g., radiology technician) may confirm that the anatomy has been captured for a surgical procedure.

[0048] The O-Arm® imaging system provided by Medtronic Navigation, Inc. supports providing a field of view (FOV) preview feature (also referred to herein as a FOV preview representation and a multiple FOV representation). Via the FOV preview representation, a user may view acquired 2D scout images, prior to the imaging system implementing a long scan process.

[0049] For example, the O-Arm® imaging system may support an imaging mode (also referred to herein as a “2D long film imaging,” a “long scan mode,” or a “long scan process”) capable of providing clinicians with coronal and sagittal long films to assess initial patient alignment and intraoperative corrections relative to their surgical goals. A long scan process described herein may include automatically acquiring low-dose X-ray projections while moving the gantry between two pre-programmed gantry locations and merging data of the projections (e.g., ‘stitch’ the projections together) to form a single long scan image (e.g., 2D long film image). Automatic labeling of the vertebrae in imaging process (e.g., 2D long film imaging) improves workflow and reduces the risk of surgical errors (e.g., wrong level surgery) by providing increased accuracy with respect to anatomical localization. Features of the O-Arm® imaging system and next generation implementations may support robotic-assisted surgery, planning, and Al-methods for spine metrics.

[0050] Techniques for training Al may involve an extensive and high-quality training dataset, which may be unattainable, time-consuming, and costly in some cases. Aspects of the present disclosure support generating realistic synthetic datasets from reference 3D medical images acquired from different patients, in which the reference 3D medical images cover a limited range of spine deformations (e.g., lumbar lordosis, scoliosis). Providing such synthetic datasets may support a much richer inclusion of clinical variance into a training dataset for training Al.

[0051] In some cases, realistic deformation of a volumetric image to produce a clinically relevant long scan image of various degrees of deformation in the spine may be challenging, and no known solutions have been proposed that provide realistic deformation and address overlapping / occlusion of 3D rigid bodies.

[0052] According to example aspects of the present disclosure, techniques described herein include computing the 3D deformation field induced by rigid bodies (e.g., bony anatomy). The techniques may include applying the 3D deformation field to acquired 3D images to produce deformed volumetric images. In some aspects, the techniques may include generating a simulated realistic long scan image (e.g., 2D long film image) based on the deformed volumetric images. The systems and techniques described herein support a model-based diffeomorphic non-rigid registration of the spine bony anatomy to compute a 3-D deformation field and a 3D deformation image. In some aspects, the model-based diffeomorphic non-rigid registration may preserve topology and preventintroducing folding. The terms “deformed image” and “deformation image” may be used interchangeably herein.

[0053] According to some example implementations, systems and techniques are described herein that support computing rigid induced elastic deformation into the non-rigid anatomy of the spine from a pre-operative 3Dimage and labeled bony anatomy. The systems and techniques include an augmented reality (AR) approach that supports providing a real-time overlay of a desired surgical plan onto an acquired long scan image (e.g., 2D long film image).

[0054] The systems and techniques may include 3D curve fitting. In some examples, the 3D curve fitting may include computing rigid transformations of a 3D bone model of the spine to generate clinical deformations (e.g., scoliosis, lumbar lordosis, kyphosis, etc.). For example, the systems and techniques may include generating clinical deformations relevant to a patient.

[0055] The systems and techniques may support producing realistic synthetic datasets for Al based on reference 3D medical images acquired from different patients. In some example aspects, for cases in which the reference 3D medical images represent a limited range of medical conditions (e.g., a limited range of spine deformations), the production of realistic synthetic datasets provides richer inclusion of clinical variance into a training dataset.

[0056] The systems and techniques described herein may support mechanisms for evaluating, quantifying, tracking, and simulating desired clinical outcomes over time. For example, the systems and techniques described herein may support evaluating, quantifying, tracking, and simulating global spine alignment metrics in patients undergoing corrective spinal surgery (e.g., simulation of specific metric values over time).

[0057] The systems and techniques described herein may support transferring existing annotations to synthetic datasets. For example, the systems and techniques described herein may support generating multiple synthetic data sets with annotations by transferring existing annotations (e.g., keypoints, labels, etc.) of an original 3D image of the patient anatomy of a patient onto a 3D deformation image generated in accordance with aspects of the present disclosure.

[0058] Implementations of the present disclosure provide technical solutions to one or more of the problems of (1) training datasets in which the training data represents a limited range of medical conditions (e.g., a limited range of spine deformations), (2) attainability, cost, and time associated with generating or obtaining extensive and high-quality training datasets, (3) generation of realistic deformation of a volumetric image to produce a clinically relevant long scan image of various degrees of deformation associated with a patient anatomy (e.g., the spine), and (4) automatic labelingof patient anatomy in the imaging process for improving workflow and reducing the risk of surgical errors.

[0059] Fig. 1 illustrates an example of a system 100 that supports aspects of the present disclosure.

[0060] The system 100 includes a computing device 102, one or more imaging devices 112, a robot 114, a navigation system 118, a database 130, and / or a cloud network 134 (or other network). Systems according to other implementations of the present disclosure may include more or fewer components than the system 100. For example, the system 100 may omit and / or include additional instances of one or more components of the computing device 102, the imaging device(s) 112, the robot 114, navigation system 118, the database 130, and / or the cloud network 134. In an example, the system 100 may omit any instance of the computing device 102, the imaging device(s) 112, the robot 114, navigation system 118, the database 130, and / or the cloud network 134. For example, the system 100 may omit the robot 114 and the navigation system 118. The system 100 may support the implementation of one or more other aspects of one or more of the methods disclosed herein.

[0061] The computing device 102 includes a processor 104, a memory 106, a communication interface 108, and a user interface 110. Computing devices according to other implementations of the present disclosure may include more or fewer components than the computing device 102.

[0062] 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 devices 112, the robot 114, the navigation system 118, the database 130, and / or the cloud network 134.

[0063] The memory 106 may be or include 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 associated with completing, for example, any step of the methods described herein, or of any other methods. The memory 106 may store, for example, instructions and / or machine learning models that support one or more functions of the imaging devices 112, the robot 114, and the navigation system 118. For instance, the memory 106 may store content (e.g., instructions and / or machine learning models) that, when executed by the processor 104, enable image processing 120, segmentation 122, transformation 124, registration 128, deformation engine 140, image simulation engine 144, and / or machine learning model(s) 148. Such content, if provided as in instruction, may, in some implementations, be organized into one or more applications, modules, packages, layers, or engines.

[0064] 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 method 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 devices 112, the robot 114, the navigation system 118, the deformation engine 140, the image simulation engine 144, the machine learning model(s) 148, the database 130, and / or the cloud network 134.

[0065] The computing device 102 may also include a communication interface 108. The communication interface 108 may be used for receiving data or other information from an external source (e.g., the imaging devices 112, the robot 114, the navigation system 118, the deformation engine 140, the image simulation engine 144, the machine learning model(s) 148, the database 130, the cloud network 134, and / or any other system or component separate from the system 100), and / or for transmitting instructions, data (e.g., image data, bone models, bone transforms, deformation field data, etc. etc.), or other information to an external system or device (e.g., another computing device 102, the imaging devices 112, the robot 114, the navigation system 118, the deformation engine 140, the image simulation engine 144, the machine learning model(s) 148, the database 130, the cloud network 134, and / or any other system or component not part of the system 100). The communication interface 108 may include 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 as802.1 la / b / g / n, Bluetooth, NFC, ZigBee, and so forth). In some implementations, the communication interface 108 may support communication between the device 102 and one or more other processors 104 or computing devices 102, whether to reduce the time needed to accomplish a computingintensive task or for any other reason.

[0066] The computing device 102 may also include one or more user interfaces 110. The user interface 110 may be or include 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 bythe system 100 from a source external to the system 100. In some implementations, the user interface 110 may support user modification (e.g., by a surgeon, medical personnel, a patient, etc.) of instructions to be executed by the processor 104 according to one or more implementations of the present disclosure, and / or to user modification or adjustment of a setting of other information displayed on the user interface 110 or corresponding thereto.

[0067] In some implementations, 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 implementations, the user interface 110 may be located proximate one or more other components of the computing device 102, while in other implementations, the user interface 110 may be located remotely from one or more other components of the computer device 102.

[0068] 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.). “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. In various examples, the image data may include data corresponding to an anatomical feature of a patient, or to a portion thereof. The image data may be or include a preoperative image, an intraoperative image, a postoperative image, or an image taken independently of any surgical procedure. In some implementations, 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 include, for example, an ultrasound scanner (which may include, 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 include, 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 include a transmitter / emitter and a receiver / detector that are in separate housings or are otherwise physically separated.

[0069] In some implementations, the imaging device 112 may include 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 implementations, 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.

[0070] The robot 114 may be any surgical robot or surgical robotic system. The robot 114 may be or include, 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 (whether based on guidance from the navigation system 118 or not) to accomplish or to assist with a surgical task. In some implementations, 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 include one or more robotic arms 116. In some implementations, the robotic arm 116 may include a first robotic arm and a second robotic arm, though the robot 114 may include more than two robotic arms. In some implementations, one or more of the robotic arms 116 may be used to hold and / or maneuver the imaging device 112. In implementations where the imaging device 112 includes 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.

[0071] 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.

[0072] The robotic arm(s) 116 may include 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).

[0073] In some implementations, 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. In some implementations, the navigation system 118 can be used to track other components of the system (e.g., imaging device 112) and the system can operate without the use of the robot 114 (e.g., with the surgeon manually manipulating the imaging device 112 and / or one or more surgical tools, based on information and / or instructions generated by the navigation system 118, for example).

[0074] 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 implementations, the navigation system 118 may include one or more electromagnetic sensors. In various implementations, 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 implementations, 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, 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.

[0075] Example aspects of the deformation engine 140 and the image simulation engine 144 are later described with reference to the following figures.

[0076] The processor 104 may utilize data stored in memory 106 as a neural network. The neural network may include a machine learning architecture. In some aspects, the neural network may be or include one or more classifiers. In some other aspects, the neural network may be or include any machine learning network such as, for example, a deep learning network, a convolutional neural network, a reconstructive neural network, a generative adversarial neural network, or any other neural network capable of accomplishing functions of the computing device 102 described herein. Some elements stored in memory 106 may be described as or referred to as instructions or instruction sets, and some functions of the computing device 102 may be implemented using machine learning techniques.

[0077] For example, the processor 104 may support machine learning model(s) 148 which may be trained and / or updated based on data (e.g., training data 152) provided or accessed by any of the computing device 102, the imaging device 112, the robot 114, the navigation system 118, the database 130, the cloud network 134, the deformation engine 140, and / or the image simulation engine 144. The machine learning model(s) 148 may be built and updated by the computing device 102 based on the training data 152 (also referred to herein as training data and feedback).

[0078] For example, the machine learning model(s) 148 may be trained with one or more training sets included in the training data 152. In some aspects, the training data 152 may include multiple training sets. In an example, the training data 152 may include a first training set that includes images associated with a medical condition (e.g., scoliosis, lumbar lordosis, kyphosis, etc.). The training data 152 may include a second training set that includes deformation images generated in accordance with aspects of the present disclosure. The training data 152 may include a third training set that includes simulated multidimensional images generated in accordance with aspects of the present disclosure. In some aspects, the training data 152 can be structured to support supervised, self-supervised, semi-supervised, and unsupervised training methods utilizing data that may or may not include an original CT (and radiographic simulations from the original CT), a deformed CT (and radiographic simulations from the deformed CT), bone segmentations, and deformation fields.

[0079] In some examples, based on the data, the neural network may generate one or more algorithms (e.g., processing algorithms) supportive of modeling 3D spine deformation induced by rigid bodies, generating deformation images based on associated deformation fields, and 3D synthetic long scan imaging for Al methods described herein.

[0080] 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; and / or any other useful information.

[0081] 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 network 134. In some implementations, the database 130 may be or include 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.

[0082] In some aspects, the computing device 102 may communicate with a server / s) and / or a database (e.g., database 130) directly or indirectly over a communications network (e.g., the cloud network 134). The communications network may include any type of known communication medium or collection of communication media and may use any type of protocols to transport data between endpoints. The communications network may include wired communications technologies, wireless communications technologies, or any combination thereof.

[0083] Wired communications technologies may include, for example, Ethernet-based wired local area network (LAN) connections using physical transmission mediums (e.g., coaxial cable, copper cable / wire, fiber-optic cable, etc.). Wireless communications technologies may include, for example, cellular or cellular data connections and protocols (e.g., digital cellular, personal communications service (PCS), cellular digital packet data (CDPD), general packet radio service (GPRS), enhanced data rates for global system for mobile communications (GSM) evolution (EDGE), code division multiple access (CDMA), single-carrier radio transmission technology (IxRTT), evolution-data optimized (EVDO), high speed packet access (HSPA), universal mobile telecommunications service (UMTS), 3G, long term evolution (LTE), 4G, and / or 5G, etc.), Bluetooth®, Bluetooth® low energy, Wi-Fi, radio, satellite, infrared connections, and / or ZigBee® communication protocols.

[0084] The Internet is an example of the communications network that constitutes an Internet Protocol (IP) network consisting of multiple computers, computing networks, and other communication devices located in multiple locations, and components in the communicationsnetwork (e.g., computers, computing networks, communication devices) may be connected through one or more telephone systems and other means. Other examples of the communications network may include, without limitation, a standard Plain Old Telephone System (POTS), an Integrated Services Digital Network (ISDN), the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a wireless LAN (WLAN), a Session Initiation Protocol (SIP) network, a Voice over Internet Protocol (VoIP) network, a cellular network, and any other type of packet-switched or circuit- switched network known in the art. In some cases, the communications network may include of any combination of networks or network types. In some aspects, the communications network may include any combination of communication mediums such as coaxial cable, copper cable / wire, fiber-optic cable, or antennas for communicating data (e.g., transmitting / receiving data).

[0085] The computing device 102 may be connected to the cloud network 134 via the communication interface 108, using a wired connection, a wireless connection, or both. In some implementations, the computing device 102 may communicate with the database 130 and / or an external device (e.g., a computing device) via the cloud network 134.

[0086] The system 100 or similar systems may be used, for example, to carry out one or more aspects of any of the methods or process flows described herein. The system 100 or similar systems may also be used for other purposes.

[0087] Fig. 2A illustrates an example block diagram 200 that supports aspects of the present disclosure. Aspects of the block diagram 200 may be implemented by a computing device 102 described herein. As described with reference to Fig. 2A, the computing device 102 may support computing a deformation field applied to a patient anatomy and generating deformation images (also referred to herein as deformed images) of the patient anatomy using the deformation field. In some aspects, the deformation field may be a 3D deformation field, and the deformation images may be 3D images.

[0088] The deformation engine 140 may support generating, based on an image 205 of a patient anatomy and a bone model 210 of the patient anatomy, a deformation image 225 of the patient anatomy. In an example, the image 205 may be a 3D image, the bone model 210 may be a 3D bone model, and the deformation image 225 may be a 3D deformation image.

[0089] In some aspects, the deformation engine 140 may be implemented by the computing device 102 in response to executing instructions stored on memory 106 of the computing device 102. In some aspects, the deformation engine 140 may perform one or more steps associated with generatingthe deformation image 225. It is to be understood that example aspects described herein may be performed by the computing device 102, the deformation engine 140, or components therein.

[0090] According to example aspects of the present disclosure, the computing device 102 may process image 205 and bone model 210. Example aspects of processing the image 205 and the bone model 210 in association with generating a deformation image 225 are described herein with reference to image processing blocks 217 through 223.

[0091] At 217, the computing device 102 may perform a transformation of bones of the bone model 210. For example, the computing device 102 may apply a transform on each segmented bone of the bone model 210 according to a profile associated with a clinical deformation (e.g., scoliosis, lumbar lordosis, kyphosis, and the like).

[0092] In the example, the bone model 210 may be a model of the spine bony anatomy (e.g., cervical spine, thoracic spine, lumbar spine, etc.). In an example implementation, the bone model 210 may be a model of a spine (e.g., cervical spine, thoracic spine, etc.) and the vertebrae of the spine. The bone model 210 may be a mathematical model of the spine.

[0093] In some examples, the transform may be a piecewise-rigid transform. For example, the computing device 102 may translate and rotate one or more bones of the bone model 210 with respect to another bone of the bone model 210. In an example, for a bone model 210 of a spine, vertebra can move with respect to another, but the data within a single vertebra remains rigid. In another example, the transform may be a non-rigid transform. For example, the computing device 102 may apply a rigid- induced elastic deformation to one or more bones of the bone model 210. In some aspects, the transform may be referred to as a deformation transform.

[0094] At 219, the computing device 102 may compose bone models. For example, the computing device 102 may generate a bone model 211 (or update bone model 210) based on the transform applied at 217 to the bone model 210. The bone model 211 may be representative of the bone model 210 in response to the transform. Accordingly, for example, at 219, the computing device 102 may compose both acquired bone models (e.g., bone model 210) and transformed 3D bone models (e.g., bone model 211) into single binary 3D volumes. Non-limiting examples of the binary 3D volumes are illustrated at Figs. 3 and 4.

[0095] At 221, the computing device 102 may compute a deformation field based on the bone model 210 and the bone model 211. For example, the computing device 102 may apply a diffeomorphic non-rigid registration in association with computing the deformation field.

[0096] Diffeomorphic non-rigid registration includes aligning and matching images of the same anatomical structure from different modalities, angles, or time points. Diffeomorphic non-rigidregistration may include applying mathematical models and algorithms to describe the deformation of the structure being registered. For example, in model-based diffeomorphic non-rigid registration, the computing device 102 may use a mathematical model of the anatomical structure to generate a deformation field that maps one image (e.g., image 205) onto another image (e.g., another image 205, deformation image 225, etc.).

[0097] Diffeomorphic non-rigid registration may include smooth and invertible transformations that preserve the topology of the structure being registered. Using diffeomorphic non-rigid registration, the computing device 102 may create a precise and accurate mapping between images (e.g., image 205 and another image 205, image 205 and deformation image 225, etc.), even for cases of significant deformation or change in the anatomical structure. In some examples, the diffeomorphic non-rigid registration described herein with respect to aspects of the present disclosure may be model-based diffeomorphic non-rigid registration or fluid- like registration deformation.

[0098] Accordingly, for example, the deformation field computed at 221 may correspond to the transform applied in association with generating the bone model 211. For example, the deformation field may correspond to the deformation applied to the bone model 210 in association with generating the bone model 211.

[0099] At 223, the computing device 102 may generate deformation image 225 (also referred to herein as a deformed image). For example, the computing device 102 may apply the deformation field to the image 205. The computing device 102 may apply the deformation field to the patient anatomy as included in the image 205.

[0100] Accordingly, for example, as described with reference to Fig. 2A, the systems and techniques described herein support a model-based diffeomorphic non-rigid registration of the spine bony anatomy to compute a multidimensional deformation field (e.g., 3D deformation field) and a deformation image (e.g., a deformed 3D image). The model-based diffeomorphic non-rigid registration may preserve topology among components of a patient anatomy. For example, the model-based diffeomorphic non-rigid registration described herein may preserve topology among vertebrae of the spine. In some other aspects, the model-based diffeomorphic non-rigid registration may prevent introducing folding in the deformation field.

[0101] The example aspects described with reference to Fig. 2A may support computing a 3D deformation field between an acquired bone model (e.g., bone model 210) and a transformed bone model (e.g., bone model 211) and, based on the 3D deformation field, generating a deformation image (e.g., deformation image 225), examples of which are later illustrated at Figs. 3 and 4. Insome example implementations, the systems and techniques described herein support using a computed deformation field in association with generating a final surgical plan including implantable medical devices (e.g., target rod bending, target screw positions, etc.) from a preoperative 3D scan of a patient. In some cases, the pre-operative 3D scan may be a scan that was acquired before a surgical procedure (e.g., days before the surgical procedure).

[0102] Fig. 2B illustrates an example block diagram 201 that supports aspects of the present disclosure. Aspects of the block diagram 201 may be implemented by the system 100 described herein. The block diagram 201 includes example aspects described with reference to the block diagram 200 of Fig. 2A, and repeated descriptions of like elements are omitted for brevity.

[0103] With reference to Fig. 2B, the computing device 102 may further include an image simulation engine 144 supportive of image acquisition and reconstruction. In some aspects, the image simulation engine 144 may be implemented by the computing device 102 in response to executing instructions stored on memory 106 of the computing device 102.

[0104] Using the deformation engine 140 and the image simulation engine 144, the computing device 102 may generate a deformation image 225 of a patient anatomy from an image 205 of the patient anatomy. The computing device 102 may generate (from the deformation image 225) a simulated long scan image 235 of the patient anatomy. In the examples described herein, the image 205 may be a 3D image, the deformation image 225 may be a 3D deformation image, and the simulated long scan image 235 may be a simulated 2D long scan image (e.g., simulated 2D long film).

[0105] The computing device 102 may support the transferring of pre-existing annotations (e.g., keypoints, labels, etc.) associated with elements of the patient anatomy from the image 205 onto the deformation image 225. In some aspects, using the deformation engine 140 and the image simulation engine 144, the computing device 102 may identify and transfer the pre-existing annotations (e.g., keypoints, labels, etc.) from the image 205 to the deformation image 225 and to the simulated long scan image 235. It is to be understood that example aspects described herein may be performed by the system 100, the computing device 102, the deformation engine 140, the image simulation engine 144, or components therein.

[0106] Fig. 3 illustrates an example process flow 300 in accordance with aspects of the present disclosure. Example aspects of the process flow 300 are described with reference to the block diagram 201 of Fig. 2B. Process flow 300 may be implemented by aspects of the system 100, computing device 102, deformation engine 140, and image simulation engine 144 described with reference to Figs. 1, 2A, and 2B. The process flow 300 includes example aspects described withreference to image processing blocks 217 through 223 of Fig. 2A, and repeated descriptions of like elements are omitted for brevity.

[0107] In the following description of the process flow 300, the operations may be performed in a different order than the order shown, or the operations may be performed in different orders or at different times. Certain operations may also be left out of the process flow 300, or other operations may be added to the process flow 300.

[0108] It is to be understood that while a computing device 102 is described as performing a number of the operations of process flow 300, any device (e.g., another computing device 102 in communication with the computing device 102) may perform the operations shown.

[0109] At 305, the computing device 102 may receive an image 205 of a patient anatomy.

[0110] At 310, the computing device 102 may identify keypoints (also referred to herein as marker points) included in the image 205. The keypoints may be associated with the patient anatomy. For example, the keypoints may be reference points or landmarks for identifying anatomical structures of the patient anatomy or other features within the image 205. In some aspects, at 310, the computing device 102 may and identify, from image data of the image 205, respective coordinates 207 associated with the keypoints.

[0111] At 315, the computing device 102 may access a bone transform 212 from a library 213 of bone transforms 212 stored at a repository (e.g., at memory 106 or database 130 described with reference to Fig. 1). The bone transform 212 may correspond to a target clinical deformation (e.g., scoliosis, lumbar lordosis, kyphosis, etc.). The bone transform 212 may be a rigid bone transform, a non-rigid bone transform, or a rigid-induced elastic transform as described herein.

[0112] In some aspects, the computing device 102 may access and select the bone transform 212 in response to a user input. In an example implementation, for patient specific modeling of a target clinical deformation for a patient, the image 205 may be an image of the anatomy of the patient. The user input may include an indication of the target clinical deformation.

[0113] At 320, the computing device 102 may apply a deformation field to the image 205. The computing device 102 may determine the deformation field based on the bone transform 212.

[0114] At 325, based on applying the deformation field to the image 205, the computing device 102 may generate a deformation image 225 that corresponds to the target clinical deformation. Accordingly, for example, the computing device 102 may generate deformation images 225 that support modeling of potential clinical scenarios.

[0115] At 330, the computing device 102 may generate new coordinates (e.g., coordinates 208) for the keypoints. The coordinates 208 may correspond to updated locations of the keypoints asrepresented in the deformation image 225. For example, the updated locations of the keypoints may be a result of applying the bone transform 212 (and corresponding deformation field) to the image 205.

[0116] At 335, the computing device 102 may transfer, from the image 205 to the deformation image 225, any pre-existing annotations (e.g., labels) corresponding to the keypoints.

[0117] Aspects of the present disclosure support generating simulated long scan images 235 for the modeling of potential clinical scenarios. For example, at 340, using the image simulation engine 144, the computing device 102 may generate a simulated long scan image 235 based on image data of the deformation image 225.

[0118] In an example, the simulated long scan image 235 may include keypoints from the deformation image 225. The computing device 102 may output coordinates 209 for the keypoints. The coordinates 209 may correspond to locations of the keypoints as represented in the simulated long scan image 235. The computing device 102 may transfer, from the deformation image 225 to the simulated long scan image 235, the annotations corresponding to the keypoints.

[0119] Accordingly, for example, the systems and techniques support generating multiple synthetic data sets with annotations by transferring existing annotations (e.g., labels, etc.) corresponding to keypoints from an original 3D image (e.g., image 205) onto a new deformation 3D image (e.g., deformation image 225). The systems and techniques support simulating a medical image (e.g., X-ray image, 2D long scan image, etc.) based on the new deformation 3D image with the annotations. The systems and techniques described herein provide technical improvements in that, in an operating room environment, the computing device 102 may generate an augmented synthetic long scan image (also referred to herein as a digitally reconstructed radiograph (DRR)) according to a final target surgical plan (e.g., a final desired planning) for a patient. The computing device 102 may overlay the augmented synthetic long scan image onto an acquired long scan image of the patient for confirmation of whether the surgical plan has been completed.

[0120] The systems and techniques described herein may support generating multiple 3D volume images (e.g., deformation images 225, simulated long scan images 235, etc.) from single CT data (e.g., an image 205), in which the multiple 3D volume images have various degree of deformations. As described herein, the systems and techniques may provide corresponding annotations for each 3D volume image. The features described herein for transferring annotations may eliminate or reduce instances in which a user manually annotates individual 3D volume images, which may thereby reduce time, cost, and potential errors associated with an imaging workflow.

[0121] Fig. 4 is an example diagram 400 that supports model-based diffeomorphic non-rigid registration of a patient anatomy (e.g., spine bony anatomy) in accordance with aspects of the present disclosure.

[0122] Example diagram 400 includes examples of a bone model 210-a of a patient anatomy prior to a bone transform, a bone model 211-a of the patient anatomy following the bone transform and computation of a deformation field, an image 205-a (e.g., an original image) of the patient anatomy prior to applying the computed deformation field, and a deformation image 225-a of the patient anatomy as generated in response to applying the computed deformation field to image 205-a. In some example implementations, applying the computed deformation field may include applying fluid-like regularization techniques in association with smoothing and regularizing the deformation field, reducing noise, and improving the visual quality of registration results.

[0123] Example diagram 400 further includes an example of a residual 240 due to inconsistencies or mismatches between the image 205-a and the deformation image 225-a. 206-a illustrates an example of the image 205-a and an overlaid grid line, before applying the computed deformation field. 226-a illustrates an example of the image 205-a and the overlaid grid line, after applying the computed deformation field.

[0124] Fig. 5 is an example diagram 500 illustrating a 3D example of model-based diffeomorphic non-rigid registration of the patient anatomy (e.g., spine bony anatomy) in accordance with aspects of the present disclosure.

[0125] Example diagram 500 includes examples of a bone model 210-b of the patient anatomy (e.g., segmented spine) prior to a bone transform, a bone model 211-b of the patient anatomy following the bone transform and computation of a deformation field, images 205 -c through 205 -e (e.g., original images) of the patient anatomy prior to applying the computed deformation field, and deformation images 225-c through 225-e of the patient anatomy as generated in response to applying the computed deformation field to images 205-c through 205-e. In some example implementations, applying the computed deformation field may include applying fluid-like regularization techniques as described herein.

[0126] Referring to example diagram 500, image 205-b is an example of an original CT image overlayed with the segmented spine, and image 205 -f is an example of the original CT image overlayed with bone model 210-f (target bone model) (e.g., prior to alignment). Example diagram 500 illustrates a 3D visualization of the bone model 210-b and a 3D visualization of the bone model 210-f (target bone model).

[0127] Image 205-c is an example of an original CT image overlayed with the bone model 210-f (e.g., prior to alignment). Image 205-d and image 205-e are examples of simulated 2D long films of the original CT image.

[0128] Image 225-c is an example of a deformed CT image overlayed with the bone model 210-f (e.g., after alignment). Image 225-d and image 225-e are examples of simulated 2D long films of the deformed CT image.

[0129] Fig. 6 illustrates an example process flow 600 in accordance with aspects of the present disclosure. Process flow 600 may be implemented by aspects of the system 100 described herein. In the following description of the process flow 600, the operations may be performed in a different order than the order shown, or the operations may be performed in different orders or at different times. Certain operations may also be left out of the process flow 600, or other operations may be added to the process flow 600.

[0130] It is to be understood that while a computing device 102 is described as performing a number of the operations of process flow 600, any device (e.g., another computing device 102 in communication with the computing device 102) may perform the operations shown. In some examples, the process flow 600 may be implemented by a system including: a processor; and a memory storing data thereon that, when processed by the processor, causes the processor to perform aspects of the process flow 600.

[0131] At 605, the process flow 600 may include generating a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements included in a captured image of a subject; and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model.

[0132] In some aspects, generating the transformation includes positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0133] At 610, the process flow 600 may include computing a deformation field based on the multidimensional bone model and the transformation.

[0134] In some aspects, computing the deformation field includes applying a diffeomorphic non- rigid registration to the one or more anatomical elements.

[0135] At 615, the process flow 600 may include generating a deformation image including the one or more anatomical elements based on the transformation and the captured image.

[0136] In some aspects, generating the deformation image includes applying the deformation field (of 610) to the captured image.

[0137] In some aspects, generating the deformation image includes correlating a first set of coordinates of one or more points of interest included in the captured image to a second set of coordinates in association with the deformation image.

[0138] At 620, the process flow 600 may include generating a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0139] In some aspects, generating the simulated multidimensional image includes correlating the second set of coordinates to a third set of coordinates in associated with the simulated multidimensional image.

[0140] At 625, the process flow 600 may include generating one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0141] In some aspects, the process flow 600 may include transferring annotation information associated with one or more points of interest included in the captured image to at least one of the deformation image and the simulated multidimensional image.

[0142] In some aspects, the captured image includes a preoperative multidimensional image. In some aspects, the simulated multidimensional image includes a digitally reconstructed radiograph including the one or more anatomical elements.

[0143] In some aspects, the captured image includes a computed tomography (CT) image. In some aspects, the simulated multidimensional image includes a cone beam computed tomography (CBCT) image including the one or more anatomical elements.

[0144] Fig. 7 illustrates an example process flow 700 in accordance with aspects of the present disclosure. Process flow 700 may be implemented by aspects of the system 100 described herein. In the following description of the process flow 700, the operations may be performed in a different order than the order shown, or the operations may be performed in different orders or at different times. Certain operations may also be left out of the process flow 700, or other operations may be added to the process flow 700.

[0145] It is to be understood that while a computing device 102 is described as performing a number of the operations of process flow 700, any device (e.g., another computing device 102 in communication with the computing device 102) may perform the operations shown. In some examples, the process flow 700 may be implemented by a system including: a processor; and a memory storing data thereon that, when processed by the processor, causes the processor to perform aspects of the process flow 700.

[0146] At 705, the process flow 700 may include generating, based on a reference image associated with a medical condition and including one or more anatomical elements, a deformation image including the one or more anatomical elements.

[0147] At 710, the process flow 700 may include generating a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0148] At 715, the process flow 700 may include generating a second deformation image in association the medical condition, based on: a captured image including one or more target anatomical elements; and a learning model trained based on the reference image, the deformation image, and the simulated multidimensional image.

[0149] At 720, the process flow 700 may include applying a deformation field associated with profile information included in the learning model to the one or more target anatomical elements in the captured image, wherein the profile information is associated with the medical condition, wherein generating the second deformation image is based on applying the deformation field.

[0150] At 725, the process flow 700 may include generating a second simulated multidimensional image in association with the medical condition, based on the second deformation image and the learning model.

[0151] At 730, the process flow 700 may include training the learning model in association with at least the medical condition based on: a first training dataset including at least the reference image; a second training dataset including at least the deformation image and the second deformation image; and a third training dataset including at least the simulated multidimensional image and the second simulated multidimensional image.

[0152] In some aspects, the simulated multidimensional image includes a digitally reconstructed radiograph or a cone beam computed tomography (CBCT) image.

[0153] The process flows described herein (and / or one or more operations 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. A processor other than any processor described herein may also be used to execute the process flows. The at least one processor may perform operations of the process flows described herein 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 operations of a function as shown in the process flows. One or more portions of the process flows may be performed by the processor executing any of the contents of memory, such as image processing 120, asegmentation 122, a transformation 124, a registration 128, a deformation engine 140, an image simulation engine 144, and / or model(s) 148.

[0154] As noted above, the present disclosure encompasses methods with fewer than all of the steps identified in the figures (and corresponding description of the respective process flows), as well as methods that include additional steps beyond those identified in the figures (and corresponding description of the respective process flows). The present disclosure also encompasses methods that include 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 include a registration or any other correlation.

[0155] 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, implementations, and / or configurations for the purpose of streamlining the disclosure. The features of the aspects, implementations, and / or configurations of the disclosure may be combined in alternate aspects, implementations, 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 lie in less than all features of a single foregoing disclosed aspect, implementation, 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 implementation of the disclosure.

[0156] Moreover, though the foregoing has included description of one or more aspects, implementations, 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, implementations, 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.

[0157] Example aspects of the present disclosure include:

[0158] A system including: a processor; and a memory storing data thereon that, when processed by the processor, causes the processor to: generate a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elementsincluded in a captured image of a subject; and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model; generate a deformation image including the one or more anatomical elements based on the transformation and the captured image; and generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0159] Any of the aspects herein, wherein the data is further executable by the processor to: compute a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image includes applying the deformation field to the captured image.

[0160] Any of the aspects herein, wherein computing the deformation field includes applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0161] Any of the aspects herein, wherein generating the transformation includes positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0162] Any of the aspects herein, wherein the data is further executable by the processor to generate one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0163] Any of the aspects herein, wherein: generating the deformation image includes correlating a first set of coordinates of one or more points of interest included in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image includes correlating the second set of coordinates to a third set of coordinates associated with the simulated multidimensional image.

[0164] Any of the aspects herein, wherein the data is further executable by the processor to transfer annotation information associated with one or more points of interest included in the captured image to at least one of the deformation image and the simulated multidimensional image.

[0165] Any of the aspects herein, wherein the simulated multidimensional image includes a digitally reconstructed radiograph including the one or more anatomical elements.

[0166] Any of the aspects herein, wherein: the captured image includes a computed tomography (CT) image; and the simulated multidimensional image includes a cone beam computed tomography (CBCT) image including the one or more anatomical elements.

[0167] Any of the aspects herein, wherein the captured image includes a preoperative multidimensional image.

[0168] A system including: a processor; and a memory storing data thereon that, when processed by the processor, cause the processor to: generate, based on a reference image associated with amedical condition and including one or more anatomical elements, a deformation image including the one or more anatomical elements; generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image; generate a second deformation image in association the medical condition, based on: a captured image including one or more target anatomical elements; and a learning model trained based at least in part on the reference image, the deformation image, and the simulated multidimensional image; and generate a second simulated multidimensional image in association with the medical condition, based on the second deformation image and the learning model.

[0169] Any of the aspects herein, wherein the data is further executable by the processor to: apply a deformation field associated with profile information included in the learning model to the one or more target anatomical elements in the captured image, wherein the profile information is associated with the medical condition, wherein generating the second deformation image is based on applying the deformation field.

[0170] Any of the aspects herein, wherein the data is executable by the processor to train the learning model in association with at least the medical condition based on: a first training dataset including at least the reference image; a second training dataset including at least the deformation image and the second deformation image; and a third training dataset including at least the simulated multidimensional image and the second simulated multidimensional image.

[0171] Any of the aspects herein, wherein the simulated multidimensional image includes a digitally reconstructed radiograph or a cone beam computed tomography (CBCT) image.

[0172] A method including: generating a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements included in a captured image of a subject; and the transformation includes a non-rigid transformation of at least a portion of the multidimensional bone model; generating a deformation image including the one or more anatomical elements based on the transformation and the captured image; and generating a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0173] Any of the aspects herein, further including: computing a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image includes applying the deformation field to the captured image.

[0174] Any of the aspects herein, wherein computing the deformation field includes applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0175] Any of the aspects herein, wherein generating the transformation includes positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0176] Any of the aspects herein, further including: generating one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0177] Any of the aspects herein, wherein: generating the deformation image includes correlating a first set of coordinates of one or more points of interest included in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image includes correlating the second set of coordinates to a third set of coordinates in associated with the simulated multidimensional image.

[0178] Any aspect in combination with any one or more other aspects.

[0179] Any one or more of the features disclosed herein.

[0180] Any one or more of the features as substantially disclosed herein.

[0181] Any one or more of the features as substantially disclosed herein in combination with any one or more other features as substantially disclosed herein.

[0182] Any one of the aspects / features / implementations in combination with any one or more other aspects / features / implementations.

[0183] Use of any one or more of the aspects or features as disclosed herein.

[0184] 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 implementation.

[0185] The phrases “at least one,” “one or more,” “or,” 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,” “A, B, and / or C,” and “A, B, 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.

[0186] 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.

[0187] The term “automatic” and variations thereof, as used herein, refers to any process or operation, which is typically continuous or semi-continuous, done without material human input when the process or operation is performed. However, a process or operation can be automatic, even though performance of the process or operation uses material or immaterial human input, if the inputis received before performance of the process or operation. Human input is deemed to be material if such input influences how the process or operation will be performed. Human input that consents to the performance of the process or operation is not deemed to be “material.”

[0188] Aspects of the present disclosure may take the form of an implementation that is entirely hardware, an implementation that is entirely software (including firmware, resident software, microcode, etc.) or an implementation combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module,” or “system.” Any combination of one or more computer- readable medium(s) may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.

[0189] A computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0190] A computer-readable signal medium may include a propagated data signal with computer- readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium that is not a computer-readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0191] The terms “determine,” “calculate,” “compute,” and variations thereof, as used herein, are used interchangeably and include any type of methodology, process, mathematical operation or technique.

[0192] Example 1. A system comprising: a processor; and a memory storing data thereon that, when processed by the processor, causes the processor to: generate a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements comprised in a captured image of a subject; and the transformation comprises a non-rigid transformation of at least a portion of the multidimensional bone model; generate a deformation image comprising the one or more anatomical elements based on the transformation and the captured image; and generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0193] Example 2. The system of example 1, wherein the data is further executable by the processor to: compute a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image comprises applying the deformation field to the captured image.

[0194] Example 3. The system of example 2, wherein computing the deformation field comprises applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0195] Example 4. The system of example 1, wherein generating the transformation comprises positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0196] Example 5. The system ofexample 1, wherein the data is further executable by the processor to generate one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0197] Example 6. The system of example 1, wherein: generating the deformation image comprises correlating a first set of coordinates of one or more points of interest comprised in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image comprises correlating the second set of coordinates to a third set of coordinates associated with the simulated multidimensional image.

[0198] Example 7. The system of example 1, wherein the data is further executable by the processor to transfer annotation information associated with one or more points of interest comprised in the captured image to at least one of the deformation image and the simulated multidimensional image.

[0199] Example 8. The system of example 1, wherein the simulated multidimensional image comprises a digitally reconstructed radiograph comprising the one or more anatomical elements.

[0200] Example 9. The system of example 1, wherein:

[0201] the captured image comprises a computed tomography (CT) image; and

[0202] the simulated multidimensional image comprises a cone beam computed tomography (CBCT) image comprising the one or more anatomical elements.

[0203] Example 10. The system of example 1, wherein the captured image comprises a preoperative multidimensional image.

[0204] Example 11. A system comprising: a processor; and a memory storing data thereon that, when processed by the processor, cause the processor to: generate, based on a reference image associated with a medical condition and comprising one or more anatomical elements, a deformation image comprising the one or more anatomical elements; generate a simulated multidimensional image of the one or more anatomical elements based on the deformation image; generate a second deformation image in association the medical condition, based on: a captured image comprising one or more target anatomical elements; and a learning model trained based at least in part on the reference image, the deformation image, and the simulated multidimensional image; and generate a second simulated multidimensional image in association with the medical condition, based on the second deformation image and the learning model.

[0205] Example 12. The system of example 11, wherein the data is further executable by the processor to:apply a deformation field associated with profile information comprised in the learning model to the one or more target anatomical elements in the captured image, wherein the profile information is associated with the medical condition, wherein generating the second deformation image is based on applying the deformation field.

[0206] Example 13. The system of example 11, wherein the data is executable by the processor to train the learning model in association with at least the medical condition based on: a first training dataset comprising at least the reference image; a second training dataset comprising at least the deformation image and the second deformation image; and a third training dataset comprising at least the simulated multidimensional image and the second simulated multidimensional image.

[0207] Example 14. The system of example 11, wherein the simulated multidimensional image comprises a digitally reconstructed radiograph or a cone beam computed tomography (CBCT) image.

[0208] Example 15. A method comprising: generating a transformation of a multidimensional bone model, wherein: the multidimensional bone model corresponds to one or more anatomical elements comprised in a captured image of a subject; and the transformation comprises a non-rigid transformation of at least a portion of the multidimensional bone model; generating a deformation image comprising the one or more anatomical elements based on the transformation and the captured image; and generating a simulated multidimensional image of the one or more anatomical elements based on the deformation image.

[0209] Example 16. The method of example 15, further comprising: computing a deformation field based on the multidimensional bone model and the transformation, wherein generating the deformation image comprises applying the deformation field to the captured image.

[0210] Example 17. The method of example 16, wherein computing the deformation field comprises applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

[0211] Example 18. The method of example 15, wherein generating the transformation comprises positioning at least the portion of the multidimensional bone model according to a target medical condition.

[0212] Example 19. The method of example 15, further comprising: generating one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image.

[0213] Example 20. The method of example 15, wherein: generating the deformation image comprises correlating a first set of coordinates of one or more points of interest comprised in the captured image to a second set of coordinates in association with the deformation image; and generating the simulated multidimensional image comprises correlating the second set of coordinates to a third set of coordinates in associated with the simulated multidimensional image.

Claims

CLAIMSWhat is claimed is:

1. A system (100) comprising: a processor (104); and a memory (106) storing data thereon that, when processed by the processor (104), causes the processor (104) to: generate a transformation of a multidimensional bone model (210, 211), wherein: the multidimensional bone model (210, 211) corresponds to one or more anatomical elements comprised in a captured image (205) of a subject; and the transformation comprises a non-rigid transformation of at least a portion of the multidimensional bone model (210, 211); generate a deformation image (225) comprising the one or more anatomical elements based on the transformation and the captured image (205); and generate a simulated multidimensional image (235) of the one or more anatomical elements based on the deformation image (225).

2. The system (100) of any of claims 1 to , wherein the data is further executable by the processor (104) to: compute a deformation field based on the multidimensional bone model (210, 211) and the transformation, wherein generating the deformation image (225) comprises applying the deformation field to the captured image (205).

3. The system (100) of any of claims 1 or 2, wherein computing the deformation field comprises applying a diffeomorphic non-rigid registration to the one or more anatomical elements.

4. The system (100) of any of claims 1 to 3, wherein generating the transformation comprises positioning at least the portion of the multidimensional bone model (210, 211) according to a target medical condition.

5. The system (100) of any of claims 1 to 4, wherein the data is further executable by the processor (104) to generate one or more surgical plans associated with the one or more anatomical elements based on the simulated multidimensional image (235).

6. The system (100) of any of claims 1 to 5, wherein: generating the deformation image (225) comprises correlating a first set of coordinates (207) of one or more points of interest comprised in the captured image (205) to a second set of coordinates (208) in association with the deformation image (225); and generating the simulated multidimensional image (235) comprises correlating the second set of coordinates (208) to a third set of coordinates (209) associated with the simulated multidimensional image (235).

7. The system (100) of any of claims 1 to 6, wherein the data is further executable by the processor (104) to transfer annotation information associated with one or more points of interest comprised in the captured image (205) to at least one of the deformation image (225) and the simulated multidimensional image (235).

8. The system (100) of any of claims 1 to 7, wherein the simulated multidimensional image (235) comprises a digitally reconstructed radiograph comprising the one or more anatomical elements.

9. The system (100) of any of claims 1 to 8, wherein: the captured image (205) comprises a computed tomography (CT) image; and the simulated multidimensional image (235) comprises a cone beam computed tomography (CBCT) image comprising the one or more anatomical elements.

10. The system (100) of any of claims 1 to 9, wherein the captured image (205) comprises a preoperative multidimensional image.

11. A system (100) comprising: a processor (104); and a memory (106) storing data thereon that, when processed by the processor (104), cause the processor (104) to: generate, based on a reference image associated with a medical condition and comprising one or more anatomical elements, a deformation image (225) comprising the one or more anatomical elements;generate a simulated multidimensional image (235) of the one or more anatomical elements based on the deformation image (225); generate a second deformation image (225) in association the medical condition, based on: a captured image (205) comprising one or more target anatomical elements; and a learning model trained based at least in part on the reference image, the deformation image (225), and the simulated multidimensional image (235); and generate a second simulated multidimensional image (235) in association with the medical condition, based on the second deformation image (225) and the learning model.

12. The system (100) of claim 11, wherein the data is further executable by the processor (104) to: apply a deformation field associated with profile information comprised in the learning model to the one or more target anatomical elements in the captured image (205), wherein the profile information is associated with the medical condition, wherein generating the second deformation image (225) is based on applying the deformation field.

13. The system (100) of any of claims 11 or 12, wherein the data is executable by the processor (104) to train the learning model in association with at least the medical condition based on: a first training dataset comprising at least the reference image; a second training dataset comprising at least the deformation image (225) and the second deformation image (225); and a third training dataset comprising at least the simulated multidimensional image (235) and the second simulated multidimensional image (235).

14. The system (100) of any of claims 11 to 13, wherein the simulated multidimensional image (235) comprises a digitally reconstructed radiograph or a cone beam computed tomography (CBCT) image.

15. A method comprising: generating a transformation of a multidimensional bone model (210, 211), wherein:the multidimensional bone model (210, 211) corresponds to one or more anatomical elements comprised in a captured image (205) of a subject; and the transformation comprises a non-rigid transformation of at least a portion of the multidimensional bone model (210, 211); generating a deformation image (225) comprising the one or more anatomical elements based on the transformation and the captured image (205); and generating a simulated multidimensional image (235) of the one or more anatomical elements based on the deformation image (225).

Images