CN113628167B - Method, system, electronic equipment and storage medium for constructing brain network with individual structure - Google Patents
Method, system, electronic equipment and storage medium for constructing brain network with individual structure Download PDFInfo
- Publication number
- CN113628167B CN113628167B CN202110788813.1A CN202110788813A CN113628167B CN 113628167 B CN113628167 B CN 113628167B CN 202110788813 A CN202110788813 A CN 202110788813A CN 113628167 B CN113628167 B CN 113628167B
- Authority
- CN
- China
- Prior art keywords
- morphological
- brain
- vectors
- structural
- magnetic resonance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004556 brain Anatomy 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000000877 morphologic effect Effects 0.000 claims abstract description 145
- 239000013598 vector Substances 0.000 claims abstract description 95
- 238000010276 construction Methods 0.000 claims abstract description 46
- 239000011159 matrix material Substances 0.000 claims description 46
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims 2
- 238000010606 normalization Methods 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 description 4
- 210000004884 grey matter Anatomy 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 210000003625 skull Anatomy 0.000 description 3
- 230000002739 subcortical effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000001054 cortical effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241001086826 Branta bernicla Species 0.000 description 1
- 241001286408 Gretna Species 0.000 description 1
- 238000005481 NMR spectroscopy Methods 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The application discloses a brain network construction method, a brain network construction system, electronic equipment and a storage medium for an individuation structure, and relates to the technical field of brain networks. The individualized structure brain network construction method comprises the following steps: acquiring a plurality of structural magnetic resonance data of a brain structure, and acquiring a plurality of first morphological feature values according to the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
Description
Technical Field
The present disclosure relates to the field of brain network technologies, and in particular, to a method, a system, an electronic device, and a storage medium for constructing a brain network with an individualized structure.
Background
Currently, there are many methods for constructing personalized structural covariant brain networks, such as methods based on probability density plus KL divergence. The method does not consider the difference of the real structural morphology in the brain, and the distribution of the structural morphology features in the brain is required to be sampled simultaneously to obtain vectors with consistent length, so that the KL divergence can be calculated. However, since the sizes of the areas in the brain are different, that is, the number of gray voxels is different, the lengths of the vectors formed are different, and the partial voxel information is lost due to the fact that the vectors with the same length are obtained through sampling, so that the accuracy of brain network construction is not high.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the prior art. Therefore, the application provides a brain network construction method, a brain network construction system, electronic equipment and a storage medium for an individual structure, which can directly calculate the optimal regular distance between vectors with different lengths formed according to morphological characteristics of a brain structure, thereby solving the problem of low accuracy of brain network construction caused by brain voxel information loss.
An individualized structural brain network building method according to an embodiment of the first aspect of the present application includes:
acquiring a plurality of structural magnetic resonance data of a brain structure;
obtaining a plurality of first morphological feature values according to a plurality of the structural magnetic resonance data;
dividing the brain structure to obtain a plurality of functional areas;
acquiring the first morphological characteristic value corresponding to each functional area as a second morphological characteristic value;
generating a corresponding morphological vector according to each second morphological feature value;
obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors;
and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors.
The method for constructing the brain network with the individuation structure has the following beneficial effects:
acquiring a plurality of structural magnetic resonance data of a brain structure, and acquiring a plurality of first morphological feature values according to the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
According to some embodiments of the present application, the obtaining a plurality of first morphological feature values according to a plurality of the structural magnetic resonance data includes:
performing data processing on a plurality of structural magnetic resonance data;
registering each processed structural magnetic resonance data to a standard template space to obtain a first morphological characteristic value corresponding to each structural magnetic resonance data.
According to some embodiments of the present application, after the dividing the brain structure into a plurality of functional areas, the method includes:
and acquiring a plurality of region voxels corresponding to each functional region and the number of the region voxels.
According to some embodiments of the present application, the obtaining the similarity of at least two morphological vectors according to at least two morphological vectors includes:
constructing a structure covariant matrix according to the number of the region voxels corresponding to each functional region and at least two morphological vectors corresponding to each functional region;
and obtaining the similarity of at least two morphological vectors according to the structural covariant matrix.
According to some embodiments of the present application, each first element in the structural covariate matrix represents a cumulative distance of at least two of the morphological vectors;
correspondingly, the obtaining the similarity of at least two morphological vectors according to the structural covariant matrix comprises the following steps:
acquiring element paths between each first element and the rest of the first elements in the structure covariant matrix;
selecting an element path with the shortest path as an optimal path;
selecting a plurality of first elements on the optimal path as a plurality of second elements according to the optimal path;
acquiring accumulated distances corresponding to a plurality of second elements;
and obtaining the similarity of at least two morphological vectors according to the accumulated distances corresponding to the second elements.
According to some embodiments of the application, the constructing the brain network of the brain structure according to the similarity of at least two of the morphological vectors comprises:
calculating network parameters of the brain structure according to the structure covariant matrix;
and constructing a brain network of the brain structure according to the network parameters.
According to some embodiments of the application, the computing network parameters of the brain structure from the structural covariate matrix comprises:
selecting the first element with the largest median among a plurality of first elements of the structure covariant matrix to obtain the maximum value;
calculating each first element in the structure covariant matrix to obtain an updated structure covariant matrix;
and calculating the network parameters of the brain structure according to the updated structure covariate matrix.
A brain network building system according to an embodiment of the second aspect of the present application, comprising:
and a data acquisition module: acquiring a plurality of structural magnetic resonance data of a brain structure;
and a similarity calculation module: obtaining a plurality of first morphological feature values according to a plurality of the structural magnetic resonance data; dividing according to the brain structure to obtain a plurality of functional areas; acquiring the first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value; obtaining the similarity of at least two morphological vectors;
the brain network construction module: and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors.
The brain network construction system according to the embodiment of the application has at least the following beneficial effects:
the brain network construction system comprises a data acquisition module, a similarity calculation module and a brain network construction module. The data acquisition module acquires a plurality of structural magnetic resonance data of the brain structure; the similarity calculation module obtains a plurality of first morphological characteristic values according to the plurality of structural magnetic resonance data; dividing according to brain structures to obtain a plurality of functional areas; acquiring a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value; obtaining the similarity of at least two morphological vectors; the brain network construction module constructs a brain network of the brain structure according to the similarity of the at least two morphological vectors.
According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
An electronic device according to an embodiment of a third aspect of the present application includes:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions that are executed by the at least one processor to cause the at least one processor to implement the personalized structural brain network construction method according to any one of the embodiments of the first aspect of the present application when the instructions are executed.
The electronic equipment provided by the embodiment of the application has at least the following beneficial effects: acquiring a plurality of structural magnetic resonance data of a brain structure by executing the individualized structural brain network construction method according to the embodiment of the first aspect, and obtaining a plurality of first morphological feature values according to the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
A computer readable storage medium according to an embodiment of a fourth aspect of the present application, comprising:
the computer readable storage medium stores computer executable instructions for performing the individualized structural brain network building method according to the embodiments of the first aspect of the present application.
The computer readable storage instructions according to embodiments of the present application have at least the following beneficial effects: acquiring a plurality of structural magnetic resonance data of a brain structure by executing the individualized structural brain network construction method according to the embodiment of the first aspect, and obtaining a plurality of first morphological feature values according to the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
Additional aspects and advantages of the application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application.
Drawings
The application is further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a first flowchart of a method for personalized structured brain network construction provided in some embodiments of the present application;
FIG. 2 is a second flowchart of a method for personalized structured brain network construction provided in some embodiments of the present application;
FIG. 3 is a third flowchart of a method for personalized structured brain network construction provided by some embodiments of the present application;
FIG. 4 is a fourth flowchart of a method for personalized structured brain network construction provided by some embodiments of the present application;
FIG. 5 is a fifth flowchart of a method for personalized structured brain network construction provided by some embodiments of the present application;
FIG. 6 is a sixth flowchart of a personalized structured brain network construction method provided by some embodiments of the present application;
FIG. 7 is a general flow chart of a method for personalized structured brain network construction provided in some embodiments of the present application;
fig. 8 is a block diagram of a brain network construction system according to some embodiments of the present application.
Reference numerals:
a data acquisition module 100, a similarity calculation module 200, and a brain network construction module 300.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present application.
In the description of the present application, a description with reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Currently, there are many methods for constructing personalized structural covariant brain networks, such as methods based on probability density plus KL divergence. The method does not consider the difference of the real structural morphology in the brain, and the distribution of the structural morphology features in the brain is required to be sampled simultaneously to obtain vectors with consistent length, so that the KL divergence can be calculated. However, since the sizes of the areas in the brain are different, that is, the number of gray voxels is different, the lengths of the vectors formed are different, and the partial voxel information is lost due to the fact that the vectors with the same length are obtained through sampling, so that the accuracy of brain network construction is not high.
Based on the above, the application provides a method, a system, electronic equipment and a storage medium for constructing a brain network with an individual structure, which are used for acquiring a plurality of structural magnetic resonance data of a brain structure and acquiring a plurality of first morphological characteristic values according to the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
In a first aspect, embodiments of the present application provide a method for constructing a brain network with a personalized structure.
Referring to fig. 1, fig. 1 is a first flowchart of a method for constructing a brain network with a personalized structure according to some embodiments of the present application, which specifically includes the steps of:
s100, acquiring a plurality of structural magnetic resonance data of a brain structure;
s200, obtaining a plurality of first morphological characteristic values according to a plurality of structural magnetic resonance data;
s300, dividing a brain structure to obtain a plurality of functional areas;
s400, acquiring a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value;
s500, generating a corresponding morphological vector according to each second morphological feature value;
s600, obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors;
s700, constructing a brain network of the brain structure according to the similarity of at least two morphological vectors.
In step S100, a plurality of structural magnetic resonance data of the brain structure may be acquired by a nuclear magnetic resonance scanner.
In step S200, a plurality of first morphology feature values are obtained according to the plurality of structural magnetic resonance data acquired in step S100, where the first morphology feature values include structural morphology features such as gray matter volume, cortex thickness, and the like.
In some embodiments, as shown in fig. 2, step S200 specifically includes the steps of:
s210, performing data processing on a plurality of structural magnetic resonance data;
and S220, registering each processed structure magnetic resonance data to a standard template space to obtain a first morphological characteristic value corresponding to each structure magnetic resonance data.
In step S210, data processing is performed on the plurality of structural magnetic resonance data acquired in step S100, and since the data of the magnetic resonance scan is skull-bearing, the skull needs to be removed to register the data to the template space for segmentation.
In step S220, the plurality of structural magnetic resonance data with the skull removed in step S210 are registered to a standard template space based on freeform or VBM8 software, and a first morphological feature value corresponding to each structural magnetic resonance data is obtained.
In some embodiments, the method for constructing the brain network with the personalized structure specifically further comprises the following steps: and acquiring a plurality of region voxels corresponding to each functional region and the number of the region voxels.
In step S300, the brain structure is divided into a plurality of functional areas, where the brain may be divided into different functional areas using templates of the brain, such as anatomical automatic labeling (Automatical Anatomical labeling, AAL) templates, harvard-Oxford templates, or brain template, etc. may be used. Wherein the ALL template comprises 90 cortical and subcortical regions and 26 cerebellar regions; the Harvard-Oxford template contained 48 cortical areas and 7 subcortical areas per hemisphere; the Brainnnetome template comprises 236 cortical and subcortical regions, and the like. It should be noted that, a person skilled in the art may select an appropriate template to partition the brain according to actual needs, which will not be described in detail herein.
In step S400, a first morphological feature value corresponding to each functional region is extracted and used as a second morphological feature value, where the first morphological feature value includes structural morphological features such as gray matter volume, cortex thickness, and the like.
In step S500, each second morphological feature value, such as thickness, gray matter volume, is extracted and then a morphological vector is formed.
In step S600, a similarity of at least two morphological vectors is obtained according to the at least two morphological vectors.
In some embodiments, as shown in fig. 3, step S600 specifically includes the steps of:
s610, constructing a structure covariant matrix according to the number of region voxels corresponding to each functional region and at least two morphological vectors corresponding to each functional region;
s620, obtaining the similarity of at least two morphological vectors according to the structural covariant matrix.
In step S610, a dynamic time warping (Dynamic Time Warping, DTW) method is applied to calculate the similarity of the structural morphological feature covariances of the different regions. In order to calculate the optimal distance, firstly, morphological characteristics of two areas with different numbers of voxels, such as gray matter volume, thickness and the like, are transformed into a vector, such as an A area 1m, m is the number of voxels of the A area, and a B area 1n, n is the number of voxels of the B area; then, a mn matrix C is constructed, and the value C (i, j) at any position in the matrix is the Euclidean distance between the area A (i) and the area B (j), namely the similarity value. Each element in the matrix represents the cumulative distance of the two vectors, with smaller distances indicating more similarity.
In step S620, the similarity of at least two morphological vectors can be obtained according to the matrix C.
In some embodiments, as shown in fig. 4, step S620 specifically includes the steps of:
s621, obtaining element paths between each first element and the rest of first elements in the structure covariant matrix;
s622, selecting an element path with the shortest path as an optimal path;
s623, selecting a plurality of first elements on the optimal path as a plurality of second elements according to the optimal path;
s624, acquiring accumulated distances corresponding to a plurality of second elements;
s625, obtaining the similarity of at least two morphological vectors according to the accumulated distances corresponding to the second elements.
In step S621, each element in the matrix C is referred to as a first element, and for each first element, element paths between the remaining first elements are calculated;
in step S622, find the shortest path from the C (1, 1) point to the C (m, n) point in the C matrix as the optimal path;
in step S623, the element on the shortest path from the C (1, 1) point to the C (m, n) point in the C matrix is called a second element;
in step S624, according to the coordinate values of the second elements, the accumulated distances corresponding to the second elements are obtained;
in step S625, the accumulated distance corresponding to the second element is defined as a similarity, and at least two morphological vectors are obtained, where the similarity of the at least two morphological vectors is used to construct a brain network.
In step S700, a brain network of the brain structure is constructed from the similarity of the at least two morphological vectors.
In some embodiments, as shown in fig. 5, step S700 specifically includes the steps of:
s710, calculating network parameters of the brain structure according to the structure covariant matrix;
s720, constructing a brain network of the brain structure according to the network parameters.
In step S710, calculating network parameters of the brain structure according to the structure covariate matrix;
in some embodiments, as shown in fig. 6, step S710 specifically includes steps;
s711, selecting a first element with the largest median among a plurality of first elements of the structural covariant matrix to obtain the maximum value;
s712, calculating each first element in the structural covariant matrix to obtain an updated structural covariant matrix;
s713, calculating the network parameters of the brain structure according to the updated structure covariate matrix.
In step S711, a maximum value in the structural covariant matrix is selected;
in step S722, each value in the structural covariate matrix is inverted and then divided by the maximum value in the matrix.
In step S720, for the normalized covariate matrix, that is, a brain network matrix for connecting different brain regions to brain regions is formed, and then the network parameters of each individual, such as indexes of small world attribute, cluster coefficient, efficiency, degree, etc., are calculated by using a brain network index calculation tool, such as GRETNA, BRANT, CONN, etc., and a brain network can be constructed according to these indexes.
In the embodiment of the application, a plurality of first morphological feature values are obtained according to a plurality of structural magnetic resonance data of a brain structure by acquiring the plurality of structural magnetic resonance data; dividing the brain structure to obtain a plurality of functional areas, and obtaining a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value, and obtaining the similarity of at least two morphological vectors according to the at least two morphological vectors; and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors. According to the method and the device, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
As shown in fig. 7, in the embodiment of the present application, first, a brain structure magnetic resonance image is acquired, brain morphological features are extracted from the brain structure magnetic resonance image, an ALL brain template is used to obtain an original covariant connection matrix, then the covariant connection matrix is standardized, a structure covariant brain network is constructed according to the standardized covariant connection matrix, and then brain network topology attributes are depicted according to the structure covariant brain network.
In a second aspect, embodiments of the present application further provide a brain network construction system for performing the individualized structural brain network construction method mentioned in the embodiments of the first aspect.
As shown in fig. 8, in some embodiments, the brain network construction system includes a data acquisition module 100, a similarity calculation module 200, and a brain network construction module 300. The data acquisition module 100 acquires a plurality of structural magnetic resonance data of the brain structure; the similarity calculation module 200 obtains a plurality of first morphological feature values according to the plurality of structural magnetic resonance data; dividing according to brain structures to obtain a plurality of functional areas; acquiring a first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value; obtaining the similarity of at least two morphological vectors; the brain network construction module 300 constructs a brain network of the brain structure based on the similarity of the at least two morphological vectors.
According to the embodiment of the application, the optimal normalization distance between the vectors with different lengths can be calculated according to the vectors with different lengths formed by the morphological characteristics of the brain structure, and the brain voxel information is not lost, so that the accuracy of brain network construction is improved.
In a third aspect, an embodiment of the present application further provides an electronic device.
In some embodiments, an electronic device includes: at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions that are executed by the at least one processor to cause the at least one processor to implement any of the personalized structure brain network construction methods of the embodiments of the present application when executing the instructions.
The processor and the memory may be connected by a bus or other means.
The memory is used as a non-transitory computer readable storage medium for storing non-transitory software programs and non-transitory computer executable programs, such as the individualized structural brain network construction methods described in the embodiments of the present application. The processor implements the above-described personalized structure brain network construction method by running non-transitory software programs and instructions stored in the memory.
The memory may include a memory program area and a memory data area, wherein the memory program area may store an operating system, at least one application program required for a function; the storage data area can store and execute the above-mentioned individuation structure brain network construction method. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located relative to the processor, the remote memory being connectable to the processor through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The non-transitory software programs and instructions required to implement the above-described personalized structured brain network construction method are stored in a memory, which when executed by one or more processors, perform the personalized structured brain network construction method mentioned in the above-described embodiments of the first aspect.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium.
In some embodiments, a computer-readable storage medium stores computer-executable instructions for performing the individualized structural brain network building method mentioned in the embodiments of the first aspect.
In some embodiments, the storage medium stores computer-executable instructions that are executed by one or more control processors, e.g., by one of the processors in the electronic device, which may cause the one or more processors to perform the personalized structure brain network building method.
The above described apparatus embodiments are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The embodiments of the present application have been described in detail above with reference to the accompanying drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge of one of ordinary skill in the art without departing from the spirit of the present application. Furthermore, embodiments of the present application and features of the embodiments may be combined with each other without conflict.
Claims (8)
1. The method for constructing the brain network of the individuation structure is characterized by comprising the following steps:
acquiring a plurality of structural magnetic resonance data of a brain structure;
obtaining a plurality of first morphological feature values according to a plurality of structural magnetic resonance data and a template space;
dividing the brain structure by using a preset brain template to obtain a plurality of functional areas, wherein each functional area corresponds to a plurality of area voxels and the number of the area voxels;
acquiring the first morphological characteristic value corresponding to each functional area as a second morphological characteristic value;
generating a corresponding morphological vector according to each second morphological feature value;
constructing a structure covariant matrix according to the number of region voxels corresponding to each functional region and at least two morphological vectors corresponding to each functional region, and obtaining at least the similarity of the two morphological vectors according to the structure covariant matrix;
and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors.
2. The method of claim 1, wherein obtaining a plurality of first morphological feature values from a plurality of the structural magnetic resonance data comprises:
performing data processing on a plurality of structural magnetic resonance data;
registering each processed structural magnetic resonance data to a standard template space to obtain a first morphological characteristic value corresponding to each structural magnetic resonance data.
3. The method of claim 1, wherein each first element in the structural covariate matrix represents a cumulative distance of at least two of the morphological vectors;
correspondingly, the obtaining the similarity of at least two morphological vectors according to the structural covariant matrix comprises the following steps:
acquiring element paths between each first element and the rest of the first elements in the structure covariant matrix;
selecting an element path with the shortest path as an optimal path;
selecting a plurality of first elements on the optimal path as a plurality of second elements according to the optimal path;
acquiring accumulated distances corresponding to a plurality of second elements;
and obtaining the similarity of at least two morphological vectors according to the accumulated distances corresponding to the second elements.
4. A method of constructing a brain network of a personalized structure according to claim 3, wherein said constructing a brain network of said brain structure based on similarities of at least two of said morphological vectors comprises:
calculating network parameters of the brain structure according to the structure covariant matrix;
and constructing a brain network of the brain structure according to the network parameters.
5. The method of claim 4, wherein calculating network parameters of the brain structure from the structural covariant matrix comprises:
selecting the first element with the largest median among a plurality of first elements of the structure covariant matrix to obtain the maximum value;
calculating each first element in the structure covariant matrix to obtain an updated structure covariant matrix;
and calculating the network parameters of the brain structure according to the updated structure covariate matrix.
6. A brain network building system, comprising:
and a data acquisition module: acquiring a plurality of structural magnetic resonance data of a brain structure;
and a similarity calculation module: obtaining a plurality of first morphological feature values according to a plurality of the structural magnetic resonance data; dividing according to the brain structure to obtain a plurality of functional areas; acquiring the first morphological characteristic value corresponding to each functional area as a second morphological characteristic value; generating a corresponding morphological vector according to each second morphological feature value; obtaining the similarity of at least two morphological vectors;
the brain network construction module: and constructing a brain network of the brain structure according to the similarity of at least two morphological vectors.
7. An electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized by: the processor, when executing the computer program, implements the individualized structural brain network construction method according to any one of claims 1 to 5.
8. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform the individualized structural brain network building method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788813.1A CN113628167B (en) | 2021-07-13 | 2021-07-13 | Method, system, electronic equipment and storage medium for constructing brain network with individual structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788813.1A CN113628167B (en) | 2021-07-13 | 2021-07-13 | Method, system, electronic equipment and storage medium for constructing brain network with individual structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113628167A CN113628167A (en) | 2021-11-09 |
| CN113628167B true CN113628167B (en) | 2024-04-05 |
Family
ID=78379617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110788813.1A Active CN113628167B (en) | 2021-07-13 | 2021-07-13 | Method, system, electronic equipment and storage medium for constructing brain network with individual structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113628167B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012097189A1 (en) * | 2011-01-13 | 2012-07-19 | Rutgers, The State University Of New Jersey | Systems and methods for multi-protocol registration and tissue classification using local morphologic scale (lms) |
| CN103942781A (en) * | 2014-04-01 | 2014-07-23 | 北京师范大学 | Method for constructing brain network based on brain image |
| CN104933729A (en) * | 2014-03-18 | 2015-09-23 | 上海联影医疗科技有限公司 | Method and device for extracting intracerebral brain tissue |
| CN107316292A (en) * | 2017-06-22 | 2017-11-03 | 电子科技大学 | A kind of method that big brain morphology symmetry is calculated based on structure covariant |
| CN107909117A (en) * | 2017-09-26 | 2018-04-13 | 电子科技大学 | A kind of sorting technique and device based on brain function network characterization to early late period mild cognitive impairment |
| CN109885712A (en) * | 2019-02-12 | 2019-06-14 | 山东中医药大学 | Lung neoplasm image search method and system based on content |
| CN111090764A (en) * | 2019-12-20 | 2020-05-01 | 中南大学 | Image classification method and device based on multitask learning and graph convolution neural network |
| CN111753947A (en) * | 2020-06-08 | 2020-10-09 | 深圳大学 | Resting brain network construction method, device, equipment and computer storage medium |
| CN111814806A (en) * | 2020-07-13 | 2020-10-23 | 山东管理学院 | Image feature extraction method based on supervised graph regularization |
| CN113344883A (en) * | 2021-06-10 | 2021-09-03 | 华南师范大学 | Multilayer morphological brain network construction method, intelligent terminal and storage medium |
-
2021
- 2021-07-13 CN CN202110788813.1A patent/CN113628167B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012097189A1 (en) * | 2011-01-13 | 2012-07-19 | Rutgers, The State University Of New Jersey | Systems and methods for multi-protocol registration and tissue classification using local morphologic scale (lms) |
| CN104933729A (en) * | 2014-03-18 | 2015-09-23 | 上海联影医疗科技有限公司 | Method and device for extracting intracerebral brain tissue |
| CN103942781A (en) * | 2014-04-01 | 2014-07-23 | 北京师范大学 | Method for constructing brain network based on brain image |
| CN107316292A (en) * | 2017-06-22 | 2017-11-03 | 电子科技大学 | A kind of method that big brain morphology symmetry is calculated based on structure covariant |
| CN107909117A (en) * | 2017-09-26 | 2018-04-13 | 电子科技大学 | A kind of sorting technique and device based on brain function network characterization to early late period mild cognitive impairment |
| CN109885712A (en) * | 2019-02-12 | 2019-06-14 | 山东中医药大学 | Lung neoplasm image search method and system based on content |
| CN111090764A (en) * | 2019-12-20 | 2020-05-01 | 中南大学 | Image classification method and device based on multitask learning and graph convolution neural network |
| CN111753947A (en) * | 2020-06-08 | 2020-10-09 | 深圳大学 | Resting brain network construction method, device, equipment and computer storage medium |
| CN111814806A (en) * | 2020-07-13 | 2020-10-23 | 山东管理学院 | Image feature extraction method based on supervised graph regularization |
| CN113344883A (en) * | 2021-06-10 | 2021-09-03 | 华南师范大学 | Multilayer morphological brain network construction method, intelligent terminal and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113628167A (en) | 2021-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280477B (en) | Method and apparatus for clustering images | |
| US20220222932A1 (en) | Training method and apparatus for image region segmentation model, and image region segmentation method and apparatus | |
| WO2021203795A1 (en) | Pancreas ct automatic segmentation method based on saliency dense connection expansion convolutional network | |
| CN110929780A (en) | Video classification model construction method, video classification device, video classification equipment and media | |
| CN111444363B (en) | Picture retrieval method and device, terminal equipment and storage medium | |
| CN111291825A (en) | Focus classification model training method and device, computer equipment and storage medium | |
| CN111967339B (en) | Method and device for planning unmanned aerial vehicle path | |
| CN108182421A (en) | Methods of video segmentation and device | |
| CN112328715A (en) | Visual positioning method, training method of related model, related device and equipment | |
| WO2022028147A1 (en) | Image classification model training method and apparatus, computer device, and storage medium | |
| CN111159451B (en) | Power line point cloud dynamic monomer method based on spatial database | |
| CN112183627A (en) | Method for generating predicted density map network and vehicle annual inspection mark number detection method | |
| CN106683105B (en) | Image segmentation method and image segmentation device | |
| CN114092651A (en) | Intelligent modeling system and method for emergency management | |
| CN113628167B (en) | Method, system, electronic equipment and storage medium for constructing brain network with individual structure | |
| CN111986242B (en) | Method and device for determining brain tissue partition, storage medium and electronic equipment | |
| CN116205964B (en) | Point cloud downsampling method and device based on horizontal distance | |
| CN114677575A (en) | Scene migration method and device and electronic equipment | |
| CN116403071B (en) | Method and device for detecting few-sample concrete defects based on feature reconstruction | |
| CN110717405B (en) | Face feature point positioning method, device, medium and electronic equipment | |
| CN117237681A (en) | Image processing method, device and related equipment | |
| CN114691630B (en) | Smart supply chain big data sharing method and system | |
| CN111582013A (en) | Ship retrieval method and device based on gray level co-occurrence matrix characteristics | |
| CN114153380B (en) | Integrated circuits, systems, and methods for data access and acquisition | |
| CN112801208B (en) | Depth measurement learning method and device based on structured agent |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |