A fiber bundle division method and system based on fiber similarity and a storage medium

Abstract

The application provides a fiber bundle division method and system based on fiber similarity and a storage medium, and relates to the technical field of image processing; the method comprises the following steps: performing interval division on each fiber of a target fiber bundle, performing cluster point sampling on the fibers in each interval, calculating the similarity between the fibers based on the cluster points, generating an initial similarity matrix, performing hierarchical clustering on the fiber bundle based on the similarity matrix, generating a preliminary clustering result, calculating the similarity of fiber clusters between intervals based on the cluster points, generating a clustering similarity matrix, performing hierarchical clustering on the fiber clusters based on the clustering similarity matrix, and performing hierarchical clustering on the clustered result to generate a fiber clustering result of the target fiber bundle. The fiber bundle is clustered multiple times, so that the fibers in the clusters have tightness, and the clusters have separation degree, thereby improving the fiber bundle division precision and efficiency.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of image processing, and in particular to a fiber bundle segmentation method, system and storage medium based on fiber similarity. Background Art

[0002] White matter fiber tracts are large fiber clusters composed of a series of adjacent nerve fibers with similar structures. They are key neural structures that play a connecting role in the brain, responsible for connecting different brain areas and facilitating information transmission. Diffusion Tensor Imaging (DTI) technology is a non-invasive in vivo detection technology that estimates the structure of white matter (WM) by measuring the diffusion of water molecules. Based on diffusion tensor imaging (DTI), the local direction field of white matter is estimated to generate a three-dimensional representation of white matter fiber tracts, enabling non-invasive research on the organizational structure and morphological characteristics of white matter fiber tracts, so as to accurately characterize the fiber tracts, thereby better understanding brain structural connections, brain functional networks, pathological changes of neurological diseases, and formulating personalized treatment plans.

[0003] Although diffusion tensor imaging (DTI) technology provides rich fiber tracking information, the precise division of fiber bundles is still challenging due to the very complex structure of the fiber bundles. Due to the complex fiber crossing and overlapping in the white matter region of the brain, traditional division methods based on spatial position or simple geometric features cannot accurately divide the morphology of the fiber bundles. The length, shape and spatial distribution of fiber bundles vary, which requires adaptive division of fibers of different scales. In addition, the noise in diffusion tensor imaging (DTI) data will affect the accuracy of fiber tracking, making subsequent division more difficult. Therefore, there is an urgent need for a fine division method for fiber bundles suitable for studying the structure and function of white matter fiber bundles in the brain. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to address the deficiencies of the existing technology and provide a fiber bundle division method, system and storage medium based on fiber similarity.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] A fiber bundle segmentation method based on fiber similarity comprises the following steps:

[0007] importing a diffusion tensor image of the brain, performing probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and selecting a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers;

[0008] Determining the longest fiber length among a plurality of fibers, dividing the longest fiber length into a plurality of length intervals in ascending order, matching a plurality of fibers with the plurality of length intervals to form a plurality of initial fiber groups corresponding to the length intervals, and calculating the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups;

[0009] Merging the fibers in the corresponding initial fiber groups according to the first clustering threshold and the multiple initial similarity matrices using a hierarchical clustering algorithm to obtain multiple fiber groups, each fiber group including multiple different fiber clusters and multiple unmerged remaining fibers;

[0010] The similarities between the plurality of fiber clusters and the plurality of remaining fibers among the plurality of fiber groups are calculated respectively by a fiber similarity algorithm to obtain an initial clustering similarity matrix, and the plurality of fiber clusters of all fiber groups and the plurality of remaining fibers are merged by a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters;

[0011] The similarities between the multiple large fiber clusters and the multiple small fiber clusters are calculated respectively by a fiber similarity algorithm to obtain a cluster similarity matrix. The multiple large fiber clusters and the multiple small fiber clusters are merged according to the third clustering threshold and the cluster similarity matrix by a hierarchical clustering algorithm to obtain a fiber clustering result consisting of multiple clusters.

[0012] Another technical solution of the present invention to solve the above technical problems is as follows:

[0013] A fiber bundle partitioning system based on fiber similarity, comprising:

[0014] a preprocessing module, configured to import a diffusion tensor image of the brain, perform probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and select a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers;

[0015] a similarity calculation module, configured to determine the longest fiber length among a plurality of fibers, divide the longest fiber length into a plurality of length intervals in ascending order, match a plurality of fibers with the plurality of length intervals, and divide the fibers into a plurality of initial fiber groups corresponding to the plurality of length intervals; and calculate the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups;

[0016] The intra-group clustering module is configured to merge the fibers in the initial fiber group according to a first clustering threshold and the initial similarity matrix by using a hierarchical clustering algorithm, so as to obtain a plurality of fiber groups, each of which comprises a plurality of different fiber clusters and a plurality of unmerged remaining fibers.

[0017] The inter-group clustering module is configured to calculate the similarity between the fiber clusters and the remaining fibers in the plurality of fiber groups by using a fiber similarity algorithm, so as to obtain an initial clustering similarity matrix, and to merge the fiber clusters and the remaining fibers in all fiber groups according to a second clustering threshold and the initial clustering similarity matrix by using a hierarchical clustering algorithm, so as to obtain a plurality of fiber large clusters and a plurality of fiber small clusters.

[0018] The inter-cluster clustering module is configured to calculate the similarity between the fiber large clusters and the fiber small clusters by using a fiber similarity algorithm, so as to obtain a clustering similarity matrix, and to merge the fiber large clusters and the fiber small clusters according to a third clustering threshold and the clustering similarity matrix by using a hierarchical clustering algorithm, so as to obtain a fiber clustering result composed of a plurality of clustering clusters.

[0019] Another technical solution of the present application for solving the above technical problem is as follows:

[0020] A fiber bundle division system based on fiber similarity, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the fiber bundle division method based on fiber similarity as described when executing the computer program.

[0021] Another technical solution of the present application for solving the above technical problem is as follows:

[0022] A computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the fiber bundle division method based on fiber similarity as described.

[0023] The present application has the following beneficial effects: the present application takes the distance similarity between fiber bundles as a feature, divides the fiber bundles into a plurality of fiber small clusters by using a hierarchical clustering algorithm, and then merges the small clusters into large clusters to form a final fiber bundle division result, that is, the similar fibers of the fiber bundles are merged into a cluster, so that the fibers in the cluster have similar shapes and directions, the fibers in the cluster have tightness, the separation degree between the clusters is improved, and high-precision and high-efficiency division of the fiber bundles is realized. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 A flowchart of the fiber bundle division method based on fiber similarity provided by the embodiment of the present application is shown in the figure.

[0025] Figure 2 A schematic diagram of a target fiber bundle provided by an embodiment of the present invention;

[0026] Figure 3 A schematic diagram of fiber clustering results of a target fiber bundle provided by an embodiment of the present invention;

[0027] Figure 4 A schematic diagram of the fiber bundle division process provided in an embodiment of the present invention;

[0028] Figure 5 This is a module block diagram of a fiber bundle segmentation system based on fiber similarity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0030] Fiber tracking algorithms estimate the local orientation field of white matter (WM) from diffusion tensor imaging (DTI), reconstruct the primary trajectories of the WM, and generate a dataset containing a three-dimensional representation of the WM fibers (i.e., a diffusion tensor image). Fiber tracking algorithms implement probabilistic streamline tracking, following the preferred direction of water molecule diffusion within each voxel to reconstruct trajectories represented by a series of midpoint coordinates in three-dimensional space. These trajectories are called "streamlines" or simply "fibers." Although they do not represent actual neural fibers, they are estimates of the primary trajectories of white matter tracts. White matter tracts are large clusters of adjacent, structurally similar fibers. They are key neural structures in the brain that play a connecting role, connecting different brain regions and facilitating information transfer. Techniques such as DTI allow for non-invasive investigation of the organizational structure and morphological characteristics of these fiber tracts, allowing for their classification and delineation. Accurate delineation of fiber tracts facilitates a more precise understanding of brain structural connectivity, functional brain networks, the pathological changes of neurological diseases, and the development of personalized treatment plans.

[0031] like Figures 1-4 As shown, an embodiment of the present invention provides a fiber bundle segmentation method based on fiber similarity, comprising the following steps:

[0032] importing a diffusion tensor image of the brain, performing probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and selecting a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers;

[0033] Determining the longest fiber length among a plurality of fibers, dividing the longest fiber length into a plurality of length intervals in ascending order, matching a plurality of fibers with the plurality of length intervals to form a plurality of initial fiber groups corresponding to the length intervals, and calculating the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups;

[0034] Merging the fibers in the corresponding initial fiber groups according to the first clustering threshold and the multiple initial similarity matrices using a hierarchical clustering algorithm to obtain multiple fiber groups, each fiber group including multiple different fiber clusters and multiple unmerged remaining fibers;

[0035] The similarities between the plurality of fiber clusters and the plurality of remaining fibers among the plurality of fiber groups are calculated respectively by a fiber similarity algorithm to obtain an initial clustering similarity matrix, and the plurality of fiber clusters of all fiber groups and the plurality of remaining fibers are merged by a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters;

[0036] The similarities between the multiple large fiber clusters and the multiple small fiber clusters are calculated respectively by a fiber similarity algorithm to obtain a cluster similarity matrix. The multiple large fiber clusters and the multiple small fiber clusters are merged according to the third clustering threshold and the cluster similarity matrix by a hierarchical clustering algorithm to obtain a fiber clustering result consisting of multiple clusters.

[0037] In embodiments of the present invention, a sampling hierarchical clustering algorithm offers significant advantages when processing large-scale fiber tracking data. It can group similar fibers into the same category based on their geometric or topological properties, thereby reducing data complexity. Clustering fiber bundles based on similarity can help accurately identify and segment fiber bundles associated with specific anatomical functions, while reducing the complexity of subsequent brain structural analysis and enabling a better understanding of the brain's structural and functional characteristics. Differences in fiber bundle morphology or connectivity can provide a basis for disease diagnosis and staging, and aid in neurosurgery planning, avoiding damage to critical fibers and thus designing personalized surgical treatment plans.

[0038] Preferably, relevant image processing tools are used to pre-process the diffusion tensor image DTI of the brain in NIFTI format, the gradient encoding file (.bval file) of the DTI in the magnetic field gradient application intensity, and the gradient encoding file (.bvec file) of the DTI in the magnetic field gradient application direction, to generate a mask file (nodif_brain_mask.nii.gz), tensor model fractional anisotropy (FA), mean diffusivity (MD) and other parameters for whole-brain probabilistic fiber tracking, thereby obtaining a whole-brain fiber data set, and generating the desired fiber bundle streamlines (i.e., target fiber bundles) according to the custom region of interest ROI, streamlines = {s1, s2, ..., s i ,…,s k}, k≥i, i≥1, where s i represents the i-th fiber in the fiber bundle to be divided.

[0039] It should be understood that the relevant image processing tools are FMRIB Software Library (FSL) software or mrtrix3 software. The mask file is used to define the area for fiber tracking and limit the tracking range. FA stands for fractional anisotropy, and the FA value is used to guide the fiber tracking algorithm to track fiber bundles along the main direction of water molecule diffusion; MD stands for mean diffusivity, which mainly reflects the overall characteristics of water molecule diffusion to assist in judging tissue status and optimizing tracking results. These files serve as input files for FSL software and provide a basis for fiber bundle tracking. The result of whole-brain probabilistic fiber tracking is a fiber dataset containing multiple fibers generated based on a diffusion tensor imaging (DTI) image. The fiber bundles to be divided (i.e., target fiber bundles) are generated from the fiber dataset, and the region of interest (ROI) of the individual target can be generated by registration with the region of interest (ROI) of the standard template.

[0040] Preferably, the longest fiber length is determined among multiple fibers, and the longest fiber length is divided into multiple length intervals in an increasing manner, including: counting the length of each fiber, taking the length L of the longest fiber max , the fiber length interval is [0,L max ], the fiber length interval is divided into c equal parts, and c initial fiber intervals (i.e., initial fiber group SI i )streamlineinterval={SI1,SI2,…,SI i ,…,SI c}, c≥1.

[0041] When the length of the longest fiber is L max=87.58 mm, and the fiber length interval is [0,87.58]. To facilitate the interval division, the interval is set to [0,90], and the fiber length interval is divided into 6 equal parts. The length intervals of the preliminary fiber intervals are (0,15], (15,30], (30,45], (45,60], (60,75], (75,90], that is, divided into 6 preliminary fiber intervals streamlineinterval = {SI1, SI2, …, SI6}.

[0042] It should be understood that the fiber bundle is a spatial structure, and the data of each fiber is generally stored in the form of three-dimensional coordinates. The three-dimensional coordinates are calculated using MATLAB tools to obtain the fiber length.

[0043] In an embodiment of the present invention, a plurality of preliminary fiber intervals are first divided, and the range of each interval is set. Fibers with a fiber length within the range of this preliminary fiber interval are divided into the interval, thereby partitioning the target fiber bundle, which can reduce the amount of data for subsequent fiber clustering.

[0044] Preferably, the similarity between each fiber in the multiple initial fiber groups is calculated using a fiber similarity algorithm to obtain an initial similarity matrix of the multiple initial fiber groups, including:

[0045] S11, obtaining the same number of cluster points on any two fibers according to the set sampling order, and obtaining multiple positive-sequence cluster points corresponding to any two fibers;

[0046] S12, calculating the distances between the positive order cluster points of the same sampling order in any two fibers using the Manhattan distance expression, and obtaining multiple forward Manhattan distances of the any two fibers;

[0047] S13, calculating the plurality of forward Manhattan distances using a similarity expression to obtain a forward similarity;

[0048] S14, performing reverse order processing on the plurality of positive order cluster points of one of any two fibers to obtain a plurality of reverse order cluster points;

[0049] S15, calculating the distances between the positive order cluster points and the corresponding reverse order cluster points of the same sampling order in any two fibers using a Manhattan distance expression, to obtain multiple reverse Manhattan distances of the any two fibers;

[0050] S16, calculating the multiple reverse Manhattan distances using a similarity expression to obtain reverse similarity;

[0051] S17, selecting the maximum value from the forward similarity and the reverse similarity to obtain the initial similarity between any two fibers;

[0052] S18, repeating S11-S17 until the similarity between each fiber in all the initial fiber groups is calculated to obtain the initial similarity matrix corresponding to the plurality of initial fiber groups.

[0053] Specifically, any one fiber is equidistantly sampled according to the set sampling parameters to obtain a plurality of sampling points (such as collecting 13 sampling points), and a plurality of clustering points are selected from the plurality of sampling points in the sampling order (such as selecting the first, fourth, seventh, tenth and thirteenth sampling points as the clustering points). The clustering points of the fibers (i.e., the plurality of forward clustering points of the initial fiber group) in each preliminary fiber interval are selected to calculate the fiber similarity, and the Manhattan distance of the corresponding clustering points between each fiber is calculated (such as the first point corresponding to the first point, the seventh point corresponding to the seventh point, etc.), to obtain the distance set D of each fiber, D={D1,D4,D7,D 10 13}, the distance calculation formula (i.e., the Manhattan distance expression) is as follows:

[0054] D bj-aj =|x bj -x aj |+|y bj -y aj |+|z bj -z aj |,

[0055] wherein a, b∈(1, k), k represents the number of fibers, j∈{1, 4, 7, 10, 13}, D bj-aj represents the Manhattan distance between the jth sampling point of fiber s b and the jth sampling point of fiber s a .

[0056] The Manhattan distances of the corresponding five sampling points (i.e., the plurality of forward clustering points) between the two fibers are summed and averaged, and then the reciprocal is taken to obtain the similarity, and the calculation formula (i.e., the similarity expression) is as follows:

[0057]

[0058] wherein D E(b-a) is the similarity between the forward fibers (i.e., the forward similarity), and 0<D E(b-a) <1.

[0059] The fiber is flipped and the similarity is calculated, including:

[0060] ​For the two fibers after calculating the forward similarity, select one of them, reverse the order of its five sampling points, calculate the Manhattan distance between the five sampling points of one fiber and the five sampling points of the reversed fiber, and calculate the fiber flip similarity (i.e., reverse similarity) based on the obtained five Manhattan distances. The calculation formula is as follows:

[0061]

[0062] D F(b-a) =D Fb-a =D b-Fa ,

[0063] Among them, D′ bj-aj Denotes the Manhattan distance of the j-th sampling point after reverse order, D F(b-a) Indicates the similarity of flipped fibers, D Fb-a For flipping fibers Fb With fiber a The similarity between b-Fa Fiber b With flipped fibers Fa The similarity between <D F(b-a) =D Fb-a =D b-Fa <1;

[0064] Take the positive fiber similarity D E(b-a) Similarity with flipped fiber D F(b-a) The maximum value of the two fibers is taken as the similarity D b-a , as the data of the similarity matrix, the calculation formula is as follows:

[0065] D b-a =max(D E(b-a) ,D F(b-a) ),

[0066] Among them, D b-a As the similarity between two fibers, 0 <D b-a <1;

[0067] Multiple similarities are obtained by calculating each fiber pairwise in the preliminary fiber interval to construct an initial similarity matrix.

[0068] It should be understood that if the three-dimensional coordinates of the five positive-order clustering points of a fiber are P1 = (10, 15, 20), P2 = (12, 18, 25), P3 = (14, 20, 30), P4 = (16, 23, 35) and P5 = (18, 25, 40), flipping the fiber is a simulated flipping, and the five positive-order clustering points are arranged in reverse order. The three-dimensional coordinates of the five reverse-order clustering points are P1′ = (18, 25, 40), P2′ = (16, 23, 35), P3′ = (14, 20, 30), P4′ = (12, 18, 25) and P5′ = (10, 15, 20).

[0069] Since the spatial arrangement of the fibers themselves remains unchanged, flipping them changes their orientation but does not alter their geometry or length. Fiber bundles have directionality in three-dimensional space, and the orientation of a fiber bundle may have the same biological significance as its reversed orientation in certain analyses. Therefore, flipping fibers prevents the same fibers from being mistakenly identified as different clusters (i.e., avoiding low similarity).

[0070] In an embodiment of the present invention, the Manhattan distance of corresponding sampling points on each pair of fibers is calculated, and then the similarity of the two fibers is calculated. By flipping the fibers to avoid the same fiber being mistakenly regarded as a different cluster, the initial similarity matrix of each initial fiber group is obtained, and clustering is performed based on similarity.

[0071] Preferably, the S11 includes:

[0072] The fiber length of any fiber is calculated according to the set sampling parameters to obtain the sampling distance, multiple sampling points are obtained on any fiber according to the sampling distance, cluster points are selected from the multiple sampling points according to the set sampling order to obtain multiple positive-order cluster points, and the remaining fibers are processed in this process to obtain multiple positive-order cluster points corresponding to any two fibers.

[0073] Specifically, the sampling parameter is set to 13, one end of the fiber is set as the starting point and the other end is set as the end point, and each fiber of the target fiber bundle is sampled at equal distances in the order from the starting point to the end point, obtaining 13 sampling points, s i ={(x1,y1,z1), (x2,y2,z2),…,(x j ,y j ,z j ),…,(x 13 ,y 13 ,z 13 )},1≤j≤13,(x j ,y j ,z j ) represents the jth sampling point, x j ,y j and zb The voxel coordinates on the x, y, and z axes corresponding to the fiber sampling point are represented respectively. Five of the points are selected as clustering points in the order from the starting point to the end point of the fiber. These five points are the center point of the fiber (x7, y7, z7), the starting point of the fiber (x1, y1, z1), and the end point (x 13 ,y 13 ,z 13 ) two endpoints, the midpoint between the starting point and the center point (x4, y4, z4), and the midpoint between the end point and the center point (x 10 ,y 10 ,z 10 ) as multiple positive order clustering points.

[0074] In this embodiment of the present invention, a fixed number of cluster points are sampled for each fiber, reducing the data size and significantly reducing the time complexity of calculating distance or similarity matrices. Equidistant sampling evenly distributes points to extract the fiber's global shape, reducing the impact of noise while preserving the fiber's key morphological features. The same number of cluster points is collected for each fiber, allowing the subsequent point-by-point calculation of the coordinates of two fibers to measure the similarity between the fibers using the distance between the cluster points.

[0075] Preferably, the fibers in the corresponding initial fiber groups are merged according to the first clustering threshold and the multiple initial similarity matrices by using a hierarchical clustering algorithm to obtain multiple fiber groups, including:

[0076] S21, selecting any initial similarity that reaches a first clustering threshold from any of the initial similarity matrices as a cluster similarity, merging two fibers corresponding to the cluster similarity to obtain a fiber cluster, and processing the fibers corresponding to all initial similarities in this manner to obtain a plurality of different fiber clusters of any of the initial fiber groups and a plurality of unmerged remaining fiber clusters;

[0077] S22, calculating the similarities between the plurality of fiber clusters and the plurality of remaining fiber clusters respectively using a fiber similarity algorithm to obtain a cluster similarity matrix;

[0078] S23, looping S21-S22, processing the cluster similarity matrix generated in each loop, the plurality of fiber clusters, and the plurality of remaining fiber clusters until no similarity reaching the first clustering threshold can be screened out, thereby obtaining a fiber group consisting of a plurality of different fiber clusters and a plurality of unmerged remaining fibers;

[0079] In this way, S21-S23 are executed to process the fibers in all the initial fiber groups to obtain multiple fiber groups.

[0080] Specifically, the clustering algorithm used is agglomerative hierarchical clustering, which is a bottom-up clustering algorithm, and the link criterion selected is average link; when clustering starts, each fiber is initially regarded as an independent cluster, that is, there are k clusters initially, and each cluster contains only one fiber; at each step of the clustering process, the two clusters with the largest similarity in the similarity matrix (since the similarity is the inverse of the Manhattan distance between the two fibers, that is, the Manhattan distance is the smallest) are found, and these two clusters are merged to form a new cluster, and then the fiber similarity algorithm is used to calculate the similarity between the new cluster and other clusters (including other new clusters and unmerged clusters), and the similarity matrix is ​​synchronously updated to reflect the Manhattan distance between the new cluster and other clusters.

[0081] When two clusters are merged into a new cluster, five cluster points on the centroid line of the new cluster are selected as the basis for calculating the Manhattan distance. The process of calculating the similarity between the two clusters (i.e., the new cluster and other clusters) by the fiber similarity algorithm is the same as the process of calculating the similarity between each fiber in the multiple initial fiber groups by the fiber similarity algorithm.

[0082] In hierarchical clustering, the clustering threshold is used to control when to stop the clustering process. If the threshold is not set, the clustering process will continue to merge similar clusters until all fibers are merged into one cluster, which is contrary to the clustering algorithm. Therefore, the first clustering threshold D1 is set (depending on the actual situation, it is set to 0.15), 0 <D1<1,两个簇的相似度为 Among them, c m with c n is a cluster, 1≤m≤k, 1≤n≤k, judge Is it true? If so, then c m and c n Merge into a new cluster, otherwise the two are not merged; then calculate the similarity between the new cluster and other clusters, compare the similarity between the two clusters with the first clustering threshold D1, and repeat the merging process until all similarities are less than the first clustering threshold D1, and no cluster can be merged into a new cluster of fibers, that is, the fiber clustering is completed;

[0083] Each preliminary fiber interval (i.e., initial fiber group) is hierarchically clustered, and each preliminary fiber interval SI p We get cluster C p ={C p1 ,C p2 ,C p3 ,…,C pi}, where i ≥ 1, p ∈ {1, 6}, i is the number of clusters in each preliminary fiber interval.

[0084] In an embodiment of the present invention, fibers that can be merged are screened out from the similarity matrix according to a first clustering threshold and merged, and the similarity between the merged fiber cluster and the remaining fibers is calculated. In this way, the fibers are continuously merged layer by layer according to the first clustering threshold until similar fibers are merged into one cluster, thereby completing the initial category division within the interval of the target fiber bundle.

[0085] Preferably, similarities between the plurality of fiber clusters and the plurality of remaining fibers between the plurality of fiber groups are calculated respectively by a fiber similarity algorithm to obtain an initial clustering similarity matrix, and the plurality of fiber clusters of all fiber groups and the plurality of remaining fibers are merged by a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters, including:

[0086] Hierarchical clustering is performed on the merged and unmerged fibers in all fiber groups. That is, the similarity between multiple fiber clusters and multiple remaining fibers in one fiber group and multiple fiber clusters and multiple remaining fibers in another fiber group is calculated pairwise. Two clusters (i.e., fiber clusters and fiber clusters, fiber clusters and remaining fibers, or remaining fibers and remaining fibers) with a similarity greater than or equal to the second clustering threshold are merged. The merged target fiber bundle includes multiple clusters (i.e., clusters containing multiple fibers after merging and clusters containing only one fiber before merging). Clusters with less than or equal to 9 fibers are considered small fiber clusters, while clusters with more than or equal to 10 fibers are considered large fiber clusters.

[0087] It should be understood that the process of calculating the similarity between two clusters using the fiber similarity algorithm is the same as the process of calculating the similarity between each fiber in the multiple initial fiber groups using the fiber similarity algorithm. Merging the multiple fiber clusters of all fiber groups with the multiple remaining fibers using the hierarchical clustering algorithm according to the second clustering threshold and the initial clustering similarity matrix is ​​the same as merging the fibers in the corresponding initial fiber groups using the hierarchical clustering algorithm according to the first clustering threshold and the multiple initial similarity matrices. The second clustering threshold D2 needs to be less than the first clustering threshold D1 and is set to 0.09 to ensure greater compactness and separation of the fiber bundles.

[0088] In the embodiment of the present invention, all fiber groups, that is, all fibers, are clustered, and the target fiber bundles are classified into categories in a full range.

[0089] Preferably, the similarities between the multiple large fiber clusters and the multiple small fiber clusters are calculated respectively by a fiber similarity algorithm to obtain a cluster similarity matrix, and the multiple large fiber clusters and the multiple small fiber clusters are merged according to the third clustering threshold and the cluster similarity matrix by a hierarchical clustering algorithm to obtain multiple fiber clustering results.

[0090] The fiber clustering result consisting of a plurality of clusters is obtained, including:

[0091] It is determined whether the number of fibers in the plurality of clusters is less than or equal to a preset number. If so, the corresponding clusters are treated as noise and deleted.

[0092] Specifically, set the merge distance threshold D R (i.e. the third clustering threshold), 0 <D R <1, set to 0.0625, as the basis for judging whether to merge small fiber clusters into large fiber clusters; calculate the similarity between each small fiber cluster and each large fiber cluster by using the fiber similarity algorithm, and the calculation process is the same as the process of calculating the similarity between each fiber in the multiple initial fiber groups by using the fiber similarity algorithm.

[0093] Based on the similarity value, the fiber cluster is made to find the fiber cluster with the greatest similarity. If the similarity is greater than the merge distance threshold D R , the small clusters are merged into the large cluster, otherwise they are not merged, and the above operation is repeated until no small fiber clusters can be merged into the large fiber cluster, thereby obtaining the merged large fiber cluster, the merged small fiber clusters, the unmerged large fiber clusters and the unmerged small fiber clusters; the process is the same as the process of merging the fibers in the corresponding initial fiber groups according to the first clustering threshold and multiple initial similarity matrices through the hierarchical clustering algorithm.

[0094] The merged results are screened. If the number of fibers in a small cluster is less than or equal to 3, the cluster is removed as a noise cluster.

[0095] In an embodiment of the present invention, after clustering the entire range of the target fiber bundle, it is clustered again so that fibers with similar structures and morphologies can be merged into one category. The white matter fibers in the target range are fully clustered, rather than just the fibers near one fiber. Similar structures are found in the entire brain to achieve high-precision category division.

[0096] like Figure 5 As shown, an embodiment of the present invention provides a fiber bundle segmentation system based on fiber similarity, comprising:

[0097] a preprocessing module, configured to import a diffusion tensor image of the brain, perform probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and select a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers;

[0098] a similarity calculation module, configured to determine the longest fiber length among a plurality of fibers, divide the longest fiber length into a plurality of length intervals in ascending order, match a plurality of fibers with the plurality of length intervals, and divide the fibers into a plurality of initial fiber groups corresponding to the plurality of length intervals; and calculate the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups;

[0099] an intra-group clustering module, configured to merge the fibers in the corresponding initial fiber groups according to a first clustering threshold and a plurality of the initial similarity matrices using a hierarchical clustering algorithm to obtain a plurality of fiber groups, each fiber group including a plurality of different fiber clusters and a plurality of unmerged remaining fibers;

[0100] an inter-group clustering module, configured to calculate the similarity between the plurality of fiber clusters and the plurality of remaining fibers between the plurality of fiber groups using a fiber similarity algorithm to obtain an initial clustering similarity matrix, and merge the plurality of fiber clusters of all fiber groups with the plurality of remaining fibers using a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters;

[0101] The inter-cluster clustering module is used to calculate the similarity between multiple large fiber clusters and multiple small fiber clusters respectively through a fiber similarity algorithm to obtain a cluster similarity matrix, and merge the multiple large fiber clusters and multiple small fiber clusters according to the third clustering threshold and the cluster similarity matrix through a hierarchical clustering algorithm to obtain a fiber clustering result consisting of multiple clusters.

[0102] Another technical solution of the present invention to solve the above technical problems is as follows:

[0103] A fiber bundle division system based on fiber similarity includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the fiber bundle division method based on fiber similarity as described above is implemented.

[0104] Another technical solution of the present invention to solve the above technical problems is as follows:

[0105] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the fiber bundle segmentation method based on fiber similarity is implemented.

[0106] The above-mentioned fiber bundle division system and storage medium based on fiber similarity can refer to the implementation content and beneficial effects of the fiber bundle division method based on fiber similarity described above, which will not be repeated here.

[0107] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0108] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is only a logical functional division. In actual implementation, other division methods may be used. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not implemented.

[0110] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected based on actual needs to achieve the objectives of the embodiments of the present invention.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A fiber bundle segmentation method based on fiber similarity, characterized in that: The steps include: importing a diffusion tensor image of the brain, performing probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and selecting a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers; Determining the longest fiber length among a plurality of fibers, dividing the longest fiber length into a plurality of length intervals in ascending order, matching a plurality of fibers with the plurality of length intervals to form a plurality of initial fiber groups corresponding to the length intervals, and calculating the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups; Merging the fibers in the corresponding initial fiber groups according to the first clustering threshold and the multiple initial similarity matrices using a hierarchical clustering algorithm to obtain multiple fiber groups, each fiber group including multiple different fiber clusters and multiple unmerged remaining fibers; The similarities between the plurality of fiber clusters and the plurality of remaining fibers among the plurality of fiber groups are calculated respectively by a fiber similarity algorithm to obtain an initial clustering similarity matrix, and the plurality of fiber clusters of all fiber groups and the plurality of remaining fibers are merged by a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters; The similarities between the multiple large fiber clusters and the multiple small fiber clusters are calculated respectively by a fiber similarity algorithm to obtain a cluster similarity matrix. The multiple large fiber clusters and the multiple small fiber clusters are merged according to the third clustering threshold and the cluster similarity matrix by a hierarchical clustering algorithm to obtain a fiber clustering result consisting of multiple clusters.

2. The fiber bundle dividing method according to claim 1, characterized in that: The similarity between each fiber in the multiple initial fiber groups is calculated using a fiber similarity algorithm to obtain an initial similarity matrix of the multiple initial fiber groups, including: S11, obtaining the same number of cluster points on any two fibers according to the set sampling order, and obtaining multiple positive-sequence cluster points corresponding to any two fibers; S12, calculating the distances between the positive order cluster points of the same sampling order in any two fibers using the Manhattan distance expression, and obtaining multiple forward Manhattan distances of the any two fibers; S13, calculating the plurality of forward Manhattan distances using a similarity expression to obtain a forward similarity; S14, performing reverse order processing on the plurality of positive order cluster points of one of any two fibers to obtain a plurality of reverse order cluster points; S15, calculating the distances between the positive order cluster points and the corresponding reverse order cluster points of the same sampling order in any two fibers using a Manhattan distance expression, to obtain multiple reverse Manhattan distances of the any two fibers; S16, calculating the multiple reverse Manhattan distances using a similarity expression to obtain reverse similarity; S17, selecting a maximum value from the forward similarity and the reverse similarity to obtain an initial similarity between any two fibers; S18. Repeat S11-S17 until the similarities between the fibers in all the initial fiber groups are calculated, and an initial similarity matrix corresponding to the multiple initial fiber groups is obtained.

3. The fiber bundle dividing method according to claim 2, characterized in that: Said S11 comprises: The fiber length of any fiber is calculated according to the set sampling parameters to obtain the sampling distance, multiple sampling points are obtained on any fiber according to the sampling distance, cluster points are selected from the multiple sampling points according to the set sampling order to obtain multiple positive-order cluster points, and the remaining fibers are processed in this process to obtain multiple positive-order cluster points corresponding to any two fibers.

4. The fiber bundle dividing method according to claim 1, characterized in that: The hierarchical clustering algorithm is used to merge the fibers in the corresponding initial fiber groups according to the first clustering threshold and the multiple initial similarity matrices to obtain multiple fiber groups, including: S21, selecting any initial similarity that reaches a first clustering threshold from any of the initial similarity matrices as a cluster similarity, merging two fibers corresponding to the cluster similarity to obtain a fiber cluster, and processing the fibers corresponding to all initial similarities in this manner to obtain a plurality of different fiber clusters of any of the initial fiber groups and a plurality of unmerged remaining fiber clusters; S22, calculating the similarities between the plurality of fiber clusters and the plurality of remaining fiber clusters respectively using a fiber similarity algorithm to obtain a cluster similarity matrix; S23, looping S21-S22, processing the cluster similarity matrix generated each time, the plurality of fiber clusters, and the plurality of remaining fiber clusters, until no similarity reaching the first clustering threshold can be screened out, thereby obtaining a fiber group consisting of a plurality of different fiber clusters and a plurality of unmerged remaining fibers; In this way, S21-S23 are executed to process the fibers in all the initial fiber groups to obtain multiple fiber groups.

5. The fiber bundle dividing method according to claim 1, characterized in that: The fiber clustering result obtained is composed of multiple clusters, including: It is determined whether the number of fibers in the plurality of clusters is less than or equal to a preset number. If so, the corresponding clusters are treated as noise and deleted.

6. A fiber bundle partitioning system based on fiber similarity, characterized in that: include: a preprocessing module, configured to import a diffusion tensor image of the brain, perform probabilistic fiber tracking on the diffusion tensor image to obtain a fiber dataset, and select a target fiber bundle from the fiber dataset, wherein the target fiber bundle includes a plurality of fibers; a similarity calculation module, configured to determine the longest fiber length among a plurality of fibers, divide the longest fiber length into a plurality of length intervals in ascending order, match a plurality of fibers with the plurality of length intervals, and divide the fibers into a plurality of initial fiber groups corresponding to the plurality of length intervals; and calculate the similarity between each fiber in the plurality of initial fiber groups using a fiber similarity algorithm to obtain an initial similarity matrix for the plurality of initial fiber groups; an intra-group clustering module, configured to merge the fibers in the corresponding initial fiber groups according to a first clustering threshold and a plurality of the initial similarity matrices using a hierarchical clustering algorithm to obtain a plurality of fiber groups, each fiber group including a plurality of different fiber clusters and a plurality of unmerged remaining fibers; an inter-group clustering module, configured to calculate the similarity between the plurality of fiber clusters and the plurality of remaining fibers between the plurality of fiber groups using a fiber similarity algorithm to obtain an initial clustering similarity matrix, and merge the plurality of fiber clusters of all fiber groups with the plurality of remaining fibers using a hierarchical clustering algorithm according to a second clustering threshold and the initial clustering similarity matrix to obtain a plurality of large fiber clusters and a plurality of small fiber clusters; The inter-cluster clustering module is used to calculate the similarity between multiple large fiber clusters and multiple small fiber clusters respectively through a fiber similarity algorithm to obtain a cluster similarity matrix, and merge the multiple large fiber clusters and multiple small fiber clusters according to the third clustering threshold and the cluster similarity matrix through a hierarchical clustering algorithm to obtain a fiber clustering result consisting of multiple clusters.

7. The fiber bundle dividing system according to claim 6, characterized in that: In the similarity calculation module, the similarity between each fiber in the multiple initial fiber groups is calculated using a fiber similarity algorithm to obtain an initial similarity matrix of the multiple initial fiber groups, including: a. Obtain the same number of cluster points on any two fibers according to the set sampling order, and obtain multiple positive-sequence cluster points corresponding to any two fibers; b. Calculate the distance between each positive order cluster point of the same sampling order in any two fibers using the Manhattan distance expression to obtain multiple positive Manhattan distances of any two fibers; c. Calculating the forward Manhattan distances of the plurality of said methods by a similarity expression to obtain a forward similarity; d. performing reverse order processing on the plurality of positive order cluster points of one of any two fibers to obtain a plurality of reverse order cluster points; e. Calculate the distances between the positive order cluster points and the corresponding reverse order cluster points of the same sampling order in any two fibers using the Manhattan distance expression to obtain multiple reverse Manhattan distances of any two fibers; f. Calculating the reverse Manhattan distances of the plurality of similarity expressions to obtain reverse similarity; g. Select the maximum value from the forward similarity and the reverse similarity to obtain the initial similarity between any two fibers; Repeat steps a to g until the similarities between the fibers in all the initial fiber groups are calculated, and obtain initial similarity matrices corresponding to the multiple initial fiber groups.

8. The fiber bundle dividing system according to claim 7, characterized in that: In the similarity calculation module, the same number of cluster points are obtained on any two fibers according to the set sampling order to obtain multiple positive-sequence cluster points corresponding to any two fibers, including: The fiber length of any fiber is calculated according to the set sampling parameters to obtain the sampling distance, multiple sampling points are obtained on any fiber according to the sampling distance, cluster points are selected from the multiple sampling points according to the set sampling order to obtain multiple positive-order cluster points, and the remaining fibers are processed in this process to obtain multiple positive-order cluster points corresponding to any two fibers.

9. A fiber bundle segmentation system based on fiber similarity, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the fiber bundle segmentation method based on fiber similarity according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fiber bundle segmentation method based on fiber similarity according to any one of claims 1 to 5 is implemented.

Images