Mesh Topology Adaptation

Abstract

Concepts are presented for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. One such concept includes identifying a correspondence between the first mesh topology and the second mesh topology based on spectral matching of the first mesh topology and the second mesh topology. The first predefined mesh topology is aligned with the second mesh topology based on the identified correspondence between the first and second mesh topologies.

Description

[Technical Field]

[0001] The present invention relates to the field of mesh topologies, and more particularly to adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. [Background technology]

[0002] Annotated medical images are widely used in scientific or medical research, e.g., for evaluating and training image segmentation techniques. A common segmentation technique is model-based segmentation (MBS). This technique allows a triangular mesh representing organ boundaries to be adapted to a medical image in a controlled manner so that the general organ shape is preserved, thus regularizing the segmentation with respect to prior anatomical knowledge. This segmentation model must be trained using image data of the segmented organs and the corresponding ground truth meshes. Typically, these meshes are created manually by clinicians or researchers. However, this manual process is very time-consuming. Summary of the Invention [Problem to be solved by the invention]

[0003] The process of generating a ground truth mesh can be accelerated by utilizing an existing model developed for the same organ, where the existing model was previously trained on similar image data. Alternatively, a basic ground truth mesh of the organ may already be available, which may have been previously delineated by a clinician with respect to another segmentation model. In either case, the topology of the available ground truth mesh (either from a prior segmentation or a different model) may not match the existing model topology (e.g., the number of vertices and triangles may not match), and in the case of model-based segmentation, the mesh must usually have the same topology.

[0004] One way to obtain organ meshes in the same topology is to find the correspondence between the vertices of two different meshes, which could be provided by well-known point matching methods such as iterative closest point (ICP) or coherent point drift (CPD). However, these methods consider a global transformation in feature space between the two shapes, but require that spatial regularities be built into the mapping so that adjacent points of one mesh correspond to adjacent points of the other mesh. [Means for solving the problem]

[0005] The invention is defined by the claims.

[0006] By way of example according to aspects of the present invention, there is provided a method of adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ, the method comprising: identifying a correspondence between the first and second mesh topologies based on spectral matching of the first and second mesh topologies; and aligning the first predefined mesh topology with the second mesh topology based on the identified correspondence between the first and second mesh topologies.

[0007] The proposed embodiments provide a concept for adapting a first predefined mesh topology to a second, different mesh topology. For example, the embodiments can be used to adapt a first ground truth mesh of an organ to a second, new mesh topology of the organ. In particular, the embodiments can use spectral matching to align / adapt the first predefined (i.e., ground truth) mesh to the second, new mesh topology. As an alternative, it is proposed to use spectral matching to align an already existing mesh to a new topology of the same organ. Such an approach helps reduce the requirements for annotated datasets.

[0008] As an example, the proposed embodiment can provide a method that uses spectral matching to find correspondence between an already existing mesh topology (e.g., obtained either from segmentation using a pre-trained model or from prior ground truth mesh generation by the user) and a newly defined mesh topology. In this way, it is possible to define correspondence between meshes of organs with different topologies, since direct vertex correspondence between the two meshes is not required for transformation to spectral space. Furthermore, such a proposed approach can guarantee spatial regularity through the use of spectral embedding (e.g., calculated from the Laplacian of the graph of the surface mesh).

[0009] Embodiments can be based on the idea of ​​using spectral matching to align an already existing mesh with a new topology of the same organ. In such embodiments, it is proposed to use spectral matching to find the correspondence between the already existing mesh topology and the newly defined mesh topology. This may allow for the transformation of a predefined ground truth mesh into a new desired mesh topology for the model, which can then be retrained for segmentation.

[0010] As an example, identifying a correspondence between a first mesh topology and a second mesh topology based on spectral matching of the first mesh topology and the second mesh topology can include obtaining a first spectral graph derived from the first mesh topology, obtaining a second spectral graph derived from the second mesh topology, decomposing the first and second spectral graphs to determine spectral coordinates from the first and second spectral graphs, analyzing the determined spectral coordinates to identify matches between the first and second spectral graphs, and identifying a correspondence between the first and second mesh topologies based on the identified matches. Accordingly, implementations can use conventional / known spectral graph generation and / or matching processes that leverage widely known and / or available processes.

[0011] In some embodiments, aligning the first predefined mesh topology with the second mesh topology can include aligning spectral components of the first and second mesh topologies. For example, aligning spectral components can include processing the first mesh topology with respect to both meshes by a point transformation method, such as a Coherent Point Drift (CPD) method or an Iterative Nearest Point (ICP) method. Thus, known point matching methods can be used, thereby reducing, for example, the complexity and / or cost of the implementation.

[0012] In an exemplary embodiment, aligning the first predefined mesh topology with the second mesh topology may include resampling the first mesh topology based on the identified correspondence between the first mesh topology and the second mesh topology.

[0013] It will be appreciated that embodiments of the present invention can be exploited for use in image segmentation, as the proposed concepts may allow for transforming a predefined ground truth mesh into a new desired mesh topology of a model, which can then be retrained for segmentation. Thus, according to another aspect of the present invention, there is provided a method for segmenting medical images of an organ, comprising the steps of adapting a first mesh topology representing the organ to a second, different mesh topology of the organ, and performing a model-based segmentation of the image using the adapted first mesh topology, according to proposed embodiments.

[0014] According to another aspect, there is provided a computer program product for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ, the computer program product having a computer readable storage medium having computer readable program code embodied therein, the computer readable program code being configured to perform all of the steps of the proposed embodiments.

[0015] Thus, there may further be provided a computer system comprising a computer program product according to the proposed embodiments and one or more processors adapted to perform methods according to the proposed concepts by execution of the computer readable program code of said computer program product.

[0016] According to yet another aspect of the present invention, there is provided a system for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ, the system having an analysis component configured to identify a correspondence between the first and second mesh topologies based on spectral matching of the first and second mesh topologies, and a mesh alignment component configured to align the first predefined mesh topology with the second mesh topology based on the identified correspondence between the first and second mesh topologies.

[0017] The system may be located remotely from a user device to adapt a first mesh topology to a second, different mesh topology. In this manner, a user (e.g., a medical professional) may have a suitably located system that can receive information remotely from the system to adapt a first mesh topology to a second, different mesh topology. Thus, embodiments may enable a user to adapt a first mesh topology to a second, different mesh topology using a local system (which may include, for example, a laptop, tablet computer, mobile phone, PDA, or other portable display device). By way of example, embodiments may provide an application for a mobile computing device, where the application may be executed and / or controlled by a user of the mobile computing device.

[0018] The system may further comprise a server device having a system for adapting a first mesh topology to a second, different mesh topology, and a client device having a user interface. Thus, dedicated data processing means may be used for the purpose of adapting the first mesh topology to the second, different mesh topology, thereby reducing the processing requirements or capabilities of other components or devices of the system.

[0019] The system may further comprise a client device, which comprises a mesh alignment component and a display unit. In other words, a user (such as a doctor or medical professional) may have a suitably configured client device (such as a laptop, tablet computer, mobile phone, PDA, etc.) that processes the received data in order to adapt a first mesh topology to a second, different mesh topology and generate display control signals. Thus, purely by way of example, embodiments may provide a mesh-based annotation system that enables medical analysis of one or more subjects (e.g., patients) from a single remote location, where communication between the subjects and a monitoring user (e.g., a nurse or doctor) is provided, such communication being able to extend or modify its functionality, for example, in accordance with the proposed concepts.

[0020] It will therefore be appreciated that processing power may be distributed throughout the system in different manners according to processing resource availability and / or predetermined constraints.

[0021] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter.

[0022] For a better understanding of the present invention and to show more clearly how the same may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings in which: [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a simplified block diagram of a proposed embodiment of a system for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. [Figure 2] 1 is a simplified flow diagram of a proposed embodiment of a method for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. [Figure 3]FIG. 1 is a simplified block diagram of a computer that can use one or more portions of the embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0024] The present invention will now be described with reference to the drawings.

[0025] It should be understood that the detailed description and specific examples, while indicating exemplary embodiments of the devices, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects and advantages of the devices, systems and methods of the present invention will become better understood from the following description, the appended claims and the accompanying drawings. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0026] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

[0027] It should be understood that the drawings are schematic only and are not drawn to scale, and that the same reference numerals will be used throughout the drawings to denote the same or similar parts.

[0028] An approach is proposed to enable adaptation of a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. Thus, embodiments can be used to translate a mesh from a first defined (e.g., ground truth with annotations) model space to another space. This may allow the ground truth annotations in the first model space to be used to train a new, different model (e.g., designed to solve a new problem).

[0029] Embodiments propose to use spectral matching to find correspondence between a first predefined (e.g., existing) mesh topology of an organ (obtained from segmentation of the organ using a pre-trained model or from prior ground truth mesh generation by a clinician) and a second (e.g., newly defined) mesh topology, which may thus enable the predefined ground truth mesh to be transformed into a new mesh topology of a model, which can then be retrained for segmentation.

[0030] Because spectral matching is widely known, a detailed discussion of spectral matching is omitted from this description. However, as a brief overview, the spectral decomposition of the Laplacian of a graph associated with a complex shape yields eigenfunctions (modes) that are invariant to isometry. Each vertex on a shape can be uniquely represented by the combination of eigenmode values ​​at each point, also called spectral coordinates. Spectral matching involves establishing point correspondences by pairing vertices on different shapes with the most similar spectral coordinates. Spectral graph theory thus provides a solution for matching surface meshes with different topologies in the spectral domain, and thus can have applications for matching different meshes to create atlases.

[0031] We propose to leverage spectral matching to incorporate predefined meshes into new model topologies. In this way, the proposed embodiment can enable the identification of correspondences between meshes of the same organ but with different topologies (e.g., the brain, heart, kidney, liver, or lungs of two different subjects / patients). In particular, due to the transformation to spectral space, direct vertex correspondences between meshes are not required. Furthermore, such an approach can guarantee spatial regularity, since it uses spectral embedding calculated, for example, from the Laplacian of the graph of the surface mesh.

[0032] Therefore, the proposed embodiment can be used for segmentation of medical images of organs. Such a method can include adapting a first mesh topology representing an organ to a second, different mesh topology of the organ according to the proposed embodiment. Model-based segmentation of the image can then be performed using the adapted first mesh topology. Thus, semi-automatic ground truth segmentation can be facilitated by the proposed concept. Using a pre-developed model can accelerate the process (since the user only needs to make minor modifications, rather than, for example, manually creating a new mesh). Furthermore, versatile data can be provided, e.g., which can be used for more projects where the same organ needs to be depicted with different topologies.

[0033] By way of example only, the exemplary embodiments may be utilized in many different types of clinical, medical or subject-related environments, such as hospitals, doctor's offices, medical research facilities, hospital wards, care homes, people's homes, etc.

[0034] To aid in understanding the proposed concepts, an exemplary embodiment of a system for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ will be described with reference to FIG. 1.

[0035] 1 is a simplified block diagram of a proposed embodiment. A proposed system 100 is configured to acquire (e.g., receive via an input interface) a first predefined mesh topology 110 representing an organ (e.g., the liver of a first subject). The system 100 is also adapted to acquire (e.g., receive via an input interface) a second, different mesh topology 120 of the organ (e.g., the liver of a second subject). The system is configured to adapt the first predefined mesh topology 110 to the second mesh topology 120. In other words, the system 100 is configured to translate a mesh from a first defined (e.g., annotated ground truth) model space to another space. This may enable the ground truth annotations of the first model space to be used to train a new, different model.

[0036] More specifically, the system 100 includes an analysis component 130 configured to perform spectral matching between the first mesh topology 110 and the second mesh topology 120 to identify a correspondence between the first mesh topology 110 and the second mesh topology 120. A mesh alignment component 135 of the system is also configured to align the first predefined mesh topology 110 with the second mesh topology 120 based on the correspondence between the first and second mesh topologies (identified by the analysis component 130).

[0037] The aligned mesh topology 140 is output from the system 100 (e.g., via an output interface), where the aligned mesh topology 140 is adapted to the second mesh topology 120. In this manner, annotations of the first mesh topology 110 are propagated to the aligned mesh topology 140, while also being aligned with the second mesh topology.

[0038] By way of further illustration and description, an exemplary method according to an embodiment will now be described with reference to FIG.

[0039] 2 is a simplified flow diagram of a proposed embodiment of a method 200 for adapting a first predefined mesh topology representing an organ to a second, different mesh topology of the organ. The method 200 comprises a first step 210 of identifying a correspondence between a first mesh topology and a second mesh topology based on spectral matching of the first and second mesh topologies. More specifically, the step 210 of identifying a correspondence between a first and second mesh topology based on spectral matching of the first and second mesh topologies comprises a step 220 of obtaining a first spectral graph derived from the first mesh topology and a step 230 of obtaining a second spectral graph derived from the second mesh topology. It should be noted here that the first and second spectral graphs can be obtained in any order. Furthermore, the step of obtaining a spectral graph can comprise a step of generating a spectral graph, or alternatively, simply receiving a generated spectral graph from an external component. After obtaining the first and second spectral graphs, identifying correspondence between the first and second mesh topologies step 210 further includes decomposing the first and second spectral graphs to determine spectral coordinates in step 235. In step 240, the spectral coordinates are analyzed to identify matches between the first and second spectral graphs. Based on the identified matches, correspondence between the first mesh topology and the second mesh topology is identified in step 250.

[0040] The method 200 then includes a second step 260 of aligning the first predefined mesh topology with the second mesh topology based on the identified correspondence between the first and second mesh topologies. Here, the step 260 of aligning the first predefined mesh topology with the second mesh topology includes aligning spectral components of the first and second mesh topologies. More specifically, in this exemplary embodiment, the step of aligning spectral components includes processing the first mesh topology with a point transformation method, such as a coherent point drift method or an iterative nearest neighbor (ICP) method. Alternatively, or additionally, the step of aligning the first predefined mesh topology with the second mesh topology can include resampling the first mesh topology based on the identified correspondence between the first and second mesh topologies.

[0041] From the above exemplary embodiments, it can be seen that the proposed concept can facilitate the generation of consistent mesh-based annotations for images using spectral matching. In particular, the proposed embodiments use spectral matching to find correspondences between already existing mesh topologies and newly defined mesh topologies. Instead of direct vertex correspondences, it is proposed to use a spectral embedding computed from the Laplacian of the graph of the surface mesh.

[0042] Therefore, a method is proposed that uses spectral matching to find correspondence between an already existing mesh topology (either obtained from organ segmentation using a pre-trained model or from prior ground truth mesh generation by a clinician) and a newly defined mesh topology. This can be achieved by using the spectral embedding of two shapes computed independently and looking for a match between the defined mesh (i.e., ground truth) and a template (i.e., new mesh topology). After a match is defined, the ground truth mesh can be resampled in the new topology. This is aided by spectral matching, which provides point-to-point mesh correspondence.

[0043] 3 illustrates an example of a computer 300 in which one or more portions of the embodiments can be used. The various processes described above can utilize the capabilities of the computer 300. For example, one or more portions of a system that provides a subject-specific user interface can be incorporated into any of the elements, modules, applications, and / or components described herein. In this regard, it should be understood that the system functional blocks can be executed on a single computer or distributed across several computers and locations (e.g., connected via the Internet).

[0044] Computer 300 may include, but is not limited to, a PC, workstation, laptop, PDA, palm device, server, storage, etc. Generally, with respect to hardware architecture, computer 300 may include one or more processors 310, memory 320, and one or more I / O devices 370 communicatively coupled via a local interface (not shown). The local interface may be, for example, but not limited to, one or more buses or other wired or wireless connections, as known in the art. The local interface may have additional elements, such as controllers, buffers (caches), drivers, repeaters, receivers, etc., to enable communication. Additionally, the local interface may have address, control, and / or data connections to enable appropriate communication between the aforementioned components.

[0045] Processor 310 is a hardware device that executes software that may be stored in memory 320. Processor 310 may be virtually any custom or commercially available processor, central processing unit (CPU), digital signal processor (DSP), or coprocessor of any number of processors associated with computer 300, and processor 310 may also be a semiconductor-based microprocessor (in the form of a microchip) or microprocessor.

[0046] Memory 320 may include any one or combination of non-volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM)), and non-volatile memory elements (e.g., ROM, erasable programmable read-only memory (EPROM), electronically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), tape, compact disc read-only memory (CD-ROM), disk, diskette, cartridge, cassette, etc.). Furthermore, memory 320 may incorporate electronic, magnetic, optical, and / or other types of storage media. It should be noted that memory 320 may have a distributed architecture, where various components are located remotely from one another but are accessible by processor 1.

[0047] The software in memory 320 may include one or more separate programs, each having an ordered list of executable instructions for implementing logical functions. According to an exemplary embodiment, the software in memory 320 includes a suitable operating system (O / S) 350, a compiler 340, source code 330, and one or more applications 360. As shown, application 360 includes multiple functional components for implementing the features and operations of the exemplary embodiments. While application 360 of computer 300 may represent various applications, computational units, logic, functional units, processes, operations, virtual entities, and / or modules according to an exemplary embodiment, application 360 is not meant to be limiting.

[0048] Operating system 350 controls the execution of other computer programs and provides scheduling, input / output control, file and data management, memory management, and communication control and related services. It is contemplated by the inventors that application 360 implementing an exemplary embodiment may be applicable to all commercially available operating systems.

[0049] Application 360 may be a source program, an executable program (object code), a script, or any other entity comprising a set of instructions to be executed. In the case of a source program, the program is typically translated via a compiler (such as compiler 340), assembler, interpreter, etc., which may or may not be included in memory 320 so that it operates properly in conjunction with O / S 350. Furthermore, application 360 may be written in an object-oriented programming language, which has classes of data and methods, or a procedural programming language, such as, but not limited to, C, C++, C#, Pascal, BASIC, API calls, HTML, XHTML, XML, ASP script, JavaScript, FORTRAN, COBOL, Perl, Java, ADA, .NET, etc.

[0050] I / O devices 370 may include input devices such as, but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Additionally, I / O devices 370 may include output devices such as, but not limited to, a printer, display, etc. Finally, I / O devices 370 may also include devices for communicating both input and output, such as, but not limited to, a network interface card or modulator / demodulator (for accessing remote devices, other files, devices, systems, or networks), radio frequency (RF) or other transceivers, telephone interfaces, bridges, routers, etc. I / O devices 370 may also include components for communicating over various networks, such as the Internet or an intranet.

[0051] If computer 300 is a PC, workstation, or other intelligent device, the software in memory 320 may further include a basic input / output system (BIOS) (omitted for simplicity). The BIOS is a set of essential software routines that initializes and tests hardware at power-on, starts O / S 350, and supports data transfers between hardware devices. The BIOS is stored in some type of read-only memory, such as ROM, PROM, EPROM, EEPROM, etc., so that the BIOS can be executed when computer 300 is powered on.

[0052] When computer 300 is operating, processor 310 is configured to execute software stored in memory 320, communicate results to and from memory 320, and generally control the operation of computer 300 in accordance with the software. Applications 360 and O / S 350 are read in whole or in part by processor 310, possibly buffered within processor 310, and then executed.

[0053] It should be noted that if application 360 is implemented in software, application 360 can be stored on virtually any computer-readable medium for use by or in connection with any computer-related system or method. In the context of this specification, a computer-readable medium can be an electronic, magnetic, optical, or other physical device or means that can contain or store a computer program for use by or in connection with a computer-related system or method.

[0054] Application 360 may be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system capable of fetching instructions from and executing instructions on an instruction execution system, apparatus, or device). In the context of this specification, a "computer-readable medium" may be any means that can store, communicate, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0055] The present invention may be a system, a method and / or a computer program product. The computer program may include a computer-readable storage medium having computer-readable program instructions for causing a processor to perform the method of the present invention.

[0056] A computer-readable storage medium may be a tangible device capable of retaining and storing instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes portable computer diskettes, hard disks, random access memories, read-only memories, erasable programmable read-only memories, static random access memories, portable compact disk read-only memories, digital versatile disks, memory sticks, floppy disks, mechanically encoded devices such as punch cards, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be construed as being a transitory signal itself, such as an electric wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., light pulses passing through a fiber optic cable), or an electrical signal transmitted through a wire.

[0057] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium into each computing / processing device, or can be downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing / processing device.

[0058] The computer-readable program instructions for carrying out the operations of the present invention may be either source code or object code written in any combination of one or more programming languages, including assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or object-oriented programming languages ​​such as Smalltalk, C++, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter situation, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of the present invention.

[0059] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0060] A single processor or other unit may fulfill the functions of several items recited in the claims.

[0061] The computer program may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0062] These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions can also be stored on a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, such that a computer-readable storage medium having instructions stored therein includes a product containing instructions that implement aspects of the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0063] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of processing steps to be executed on the computer, other programmable apparatus, or other device to generate a computer-implemented process, whereby the instructions executing on the computer, other programmable apparatus, or other device perform the functions / acts specified in the flowcharts and / or one or more blocks of the block diagrams.

[0064] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, or portion of instructions, comprising one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the blocks may be executed in an order different from that noted in the figures. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may be executed in the reverse order, depending on the functionality involved. Furthermore, it should be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a special-purpose hardware-based system that performs the specified functions or processes or executes a combination of special-purpose hardware and computer instructions.

Claims

1. 1. A computer-implemented method for aligning a predefined first mesh topology representing an organ to a different second mesh topology of said organ, the method comprising: identifying a correspondence between the first mesh topology and the second mesh topology based on spectral matching between the first mesh topology and the second mesh topology; aligning the first mesh topology with the second mesh topology based on the identified correspondence between the first mesh topology and the second mesh topology; and aligning the first mesh topology with the second mesh topology; resampling the first mesh topology based on the identified correspondence between the first mesh topology and the second mesh topology.

2. the step of identifying a correspondence between the first mesh topology and the second mesh topology based on spectral matching of the first mesh topology and the second mesh topology, obtaining a first spectral graph derived from the first mesh topology; obtaining a second spectral graph derived from the second mesh topology; decomposing the first and second spectral graphs to determine spectral coordinates from the first and second spectral graphs; analyzing the determined spectral coordinates to identify matches between the first and second spectral graphs; identifying a correspondence between the first mesh topology and the second mesh topology based on the identified match; 2. The method of claim 1, comprising:

3. aligning the first mesh topology with the second mesh topology; 3. The method of claim 1, further comprising aligning spectral components of the first mesh topology and the second mesh topology.

4. aligning the spectral components The method of claim 3 , further comprising processing the first mesh topology with a point transformation method.

5. The method of claim 4 , wherein the point transformation method comprises a coherent point drift method.

6. A method for segmenting a medical image of an organ, comprising:

6. Aligning a first mesh topology representing an organ to a different second mesh topology of said organ according to the method of any one of claims 1 to 5; performing a model-based segmentation of the medical image using the aligned first mesh topology; A method having the following.

7. A computer program having a computer program code for performing the method according to any one of claims 1 to 6 when the computer program is run on a computer.

8. 1. A system for aligning a predefined first mesh topology representing an organ to a different second mesh topology of said organ, comprising: an analysis component configured to identify a correspondence between the first mesh topology and the second mesh topology based on spectral matching between the first mesh topology and the second mesh topology; a mesh alignment component configured to align the first mesh topology with the second mesh topology based on the identified correspondence between the first mesh topology and the second mesh topology; and the mesh alignment component further comprising a resampling component configured to resample the first mesh topology based on the identified correspondence between the first mesh topology and the second mesh topology. system.

9. the analysis component further comprising a spectral graph component configured to obtain a first spectral graph derived from the first mesh topology and to obtain a second spectral graph derived from the second mesh topology; 10. The system of claim 8, wherein the analysis component is further configured to: decompose the first and second spectral graphs to determine spectral components; identify matches between the first and second spectral graphs based on the determined spectral components; and identify correspondences between the first and second mesh topologies based on the identified matches.

10. The system of claim 8 or 9, wherein the mesh alignment component is configured to align spectral components of the first and second mesh topologies.

11. The system of claim 10 , wherein the mesh alignment component comprises a point transformation component configured to process the first mesh topology through a point transformation method.

12. The system of claim 11 , wherein the point transformation method comprises a coherent point drift method.

13. 1. A system for segmenting medical images of organs, comprising: A system according to any one of claims 8 to 12; a segmentation component configured to perform a model-based segmentation of the image using the aligned first mesh topology; A system having:

Images