Visual display for tendon sheath tear diagnosis

Abstract

This invention relates to a visual display for diagnosing tendon sheath tears. A system and method are provided for visually displaying one or more anatomical objects. The process involves receiving one or more 3D medical images of one or more anatomical objects from a patient. A correspondence is determined between the one or more 3D medical images and points on a 2D graph representing the one or more anatomical objects. The 2D graph is updated using patient information extracted from the one or more 3D medical images. The updated 2D graph with the determined correspondences is output.

Description

Technical Field

[0001] This invention generally relates to intuitive display systems and methods, and particularly to intuitive displays for the diagnosis of tendon sleeve tears. Background Technology

[0002] The girdle is a group of muscles and tendons that surround the shoulder joint, holding the humeral head in the scapular region. Girdle tears are one of the most common causes of shoulder pain. In current clinical practice, MRI (magnetic resonance imaging) is considered the standard of care for girdle assessment and treatment planning. Currently, the interpretation of MRI images is performed manually by radiologists who scroll through numerous MRI images to detect girdle tears and measure or estimate the size of any detected tears. However, this manual interpretation of MRI images can be complex and time-consuming, requiring the analysis of several image sequences acquired in different imaging planes. For example, measuring girdle tears in two dimensions across different imaging planes. Recently, artificial intelligence-based methods have been proposed for the automated diagnosis and measurement of girdle tears. While these AI-based methods can improve the speed of MRI image interpretation, the discovery of AI-based methods requires manual validation by the user. Summary of the Invention

[0003] According to one or more embodiments, a system and method are provided for visually displaying one or more anatomical objects. The system receives one or more 3D medical images of one or more anatomical objects from a patient. It determines a correspondence between the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects. It outputs an updated 2D map having the determined correspondence.

[0004] In one embodiment, a correspondence is determined between 2D slices of the one or more 3D medical images and points on the 2D image. In another embodiment, a correspondence is determined between locations in the one or more 3D medical images and points on the 2D image. In one embodiment, user input is received to select one of the points on the 2D image, and in response to receiving the user input, one or more 2D slices of the one or more 3D medical images corresponding to the selected point are displayed based on the determined correspondence.

[0005] In one embodiment, the correspondence between one or more 3D medical images and points on the 2D image is determined based on user input. In another embodiment, the correspondence between one or more 3D medical images and points on the 2D image is determined by automatically identifying landmarks in one or more 3D medical images using a trained machine learning network and associating the automatically identified landmarks with points on the 2D image. In another embodiment, the correspondence between one or more 3D medical images and points on the 2D image is determined by creating an atlas of one or more anatomical objects, annotating the atlas with anatomical features corresponding to anatomical features in the 2D image, and registering the annotated atlas with one or more 3D medical images. In yet another embodiment, the correspondence between one or more 3D medical images and points on the 2D image is determined by creating an atlas of one or more anatomical objects, annotating the atlas with anatomical features corresponding to anatomical features in the 2D image, segmenting one or more anatomical structures from one or more 3D medical images and from the annotated atlas, and registering the annotated atlas with one or more 3D medical images based on the segmented anatomical structures from one or more 3D medical images and the segmented anatomical structures from the annotated atlas.

[0006] In one embodiment, one or more anatomical objects are associated with a patient's tendon sleeve. A 2D diagram may represent one or more muscles of the tendon sleeve in an extended state. In one embodiment, a trained machine learning network is used to automatically determine the muscle mass of one or more muscles of the tendon sleeve from the one or more 3D medical images, and the one or more muscles are represented in the 2D diagram based on the automatically determined muscle mass. In one embodiment, a trained machine learning network is used to automatically determine the location and size of tears in the muscles of the tendon sleeve from the one or more 3D medical images, and the tears in the muscles are represented in the 2D diagram based on the automatically determined location and size of the tears. The 2D diagram may also include text labels identifying structures of one or more anatomical objects.

[0007] These and other advantages of the present invention will become apparent to those skilled in the art from the following detailed description and accompanying drawings. Attached Figure Description

[0008] Figure 1 A method for generating a 2D diagram representing one or more anatomical objects is illustrated according to one or more embodiments;

[0009] Figure 2 Exemplary 2D diagrams of patient tendon sleeves according to one or more embodiments are shown; and

[0010] Figure 3A high-level block diagram is shown that can be used to implement one or more embodiments of a computer. Detailed Implementation

[0011] This invention generally relates to a visual display for the diagnosis of tendon sleeve tears. Embodiments of the invention are described herein to provide a visual understanding of such methods and systems. Digital images typically consist of digital representations of one or more objects (or shapes). The digital representations of objects are generally described herein in terms of identifying and manipulating them. Such manipulation is a virtual manipulation performed in the memory or other circuitry / hardware of a computer system. Therefore, it is to be understood that embodiments of the invention can be performed within a computer system using data stored within it.

[0012] The embodiments described herein provide a visual display for diagnosing tendon sleeve tears by generating a 2D (two-dimensional) map representing a patient's tendon sleeve. Correspondences between points on the 2D map and one or more 3D (three-dimensional) images of the patient are determined, allowing a user (e.g., a radiologist or clinician) to interact with the 2D map to view relevant 2D slices. The 2D map also illustrates various information of interest, such as anatomical landmarks, tears in the tendon sleeve muscle, and muscle mass of the tendon sleeve muscle, which can be automatically determined using a machine learning-based network. Advantageously, the 2D map representing the tendon sleeve according to the embodiments described herein significantly reduces the time required for the user to validate automatically determined findings by the machine learning-based network. Furthermore, the 2D map efficiently presents findings to the user and provides information of interest that can reduce errors in diagnosis.

[0013] Figure 1 A method 100 for generating 2D diagrams representing one or more anatomical objects is illustrated according to one or more embodiments. The steps of method 100 may be performed by one or more suitable computing devices, such as… Figure 3 The computer 302 executes.

[0014] In step 102, one or more 3D medical images of one or more anatomical objects of the patient are received. In one embodiment, the one or more anatomical objects include anatomical objects of interest associated with the patient's tendon sleeve, such as, for example, muscles and tendons associated with the tendon sleeve (e.g., supraspinatus, infraspinatus, teres minor, and subscapularis), bones coupled to these muscles and tendons (e.g., humerus and scapula), and any other anatomical objects of interest associated with the tendon sleeve. However, it should be understood that the one or more anatomical objects may include other organs, bones, blood vessels, or any other suitable anatomical structures of the patient.

[0015] 3D medical images can include multiple 3D medical images acquired using different acquisition parameters and / or different imaging planes. Each 3D medical image includes multiple 2D slices depicting a cross-section of the 3D medical image. In one embodiment, the 3D medical image includes an MRI (Magnetic Resonance Imaging) image. However, the input image can have any other suitable modality, such as, for example, CT (Computed Tomography), US (Ultrasound), or any other modality or combination of modalities. 3D medical images can be acquired directly from the image acquisition device (e.g., during image acquisition). Figure 3 Image acquisition devices 314) such as MRI scanners can receive images, or images can be received by loading previously acquired images from storage devices or memory of a computer system or by receiving images from a remote computer system.

[0016] In step 104, a correspondence is determined between one or more 3D medical images and points on a 2D diagram representing one or more anatomical objects. The 2D diagram may be a symbolic representation of the anatomical object for user comprehension. For example, in the case where the anatomical object is an object of interest associated with a patient's tendon sleeve, the 2D diagram may include 2D representations of the supraspinatus, infraspinatus, teres minor, and subscapularis muscles of the tendon sleeve coupled between the humerus and scapula. In one embodiment, the supraspinatus, infraspinatus, teres minor, and subscapularis muscles are depicted in a 2D unfolded state in the 2D diagram, the 2D unfolded state being based on the 3D medical image using any suitable (e.g., known) technique.

[0017] The correspondence associates a 3D medical image with one or more points on a 2D graph. In one example, the correspondence associates one or more 2D slices of the 3D medical image with corresponding points in the 2D graph. In another example, the correspondence associates a location in the 3D medical image (i.e., a location in a 2D slice) with a corresponding location in the 2D graph. The points on the 2D graph can be any suitable point.

[0018] In one embodiment, a correspondence between one or more 3D medical images and points on a 2D map is determined based on user input. For example, a user can select a point on a 2D map, navigate to one or more 2D slices depicting the corresponding location of the selected point, and select one or more 2D slices or the corresponding location of the selected point on one or more 2D slices.

[0019] In another embodiment, a trained machine learning network is used to automatically determine the correspondence between one or more 3D medical images and points on a 2D map. For example, the trained machine learning network can be trained using annotated training data (during a previous offline or training phase) to automatically identify anatomically significant landmarks in the 3D medical images. Anatomically significant landmarks could be, for example, the insertion points of muscles where tendons attach to the humerus and scapula. The automatically identified landmarks in the 3D medical images are associated with 2D points on the 2D map. Other points in the 2D map are associated with their locations in the 3D medical images through linear interpolation. Specifically, for a given point in the 2D map, a triangle can be formed by its three nearest neighbors, and the interpolation weights can be the centroid coordinates in the 3D medical image.

[0020] In another embodiment, a correspondence between one or more 3D medical images and points on a 2D map is determined by creating an atlas of one or more anatomical objects (e.g., using an averaged 3D dataset). The atlas is then annotated with anatomical features corresponding to the anatomical features in the 2D map. The annotated atlas is then registered with the patient's 3D medical images (e.g., 3D affine or deformable registration) to establish the correspondence between the 2D and 3D medical images.

[0021] In another embodiment, a correspondence between one or more 3D medical images and points on the 2D map is determined by creating an atlas of one or more anatomical objects (e.g., using an average 3D dataset) and annotating the atlas with anatomical features corresponding to those in the 2D map, as described above. Anatomical structures are then segmented from the 3D medical images and the annotated atlas. For example, the supraspinatus, infraspinatus, teres minor, and subscapularis muscles can be segmented from the 3D medical images and the annotated atlas using a trained machine learning network. The annotated atlas is then registered with the patient's 3D medical images based on the segmented anatomical structures to establish a correspondence between the 2D and 3D medical images.

[0022] In one embodiment, an initial correspondence may be determined (e.g., according to embodiments described herein, such as automatically identifying anatomically significant landmarks using an artificial intelligence system based on user input by registering an annotated atlas with 3D medical images (e.g., 3D affine or deformable registration or segmentation-based registration, as described above), and the initial correspondence may be iteratively refined based on user input to determine correspondences between points on one or more 3D medical images and 2D maps. For example, a user may iteratively refine the initial correspondence for any number of iterations to adjust the corresponding positions on 2D slices of 3D medical images or on 2D maps.

[0023] In step 106, the 2D graph is updated using patient information extracted from one or more 3D medical images. Patient information may include anatomical landmarks identified in the one or more 3D medical images, muscle mass determined from the one or more 3D medical images (e.g., Goutallier score), muscle tears determined from the one or more 3D medical images, or any other information of interest to the patient determined from the one or more 3D medical images. This patient information facilitates the user's interpretation of the 2D graph.

[0024] Figure 2 An exemplary 2D diagram 200 illustrates a patient's tendon sleeve updated using patient information extracted from 3D medical images, according to one or more embodiments. Figure 2 As shown, 2D Figure 200 includes a 2D representation of the supraspinatus 202-A, infraspinatus 202-B, teres minor 202-C, and subscapularis 202-D (collectively referred to as muscles 202) of the tendon sleeve coupled between the humerus 206 and the scapula 204 in an extended state. 2D Figure 200 depicts various patient information associated with the patient's tendon sleeve extracted from 3D medical images.

[0025] In one embodiment, various patient information may be depicted by text markers 210-A, 210-B, 210-C, and 210-D, respectively identifying the supraspinatus 202-A, infraspinatus 202-B, teres minor 202-C, and subscapularis 202-D (or any other relevant anatomical landmarks or structures). Various patient information may also be depicted by text markers 210-E and 210-F, respectively identifying posterior and anterior anatomical locations (or any other relevant anatomical locations). Various patient information may also be described by text marker 210-G, which identifies the tendon sleeve as belonging to the patient's right shoulder. In one embodiment, various patient information may be depicted by an avatar 212 identifying the patient's orientation.

[0026] In one embodiment, the various patient information depicted in 2D Figure 200 includes patient information automatically determined using artificial intelligence-based or machine learning-based networks. In one example, a trained machine learning network can be used to automatically determine the muscle mass of muscle 202, such as, for example, a Gutalier score. Muscle 202 can be represented in 2D Figure 200 based on muscle mass. For example, muscle 202 can be color-coded in 2D Figure 200 based on automatically determined muscle mass, or it can be represented in 2D Figure 200 using a pattern corresponding to the automatically determined muscle mass. In another example, a trained machine learning network can be used to automatically determine the location and size of tears 208-A and 208-B in muscle 202. The automatically determined locations of tears 208-A and 208-B are represented as straight lines at approximate locations of the tears in muscle 202 in 2D Figure 200. Figure 2 As shown, tear 208-A is depicted as a partial tear that does not extend through the supraspinatus muscle 202-A, while tear 208-B is depicted as a complete tear that extends through the subscapularis muscle 202-D. The automatically determined sizes (e.g., small, medium, large, or giant) of tears 208-A and 208-B are represented on 2D graph 200 by, for example, color-coding tears 208-A and 208-B based on their automatically determined tear sizes, or representing tears 208-A and 208-B using patterns corresponding to their automatically determined tear sizes. Other patient information automatically determined using a trained machine learning network can also be represented in the 2D graph. The trained machine learning network utilized herein can be any suitable machine learning network (e.g., neural network, support vector machine, decision tree, Bayesian network, etc.) implemented according to any suitable (e.g., known) technique. The trained machine learning network is trained during a prior offline or training phase and, once trained, is applied during an online or testing phase to automatically determine various patient information.

[0027] 2D graph 200 includes multiple points of interest 214. In Figure 2 In this context, point 214 of interest is the insertion point where muscle 202 attaches to humerus 206 and / or scapula 204. However, point 214 of interest can be any other point of interest, such as, for example, a user-selected point, an anatomically significant point, etc. Point 214 of interest can be a point on a 2D diagram, at which point... Figure 1 Step 104 determines the correspondence between one or more 3D medical images.

[0028] In step 108, an updated 2D graph with the determined correspondence is output. For example, the updated 2D graph with the determined correspondence can be output by displaying the updated 2D graph with the determined correspondence on a display device of a computer system, storing the updated 2D graph with the determined correspondence on a memory or storage device of a computer system, or by sending the updated 2D graph with the determined correspondence to a remote computer system.

[0029] In one embodiment, an updated 2D map with a determined correspondence is presented to the user to, for example, assess a tendon tear or validate automatically determined findings (e.g., tear location, tear size, muscle mass, etc.) by a trained machine learning network. The user can interact with the updated 2D map by selecting points on it. In one example, user input to select a point on the 2D map is received, and in response to receiving the user input, one or more 2D slices of a 3D medical image corresponding to the selected point according to the determined correspondence are presented to the user. In another example, user input to select a point on the 2D map is received, and in response to receiving the user input, the location in one or more 3D medical images corresponding to the selected point according to the determined correspondence (e.g., a location identified in a 2D slice of one or more 3D medical images) is presented to the user.

[0030] The embodiments described herein relate to the claimed system and the claimed method. Features, advantages, or alternative embodiments described herein may be assigned to other claims, and vice versa. In other words, the system claims may be improved using features described or claimed in the context of the method. In this case, the functional characteristics of the method are embodied by the target unit providing the system.

[0031] The systems, apparatus, and methods described herein can be implemented using digital circuitry or using one or more computers that employ known computer processors, memory units, storage devices, computer software, and other components. Typically, a computer includes a processor for executing instructions and one or more memories for storing instructions and data. A computer may also include or be coupled to one or more mass storage devices, such as one or more disks, internal hard disks and removable disks, magneto-optical disks, optical disks, etc.

[0032] The systems, apparatus, and methods described herein can be implemented using computers operating in a client-server relationship. Typically, in such a system, the client computer is located remotely from the server computer and interacts via a network. The client-server relationship can be defined and controlled by computer programs running on the respective client and server computers.

[0033] The systems, apparatuses, and methods described herein can be implemented within a network-based cloud computing system. In such a system, a server or other processor connected to the network communicates with one or more client computers via the network. For example, a client computer may communicate with the server via a web browser application residing on and operating on the client computer. The client computer may store data on the server and access the data via the network. The client computer may send data requests or online service requests to the server via the network. The server may perform the requested service and provide data to one or more client computers. The server may also send data suitable for causing the client computer to perform a specified function (e.g., perform a calculation, display specified data on a screen, etc.). For example, the server may send data suitable for causing the client computer to perform one or more steps or functions of the methods and workflows described herein (including...). Figure 1 The methods and workflows described herein include requests for one or more of the following steps or functions. Figure 1 One or more of the steps or functions described herein may be executed by a server or by another processor in a web-based cloud computing system. Certain steps or functions of the methods and workflows described herein (including...) Figure 1 One or more of the steps in the process can be executed by a client computer in a web-based cloud computing system. The steps or functions of the methods and workflows described herein (including...) Figure 1 One or more of the steps can be performed by a server and / or by a client computer in any combination in a web-based cloud computing system.

[0034] The systems, apparatuses, and methods described herein can be implemented using a computer program product tangibly embodied in an information carrier (e.g., in a non-transitory machine-readable storage device) for execution by a programmable processor; and the methods and workflow steps described herein (including...) Figure 1 One or more of the steps or functions of a computer program can be implemented using one or more computer programs that can be executed by such a processor. A computer program is a set of computer program instructions that can be used directly or indirectly in a computer to perform an activity or produce a result. Computer programs can be written in any form of programming language (including compiled or interpreted languages) and can be deployed in any form (including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment).

[0035] Figure 3A high-level block diagram of an example computer 302, which can be used to implement the systems, apparatus, and methods described herein, is shown. Computer 302 includes a processor 304 operatively coupled to a data storage device 312 and a memory 310. Processor 304 controls this operation by executing computer program instructions that define the overall operation of computer 302. The computer program instructions may be stored in the data storage device 312 or other computer-readable medium and loaded into memory 310 when execution of the computer program instructions is desired. Therefore, Figure 1 The methods and workflow steps or functions can be defined by computer program instructions stored in memory 310 and / or data storage device 312, and controlled by processor 304 that executes the computer program instructions. For example, the computer program instructions can be implemented as computer executable code, which is programmed by those skilled in the art to perform... Figure 1 The methods and workflow steps or functions. Therefore, by executing computer program instructions, processor 304 executes... Figure 1 The computer 302 may also include one or more network interfaces 306 for communicating with other devices via a network. The computer 302 may also include one or more input / output devices 308 that enable a user to interact with the computer 302 (e.g., a monitor, keyboard, mouse, speakers, buttons, etc.).

[0036] Processor 304 may include both general-purpose and special-purpose microprocessors, and may be the sole processor of computer 302 or one of multiple processors. Processor 304 may include, for example, one or more central processing units (CPUs). Processor 304, data storage device 312 and / or memory 310 may include one or more application-specific integrated circuits (ASICs) and / or one or more field-programmable gate arrays (FPGAs), or be supplemented by one or more ASICs and / or one or more FPGAs, or incorporated into one or more ASICs and / or one or more FPGAs.

[0037] Data storage device 312 and memory 310 each include a tangible, non-transitory computer-readable storage medium. Data storage device 312 and memory 310 may each include high-speed random access memory, such as dynamic random access memory (DRAM), static random access memory (SRAM), dual data rate synchronous dynamic random access memory (DDR RAM), or other random access solid-state memory devices, and may include non-volatile memory, such as one or more disk storage devices such as internal hard disks and removable disks, magneto-optical disk storage devices, optical disk storage devices, flash memory devices, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), digital multifunction disc read-only memory (DVD-ROM), or other non-volatile solid-state storage devices.

[0038] Input / output device 308 may include peripheral devices such as printers, scanners, displays, etc. For example, input / output device 308 may include display devices (such as cathode ray tube (CRT) or liquid crystal display (LCD) monitors) for displaying information to a user, keyboards, and pointing devices such as mice or trackballs through which the user can provide input to computer 302.

[0039] Image acquisition device 314 can be connected to computer 302 to input image data (e.g., medical images) to computer 302. It is possible that image acquisition device 314 and computer 302 are implemented as a single device. It is also possible that image acquisition device 314 and computer 302 communicate wirelessly via a network. In one possible embodiment, computer 302 can be remotely located relative to image acquisition device 314.

[0040] Any or all systems and apparatus discussed herein may be implemented using one or more computers, such as computer 302.

[0041] Those skilled in the art will recognize that actual computer or computer system implementations can also have other structures and can include other components, and Figure 3 This is a high-level representation of some components of such a computer for illustrative purposes.

[0042] The foregoing detailed description is to be understood as illustrative and exemplary in every respect and not restrictive, and the scope of the invention disclosed herein should not be determined from this detailed description, but rather from the claims as interpreted in the full breadth permitted by patent law. It should be understood that the embodiments shown and described herein are merely illustrative of the principles of the invention, and various modifications can be made by those skilled in the art without departing from the scope and spirit of the invention. Various other combinations of features can be implemented by those skilled in the art without departing from the scope and spirit of the invention.

Claims

1. A method for visually displaying one or more anatomical objects, comprising: Receive one or more 3D medical images of one or more anatomical objects of the patient; The following steps are used to determine the correspondence between 2D slices of the one or more 3D medical images and points on 2D maps representing the one or more anatomical objects: An atlas of one or more anatomical objects is annotated using anatomical features corresponding to those in the 2D diagrams. Register the annotated atlas with the one or more 3D medical images to establish the correspondence; The 2D image is updated using patient information extracted from the one or more 3D medical images; Output an updated 2D graph with the defined correspondences; Receive user input to select one of the points on the 2D graph; as well as In response to receiving the user input, one or more 2D slices of the one or more 3D medical images corresponding to the selected point are displayed based on the determined correspondence.

2. The method according to claim 1, wherein, Determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects includes: Determine the correspondence between the locations in the one or more 3D medical images and the points on the 2D image.

3. The method according to claim 1, wherein, Determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects includes: Create the atlas of the one or more anatomical objects.

4. The method according to claim 1, wherein, Determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects includes: Segmenting one or more anatomical structures from the one or more 3D medical images and from the annotated atlas. The process of registering the annotated atlas with the one or more 3D medical images to establish the correspondence includes: registering the annotated atlas with the one or more 3D medical images based on the segmentation of the one or more anatomical structures from the one or more 3D medical images and the segmentation of the one or more anatomical structures from the annotated atlas.

5. The method according to claim 1, wherein, The one or more anatomical objects are associated with the patient's tendon sleeve, and the 2D diagram includes a 2D representation of one or more muscles of the tendon sleeve coupled between the humerus and scapula.

6. The method according to claim 1, wherein, The one or more anatomical objects are associated with the patient's tendon sleeve, and updating the 2D image using patient information extracted from the one or more 3D medical images includes: Using a trained machine learning network, the muscle mass of one or more muscles of the tendon sleeve is automatically determined from the one or more 3D medical images; and The one or more muscles are represented in the 2D diagram based on automatically determined muscle mass.

7. The method according to claim 1, wherein, The one or more anatomical objects are associated with the patient's tendon sleeve, and updating the 2D image using patient information extracted from the one or more 3D medical images includes: Using a trained machine learning network, the location and size of the tear in the muscle of the tendon sleeve are automatically determined from the one or more 3D medical images; and The tear in the muscle is represented in the 2D diagram based on the automatically determined location and size of the tear.

8. The method according to claim 1, wherein, The 2D diagram includes textual markers that identify the structures of the one or more anatomical objects.

9. An apparatus for visually displaying one or more anatomical objects, comprising: A component for receiving one or more 3D medical images of one or more anatomical objects of a patient; Components for determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects: A component for annotating an atlas of one or more anatomical objects using anatomical features corresponding to anatomical features in a 2D drawing, and A component for registering annotated atlases with one or more 3D medical images to establish the correspondence; Components for updating the 2D image using patient information extracted from the one or more 3D medical images; Components used to output an updated 2D graph with the defined correspondences; A component for receiving user input to select one of the points on the 2D graph; as well as A component for displaying one or more 2D slices of the one or more 3D medical images corresponding to the selected point based on a determined correspondence, in response to receiving the user input.

10. The apparatus according to claim 9, wherein, The components for determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects include: A component for determining the correspondence between a location in one or more 3D medical images and a point on the 2D image.

11. A non-transitory computer-readable medium storing computer program instructions that, when executed by a processor, cause the processor to perform operations, the operations including: Receive one or more 3D medical images of one or more anatomical objects of the patient; The following steps are used to determine the correspondence between 2D slices of the one or more 3D medical images and points on 2D maps representing the one or more anatomical objects: An atlas of one or more anatomical objects is annotated using anatomical features corresponding to those in the 2D diagrams. Register the annotated atlas with the one or more 3D medical images to establish the correspondence; The 2D image is updated using patient information extracted from the one or more 3D medical images; Output an updated 2D graph with the defined correspondences; Receive user input to select one of the points on the 2D graph; as well as In response to receiving the user input, one or more 2D slices of the one or more 3D medical images corresponding to the selected point are displayed based on the determined correspondence.

12. The non-transitory computer-readable medium according to claim 11, wherein, Determining the correspondence between 2D slices of the one or more 3D medical images and points on a 2D map representing the one or more anatomical objects includes: Create the atlas of the one or more anatomical objects.

13. The non-transitory computer-readable medium according to claim 11, wherein, Determining the correspondence between the one or more 3D medical images and points on 2D maps representing the one or more anatomical objects includes: Segmenting one or more anatomical structures from the one or more 3D medical images and from the annotated atlas. The process of registering the annotated atlas with the one or more 3D medical images to establish the correspondence includes: registering the annotated atlas with the one or more 3D medical images based on the one or more anatomical structures segmented from the one or more 3D medical images and the one or more anatomical structures segmented from the annotated atlas.

Images