Method and system for exporting brain atlas target data
By dividing brain data into regions and selecting target data, and automatically extracting subsets of brain maps, the problems of time-consuming and inaccurate processing in existing technologies are solved, enabling the rapid and accurate generation of personalized treatment data.
Patent Information
- Application Number
- CN202511486642.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-17
- Publication Date
- 2026-01-09
AI Technical Summary
In existing technologies, the complexity and high dimensionality of brain data from a single patient make it difficult for clinicians to quickly identify a subset of brain maps relevant to diagnosis or surgical planning, which is time-consuming and prone to errors.
By acquiring raw brain data, dividing it into regions and partitions, selecting target data, obtaining associated brain atlas data, and outputting associated data subsets, the system can automatically and quickly extract accurate brain atlas subsets.
It significantly reduces the time required to extract target data, improves accuracy and precision, and enables the rapid generation of precise data for personalized patient treatment.
Smart Images
Figure CN121306508A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the technical field of medical image processing and data analysis and processing, involving the combination of computer science, medical imaging technology and machine learning models, specifically involving a method and system for deriving target brain atlas data from selected brain data. Background Technology
[0002] Medical imaging (such as sMRI, fMRI, and DWI) plays a crucial role in modern medicine. It is used not only for disease diagnosis (such as brain tumors and neurodegenerative diseases) but also for surgical planning, treatment efficacy evaluation, and basic medical research. Especially in analyzing and processing brain image data, structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), or functional magnetic resonance imaging (fMRI) can be used. Specifically:
[0003] 1.1 sMRI (structural magnetic resonance imaging): used to obtain high-resolution anatomical images of the brain.
[0004] 1.2 fMRI (functional magnetic resonance imaging): used to study the functional activity of different regions of the brain.
[0005] 1.3 DWI (Diffusion-weighted imaging) and DTI (Diffusion tensor imaging): used to track nerve fibers in the brain and help understand neural connections.
[0006] Medical image data typically has the following characteristics:
[0007] 2.1 High Dimensionality: For example, fMRI data may contain multiple time frames, forming four-dimensional data (3D space + time).
[0008] 2.2 Complexity: Large data volume, and needs to meet specific formats and protocols (such as the DICOM standard).
[0009] 2.3 Clinical relevance: The image data needs to be able to support clinical analysis, such as brain functional connectivity analysis or nerve fiber tracing.
[0010] In practical applications, medical image data often faces the following problems: When processing data related to a patient's brain, the brain data of a single patient may be extremely complex and high-dimensional. For example, the correlation matrix of brain fMRI data may contain hundreds of thousands or millions of elements. Therefore, for clinicians, it may be very difficult to manually examine and analyze this data when planning surgery or diagnosing a patient's brain disease or mental disorder, and it is even more difficult to quickly identify problematic image elements.
[0011] As mentioned above, a set of brain data describing a single patient's brain is often very large and complex, making it difficult and time-consuming for clinical users to extract useful information from it. Therefore, there is an urgent need for a method or system that can quickly identify and present a subset of the brain atlas that is clinically relevant to the user, eliminating the need for the user to search and analyze large amounts of clinically irrelevant data; significantly reducing the time required for users to discover the parts of the brain atlas that are useful to them, thereby leading to improved outcomes for patients, users, and / or clinicians. Summary of the Invention
[0012] In view of the above problems, this application proposes a method and system for deriving target data from selected brain data, which can quickly identify the required subset of brain maps that are clinically relevant to the user and improve work efficiency.
[0013] The first aspect of this application provides a method for exporting target data of a brain atlas, comprising the following steps:
[0014] Obtaining raw brain data: collecting direct measurement data of the patient's brain, and / or indirect measurement data derived from the initial measurement data;
[0015] Preprocessing raw brain data: The acquired raw brain data is divided into regions and partitions to obtain several sets of brain partition data;
[0016] Select target data: The user inputs one or more target data from the selected brain data;
[0017] Acquire associated brain atlas data, identify one or more brain regions associated with selected target data, and acquire brain atlas data within that region;
[0018] Acquire target data: Determine a subset of brain mapping data associated with the determined partition and output this subset to the user for presentation.
[0019] Furthermore, the target data includes the following two data types: fiber bundles depicting the patient's brain; or connectivity data, specifically represented as a connectivity matrix, where each element in the connectivity matrix corresponds to two specific regions in the brain.
[0020] Furthermore, the method for selecting one or more target data in the connectivity matrix specifically involves: selecting one or more positions in the connectivity matrix from the user terminal; the selection of one or more positions in the connectivity matrix includes: selecting columns of the connectivity matrix or selecting rows of the connectivity matrix.
[0021] Furthermore, the method for selecting one or more segments of target data in the fiber bundles of the patient's brain specifically involves selecting a specific fiber bundle segment or a fiber bundle connecting a specific brain region from the user end.
[0022] Furthermore, it also includes processing a subset of the identified brain mapping data to generate clinical data for patient treatment.
[0023] Furthermore, it also includes providing the clinical data to one or more medical devices to perform treatment on the patient.
[0024] This application also provides a system for deriving target data of a brain atlas based on the above-described method, characterized in that it includes at least one programmable processor and a non-transitory machine-readable medium storing instructions; when executed by the programmable processor, the instructions enable the programmable processor to perform the following operations:
[0025] Obtaining raw brain data: collecting direct measurement data of the patient's brain, and / or indirect measurement data derived from the initial measurement data;
[0026] Preprocessing raw brain data: The acquired raw brain data is divided into regions and partitions to obtain several sets of brain partition data;
[0027] Select target data: The user inputs one or more target data from the selected brain data;
[0028] Acquire associated brain atlas data, identify one or more brain regions associated with selected target data, and acquire brain atlas data within that region;
[0029] Acquire target data: Determine a subset of brain mapping data associated with the determined partition and output this subset to the user for presentation.
[0030] Furthermore, the system includes a data acquisition module, a brain map data storage module, a preprocessing module, a partitioning module, a user instruction receiving module, and a target data generation module, with each module communicatively coupled through a network.
[0031] The data acquisition module is used to collect direct measurement data of the patient's brain and / or indirect measurement data derived from the initial measurement data;
[0032] The preprocessing module is used to preprocess raw brain data;
[0033] The partitioning module is used to divide the acquired raw brain data into regions and partitions to obtain several sets of brain partition data.
[0034] The user instruction receiving module is used to receive one or more target data selected by the user terminal;
[0035] The brain map data storage module is used to store and retrieve associated brain map data;
[0036] The target data generation module is used to determine a subset of brain map data associated with the determined partition and output the subset to the user device for presentation to the user.
[0037] Furthermore, the brain map data storage module uses either a table format, a document database, or a three-dimensional tensor for storage.
[0038] Furthermore, it also includes a clinical data generation module for processing a subset of the identified brain mapping data to generate clinical data for patient treatment.
[0039] Compared with the prior art, this application has the following advantages:
[0040] 1. The system and method of this application require less time to extract target data. Compared to existing technologies where users may need to spend hours extracting a subset of patient brain maps required for a specific treatment, the system and method of this application can quickly identify a subset of brain maps that are clinically relevant to the user and present this subset to the user. This eliminates the need for users to search and analyze large amounts of clinically irrelevant data, significantly reducing the time required. Using the system and method of this application, the process of extracting target data from brain datasets can be fully automated and completed within seconds or minutes, thereby bringing improved results for patients, users, and clinicians.
[0041] 2. The system and method of this application extract target data with high accuracy. Existing technologies, due to the significant time and attention required, may result in inaccurate and error-prone subsets of extracted brain maps. This application completely solves this technical problem.
[0042] 3. The system and method of this application extract highly accurate target data. Compared to existing technologies where users may only be able to generate target data that identifies most areas of the patient's brain, such as the frontal lobe, the system and method of this application can generate precise target data for highly personalized patient treatment. For example, users can identify abnormal brain data, and the system can determine the precise region of behavioral abnormality in the patient's brain from the identified brain data, such as a single region. The system can then generate target data for treatment of the target region. Therefore, treatment can be highly targeted and personalized, leading to improved health outcomes for individual patients. Attached Figure Description
[0043] Figure 1Flowchart of the method for exporting target brain atlas data for this application;
[0044] Figure 2 This is a flowchart illustrating an application example of the target data from the brain mapping technique used in this application.
[0045] Figure 3 A schematic diagram illustrating the system for exporting target data from a brain mapping dataset. Figure 1 ;
[0046] Figure 4 A schematic diagram illustrating the system for exporting target data from a brain mapping dataset. Figure 2 ;
[0047] Figure 5 This is a schematic diagram of a connectivity matrix and a schematic diagram of brain map data;
[0048] Figure 6 A schematic diagram for selecting one or more target data from a connectivity matrix or brain mapping dataset;
[0049] Explanation of markings in the diagram:
[0050] Figure 3 The system includes: 200 Export Brain Map Target Data System, 202 Patient Brain Data, 210 Brain Map Data Storage Module, 212 Brain Map Data, 220 Preprocessing Module, 222 Brain Partition Data, 230 Partition Related Module, 232 Brain Partition Related Data, 240 Target Data Generation Module, 250 Graphical User Interface and User Command Receiving Module, 252 Selected Elements, 242 Brain Map Data Subset, 254 Export Command, and 244 Target Data.
[0051] Figure 4 The system comprises the following modules: 201 Export Brain Atlas Target Data System, 202 Patient Brain Data, 210 Brain Atlas Data Storage Module, 212 Brain Atlas Data, 220 Preprocessing Module, 222 Brain Partition Data, 260 Brain Fiber Bundle Module, 262 Patient Brain Fiber Bundle Data, 270 Target Data Generation Module, 250 Graphical User Interface and User Command Receiving Module, 256 Selected Elements, 272 Brain Atlas Data Subset, 258 Export Command, and 274 Target Data. Detailed Implementation
[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0053] Example 1 is a method for deriving target data from a brain atlas, such as... Figure 1 As shown, it includes the following steps:
[0054] S1 Acquisition of raw brain data: Collection of direct measurement data of the patient's brain, such as brain images obtained through brain imaging techniques, and / or indirect measurement data derived from the initial measurement data;
[0055] S2 preprocessing of raw brain data: The acquired raw brain data is divided into regions to obtain several sets of brain region data;
[0056] S3 Select target data: The user inputs one or more target data from the selected brain data; In this embodiment, the target data includes the following two data types: fiber bundles depicting the patient's brain; or connectivity data, specifically represented as a connectivity matrix, where each element in the connectivity matrix corresponds to two specific regions in the brain.
[0057] S4 acquires associated brain atlas data, identifies one or more brain regions associated with the selected target data, and acquires brain atlas data within that region;
[0058] S5 Acquire Target Data: Determine a subset of brain map data associated with the determined partition and output this subset to a user device for presentation to the user. Providing the subset of brain map data for presentation to the user includes: providing data to the user device to represent the interface, wherein the interface includes i) visual indications of selected columns or rows of the connectivity matrix, and ii) a visual representation of the subset of brain map data;
[0059] Generate target data from defined partitions to generate patient treatment data, and provide the target data to one or more medical devices.
[0060] Example 2, based on the method of Example 1, further includes providing connectivity data for user display, including:
[0061] Identify one or more partition pairs from multiple partitions, wherein the association between brain activity in the patient's brain of the first and second partitions specified in the connectivity data exceeds the normal range of association corresponding to partition pairs; and
[0062] Provides users with data describing one or more identified partition pairs displayed on a graphical interface.
[0063] Connectivity data describes the degree of association of brain activity between the first and second partitions in each pair of partitions, which are derived from a pair of multiple partitions; brain functional connectivity data describes the degree of association of brain activity between one or more pairs of locations in a patient's brain tissue.
[0064] Example 3 is a method of any of Example 1 or 2, wherein connectivity data specifies a connectivity matrix, and each position in the connectivity matrix describes a pair of partitions, such as... Figure 5 As shown.
[0065] Example 4 is the method of Example 3, wherein determining one or more target data in the connectivity matrix includes receiving one or more locations selected by the user from the connectivity matrix, such as... Figure 6 As shown.
[0066] Example 5 is the method of Example 4, wherein receiving the selection of one or more positions in the connectivity matrix includes receiving the selection of a column or row of the connectivity matrix.
[0067] Example 6 is a method of any of Examples 1-5, such as Figure 2 As shown, it further includes processing the identified partition pairs to generate clinical treatment data for the patient.
[0068] Example 7 is the method of Example 6, such as Figure 2 As shown, it further includes providing clinical data to one or more medical devices to perform treatment on the patient.
[0069] Example 8 is a system comprising one or more computers and a storage device, wherein instructions stored in the storage device, when executed by the one or more computers, enable the one or more computers to perform any of the methods of Examples 1-7.
[0070] Example 9 is a computer storage medium encoded with a computer program including instructions that, when executed by a data processing device, enable the data processing device to perform any of the methods of Examples 1-7.
[0071] A system for deriving targeted brain mapping data is disclosed, capable of identifying a subset of brain mapping data associated with a patient-selected subset of brain data. The system can receive user input to identify the selected subset of the patient's brain data, and can use this identified subset of brain mapping data to generate targeted clinical data for treating the patient. For example, the system can generate targeted clinical data for high-precision targeted brain therapies, such as transcranial magnetic stimulation (TMS), and can also provide the user with the ability to display the subset of brain mapping data.
[0072] In this embodiment, brain data can be any data describing the patient's brain. For example, it can include one or both of the following: i) direct measurement data of the patient's brain, such as magnetic resonance brain images collected using magnetic resonance imaging techniques; or ii) data derived from or generated from the patient's initial measurement data, such as a correlation matrix.
[0073] In this embodiment, a brain region is a predefined area of the brain. The region can be defined by the boundaries of brain tissue, or by functionally similar clusters of neurons within that region based on one or more criteria. For example, a set of brain regions can be defined based on changes in cortical structure, function, connectivity, and / or morphology.
[0074] In this embodiment, a brain atlas is data that defines one or more regions of a patient's brain, for example, by defining the contour coordinates of the regions or the regions in a standard three-dimensional coordinate system.
[0075] In this embodiment, the target data can be a defined subset of brain atlas data or data on any specific brain region for targeted therapy. For example, the target data can identify one or more specific regions of a patient's brain, such as regions defined by a brain atlas. In some cases, the target data can be provided to one or more medical devices to perform treatment on the patient; for example, the target data can be provided to an image-guided system to deliver treatment to the patient.
[0076] Figure 3 and 4 These are diagrams illustrating example systems 200 and 201 for exporting target brain mapping data. Systems 200 and 201 for exporting target brain mapping data are examples of systems implemented as computer programs on one or more computers at one or more locations, where the systems, components, and techniques described below can be implemented.
[0077] like Figure 3 As shown, the brain atlas target data export system 200 is configured to determine a subset of brain atlas data based on one or more patient-specific partition-related data elements selected by the user. For example... Figure 4 As shown, the brain atlas target data export system 201 is configured to determine a subset of brain atlas data based on one or more specific patient fiber bundles selected by the user.
[0078] refer to Figure 3 The brain mapping target data system 200 is configured to acquire patient brain data 202 describing the patient's brain and process the patient brain data 202 to derive target data 244. In this embodiment, the patient brain data 202 may include blood oxygen level-dependent imaging data, functional magnetic resonance imaging (fMRI) data, or electroencephalogram (EEG) data captured from the patient's brain.
[0079] The brain atlas target data export system 200 includes a brain atlas data storage module 210, a preprocessing module 220, a partition correlation module 230, a target data generation module 240, and a graphical user interface and user command receiving module 250.
[0080] In some embodiments, the brain mapping target data system 200 is located locally to the user, for example, as a component of a user device. In other implementations, one or more components of the brain mapping target data system 200 are not local to the user, for example, hosted in a data center, which may be a distributed computing system with hundreds or thousands of computers in one or more locations. As a specific example, the graphical user interface and user command receiving module 250 may be located locally to the user, while each of the other components of the brain mapping target data system 200 is in the cloud and communicatively connected to the graphical user interface and user command receiving module 250.
[0081] The brain atlas data storage module 210 is configured to maintain brain atlas data 212 that defines multiple regions of the human brain. For example, the brain atlas data 212 may include a brain model composed of three-dimensional voxels, each voxel being defined by its position and orientation in a standard brain coordinate system.
[0082] Each voxel can be assigned to a specific region, such that the location and shape of each region are defined by the corresponding voxel assigned to that region. As a concrete example, brain mapping data 212 can be stored using a table that maps (x, y, z) locations within the brain to specific region identifications. As another concrete example, brain mapping data 212 can be stored in a document-oriented database, for example, using JSON format. As yet another concrete example, brain mapping data 212 can be stored using a set of three-dimensional tensors that identify specific regions within the brain corresponding to (x, y, z) locations.
[0083] Figure 1 , Figure 2 The example flowchart shown illustrates the process of identifying and deriving target data from patient brain data. The process can be implemented by one or more computer programs installed on one or more computers and programmed according to this specification. For example, the process can be implemented by… Figure 3 or Figure 4 The computer server module described herein will be executed. For convenience, the process will be described as being executed by one or more computer systems.
[0084] The system provides the user with patient brain data for display (step S1). The patient brain data may include fiber bundles and / or connectivity data depicting the patient's brain.
[0085] Connectivity data can describe the degree of correlation between brain activity in a patient's brain for each pair of partitions in a set of multiple subdivided regions, including a first partition and a second partition. In some practices, connectivity data specifies a connectivity matrix, where each position in the matrix describes a pair of partitions.
[0086] In some embodiments, the system can identify one or more partition pairs from a set of partitions, wherein the correlation between brain activity in the patient's brain between the first and second partitions specified in connectivity data exceeds the normal range. The system can then provide the user with data describing the one or more identified partition pairs for display on a graphical interface.
[0087] The system identifies one or more target data points from the patient's brain data (S3). For example, the system may receive selections from the user, choosing one or more locations in a connectivity matrix that describes the correlations between pairs of partitions in the patient's brain. As a concrete example, the system may receive selections of a column or a row of the connectivity matrix.
[0088] The system identifies one or more partitions associated with the element of interest (S4). For example, each region of interest may include the identification of a specific partition.
[0089] The system acquires brain mapping data (step S4).
[0090] The system identifies a subset of brain map data associated with the identified partitions (step S5).
[0091] The system provides a subset of brain mapping data to the user device so that the subset can be rendered to the user (step S5).
[0092] The system processes the determined partition pairs to generate treatment target data for the patient (step S6).
[0093] The system provides the target data to one or more medical devices to perform the patient's treatment (step S7).
[0094] The functional operations described in this embodiment can be implemented by digital electronic circuits, tangibly embodied computer software or firmware, computer hardware, including the structures disclosed in this specification and their structural equivalents, or one or more combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more computer program instruction modules, encoded on a tangible, non-transitory storage medium, executed or controlled by a data processing device. The computer storage medium can be a machine-readable storage device, a machine-readable storage matrix, a random or serial access storage device, or one or more combinations thereof. Alternatively, program instructions can also be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals generated for transmitting information to a suitable receiving device for execution by a data processing device.
[0095] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Although the invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that the invention is not limited to the details of the above exemplary embodiments, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Therefore, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.
Claims
1. A method for deriving target data from a brain atlas, characterized in that, Includes the following steps: Obtaining raw brain data: collecting direct measurement data of the patient's brain, and / or indirect measurement data derived from the initial measurement data; Preprocessing raw brain data: The acquired raw brain data is divided into regions to obtain several sets of brain region data; Select target data: The user inputs one or more target data from the selected brain data; Obtain associated brain atlases, identify one or more brain regions associated with selected target data, and acquire brain atlas data within those regions; Acquire target data: Determine a subset of brain mapping data associated with the determined partition and output this subset to the user for presentation.
2. The method for deriving target data of a brain atlas according to claim 1, characterized in that, The target data includes the following two data types: fiber bundles depicting the patient's brain; or connectivity data, specifically represented as a connectivity matrix, where each element in the connectivity matrix corresponds to two specific regions in the brain.
3. The method for deriving target data of a brain atlas according to claim 2, characterized in that, The method for selecting one or more target data in the connectivity matrix specifically involves: selecting one or more positions in the connectivity matrix from the user's perspective; The selection of one or more positions in the connectivity matrix includes: the selection of columns of the connectivity matrix or the selection of rows of the connectivity matrix.
4. The method for deriving target data of a brain atlas according to claim 2, characterized in that, The method for selecting one or more segments of target data in the fiber bundles of the patient's brain is specifically: selecting a specific fiber bundle segment or a fiber bundle connecting a specific brain region from the user terminal.
5. The method for deriving target data of a brain atlas according to claim 1, characterized in that, It also includes processing a subset of the identified brain mapping data to generate clinical data for patient treatment.
6. The method for deriving target data of a brain atlas according to claim 5, characterized in that, It also includes providing the clinical data to one or more medical devices to perform treatment on the patient.
7. A system for deriving target brain atlas data constructed based on the method described in any one of claims 1-6, characterized in that, It includes at least one programmable processor and a non-transitory machine-readable medium storing instructions; when executed by the programmable processor, the instructions enable the programmable processor to perform the following operations: Obtaining raw brain data: collecting direct measurement data of the patient's brain, and / or indirect measurement data derived from the initial measurement data; Preprocessing raw brain data: The acquired raw brain data is divided into regions and partitions to obtain several sets of brain partition data; Select target data: The user inputs one or more target data from the selected brain data; Acquire associated brain atlas data, identify one or more brain regions associated with selected target data, and acquire brain atlas data within that region; Acquire target data: Determine a subset of brain mapping data associated with the determined partition and output this subset to the user for presentation.
8. The system for deriving target data of a brain atlas according to claim 7, characterized in that, The system includes a data acquisition module, a brain map data storage module, a preprocessing module, a partitioning module, a user instruction receiving module, and a target data generation module. The modules are coupled to each other communicatively via a network. The data acquisition module is used to collect direct measurement data of the patient's brain and / or indirect measurement data derived from the initial measurement data; The preprocessing module is used to preprocess raw brain data; The partitioning module is used to divide the acquired raw brain data into regions and partitions to obtain several sets of brain partition data. The user instruction receiving module is used to receive one or more target data selected by the user terminal; The brain map data storage module is used to store and retrieve associated brain map data; The target data generation module is used to determine a subset of brain map data associated with the determined partition and output the subset to the user device for presentation to the user.
9. The system for deriving target data of a brain atlas according to claim 8, characterized in that, The brain map data storage module uses either a table format, a document database, or a three-dimensional tensor for storage.
10. The system for deriving target data of a brain atlas according to claim 8, characterized in that, It also includes a clinical data generation module for processing a subset of the identified brain mapping data to generate clinical data for patient treatment.