Method, device, medium and product for determining cerebral vascular aging index

Abstract

This application discloses a method, device, medium, and product for determining a cerebral vascular aging index, relating to the field of image data processing. The method comprises: extracting the central axis of a cerebral vascular segmentation image using Voronoi covariance, then determining the tangent and normal plane corresponding to each voxel on the central axis using the λ-maximum segment tangent method; fitting a maximum circle in the corresponding normal plane for each voxel and determining the corresponding diameter; performing a three-dimensional reconstruction of the tubular tree structure based on the central axis and diameter; extracting multi-level standardized imaging features from the three-dimensionally reconstructed image, and inputting these features into a cerebral vascular biological age prediction model to obtain a cerebral vascular biological age prediction result; and calculating the cerebral vascular aging index by combining the cerebral vascular biological age prediction result with the user's actual age. This application enables quantitative and accurate assessment of cerebral vascular aging.

Description

Technical Field

[0001] The present application relates to the field of image data processing, and in particular to a method, device, medium and product for determining a cerebral vascular aging index. Background Art

[0002] Due to the unique nature of intracranial blood vessels being encased by the skull, many methods used to assess vascular elasticity and stiffness in peripheral vessels cannot be performed intracranially. Compared to extracranial vessels, intracranial vessels possess significant structural peculiarities, such as a thin adventitia, the absence of an external elastic layer, and vasa vasorum. Furthermore, the characteristics of intracranial atherosclerotic plaques differ from those in the neck vessels, with intracranial hemorrhage and calcified plaques exhibiting lower levels than those outside the skull.

[0003] Abnormalities in the cerebral vascular walls (such as thickening, sclerosis, and plaque formation) are important risk factors for stroke, but conventional imaging cannot quantitatively analyze the characteristics of the intracranial vascular walls and cavities. No imaging method for evaluating the brain can comprehensively reflect the characteristics of the intracranial vascular cavities and vascular walls from multiple perspectives, and therefore cannot achieve quantitative and accurate assessment of cerebral vascular aging. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, medium and product for determining the cerebral vascular aging index, which can achieve quantitative and accurate assessment of cerebral vascular aging.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for determining a cerebral vascular aging index, comprising:

[0007] Obtaining a magnetic resonance image of the brain of the user to be determined;

[0008] Obtain cerebral vascular segmentation images based on magnetic resonance images;

[0009] The central axis of the cerebral vascular segmentation image was extracted using Voronoi covariance;

[0010] The λ-maximum segment tangent method is used to determine the tangent line corresponding to each voxel on the central axis, and the normal plane on each voxel is determined based on the tangent line;

[0011] For each voxel on the central axis, fit the largest circle in the corresponding normal plane and determine the diameter of the circle corresponding to the voxel;

[0012] The tubular tree-like structure in the cerebral vascular segmentation image is reconstructed in three dimensions by combining the central axis and diameter to obtain a 3D cerebral vascular segmentation image.

[0013] Extract multi-level standardized imaging features based on 3D images of cerebral vascular segmentation;

[0014] Get the age of the user to be determined;

[0015] Constructing a cerebrovascular biological age prediction model; the cerebrovascular biological age prediction model is a neural network model constructed based on a generalized linear model;

[0016] Multi-level standardized imaging features were input into the cerebrovascular biological age prediction model to obtain the cerebrovascular biological age prediction results;

[0017] The cerebrovascular aging index was obtained based on the cerebrovascular biological age prediction results and age.

[0018] Optionally, obtaining a cerebral blood vessel segmentation image based on the magnetic resonance image includes:

[0019] Preprocessing the magnetic resonance image to obtain a preprocessed image;

[0020] Constructing a cerebral vascular tissue segmentation model; the cerebral vascular tissue segmentation model is a network model constructed and trained by introducing an attention gating module into the skip connection of a 3D-UNet convolutional neural network;

[0021] Inputting the preprocessed image into the cerebral vascular tissue segmentation model to obtain a segmented image;

[0022] The segmented image is post-processed to obtain the cerebral blood vessel segmented image.

[0023] Optionally, preprocessing the magnetic resonance image to obtain a preprocessed image includes:

[0024] performing brain tissue-specific identification and segmentation on the magnetic resonance image to obtain a brain tissue structure image;

[0025] The brain tissue structure image is transformed into the same anatomical coordinates using the linear rigid body transformation and spline interpolation method to obtain the transformed image;

[0026] Performing image noise reduction processing on the converted image using an adaptive non-local means algorithm to obtain a denoised image;

[0027] removing magnetic resonance image artifacts caused by B0 field inhomogeneity in the denoised image using a signal intensity remapping method after Gaussian deconvolution to obtain an intermediate image;

[0028] Processing the intermediate image using a contrast-limited adaptive histogram equalization method to obtain a first signal-enhanced image;

[0029] Using a Sobel convolution method, identifying edge locations where a sudden change in signal intensity occurs in the first signal-enhanced image, and obtaining a second signal-enhanced image based on the identified edge locations;

[0030] The second signal-enhanced image is processed using a gamma correction method to obtain the preprocessed image.

[0031] Optionally, post-processing the segmented image to obtain the cerebral blood vessel segmented image includes:

[0032] A three-dimensional conditional random field model is used to penalize adjacent points with similar signal intensities on the segmented image to obtain a three-dimensional spatial segmented image; the adjacent points with similar signal intensities are pixels whose signal intensity difference is within a set range;

[0033] The 3D maximum connected component is found on the 3D space segmentation image, and unconnected signal noise in the 3D space segmentation image is removed based on the 3D maximum connected component to obtain the cerebral blood vessel segmentation image.

[0034] Optionally, the process of extracting basic features of the cerebral blood vessels based on the cerebral blood vessel segmentation three-dimensional image includes:

[0035] Counting the number of voxels with positive labels in the cerebral blood vessel segmentation three-dimensional image, and obtaining the absolute length of the cerebral blood vessels based on the number of voxels;

[0036] Acquiring an individual brain tissue volume, and obtaining a relative cerebral blood vessel length based on the absolute cerebral blood vessel length and the individual brain tissue volume, and using the relative cerebral blood vessel length as the cerebral blood vessel length;

[0037] determining a voxel volume based on an image resolution, and obtaining an absolute volume of cerebral blood vessels in the cerebral blood vessel segmentation three-dimensional image based on a statistical number of the voxels;

[0038] A relative cerebral vascular volume is obtained based on the absolute cerebral vascular volume and the individual brain tissue volume, and the relative cerebral vascular volume is used as the volume of the cerebral vascular.

[0039] Optionally, the process of extracting cerebral blood vessel geometric features based on the cerebral blood vessel segmentation three-dimensional image includes:

[0040] In the 3D image of cerebral vascular segmentation, the curvature radius and curvature degree of each voxel on the central axis in 3D space are determined according to the tangent vector flip angle and Frenet frame respectively.

[0041] Determining the average vascular curvature radius and the average vascular tortuosity of each brain region in the 3D cerebral vascular segmentation image;

[0042] The cerebral vascular curvature radius is obtained based on the curvature radius of each voxel in three-dimensional space and the average vascular curvature radius of the brain region;

[0043] The curvature of cerebral blood vessels is obtained based on the curvature of each voxel in three-dimensional space and the average curvature of blood vessels in the brain region.

[0044] Optionally, the process of extracting cerebral vascular topological features based on the cerebral vascular segmentation three-dimensional image includes:

[0045] Based on the three-dimensional image of cerebral vascular segmentation, a tree structure is used to characterize the adjacency relationship of each voxel on the central axis, bifurcation points are obtained, and the number of bifurcations and the spatial distribution of the bifurcation points are counted;

[0046] Determine the angle between the tangent vectors of the adjacent voxels at the bifurcation point;

[0047] determining an average bifurcation angle and a cerebral vascular bifurcation density in each brain region of the cerebral vascular segmentation three-dimensional image based on the number of bifurcations and the spatial distribution of bifurcation points;

[0048] The overall bifurcation angle characteristics of cerebral vessels are determined based on the angle between the tangent vectors of adjacent voxels and the average bifurcation angle;

[0049] The process of extracting morphological features of cerebral blood vessels based on the cerebral blood vessel segmentation three-dimensional image includes:

[0050] Obtain cerebral vascular segmentation images of healthy people, and iteratively register the cerebral vascular segmentation images in healthy people to obtain a population cerebral vascular distribution density map;

[0051] Nonlinearly registering the cerebral blood vessel segmentation three-dimensional image with the population cerebral blood vessel distribution density map in a nonlinear registration manner, and obtaining a transformed Jacobian matrix;

[0052] The 3D image of the cerebral blood vessels segmented after normalization and registration with the Jacobian matrix is ​​used to obtain the distribution density of the cerebral blood vessels in the standard atlas space.

[0053] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-mentioned method for determining the cerebral vascular aging index.

[0054] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for determining the cerebral vascular aging index.

[0055] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for determining the cerebral vascular aging index.

[0056] According to the specific embodiments provided in this application, this application has the following technical effects:

[0057] This application provides a method, device, medium, and product for determining a cerebrovascular aging index. This method predicts the biological age of cerebrovascular vessels by integrating a multi-feature fusion index based on cerebrovascular features (i.e., a multi-level standardized imaging feature that includes basic cerebrovascular features, cerebrovascular geometric features, cerebrovascular topological features, and cerebrovascular morphological features). This method offers a qualitative improvement over methods that only reflect a single aspect of cerebrovascular aging. By defining the model output as the biological age of the cerebrovascular vessels and comparing it with the user's actual physical age to obtain a cerebrovascular aging index, the method can quantitatively and objectively measure the degree of cerebrovascular aging seen in the user's imaging, thereby achieving an accurate assessment of cerebrovascular aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0059] Figure 1 A schematic flow chart of a method for determining a cerebral vascular aging index according to an embodiment of the present application;

[0060] Figure 2 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0062] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0063] In an exemplary embodiment, the present application provides a method for determining a cerebral vascular aging index, which is executed by a computer device. Specifically, the method can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is described by taking the application of the method to a server as an example. Figure 1 As shown, the method includes:

[0064] Step 100: Obtain a magnetic resonance image of the brain of the user to be determined.

[0065] Step 101: Obtain a cerebral blood vessel segmentation image based on a magnetic resonance image.

[0066] Step 102: Use Voronoi covariance to extract the central axis of the cerebrovascular segmentation image. For example, first perform centerline estimation on the cerebrovascular segmentation image. Based on the Voronoi covariance measure (VCM), the central axis of the cerebrovascular segmentation is stably extracted to reduce center point identification drift and voxel discontinuity issues at cerebrovascular bifurcations.

[0067] Step 103: Use the λ-maximal segment tangent method to determine the tangent corresponding to each voxel on the central axis, and determine the normal plane of each voxel based on the tangent. For example, based on the extraction of the central axis of the cerebral blood vessels, the λ-maximal segment tangent method (λ-MST) is used to calculate the tangent corresponding to each voxel on the central axis, and then further calculate the normal plane of each voxel on the central axis. The square axis method, which is a weighted average of the normal planes of adjacent voxels, is used to obtain a robust estimate of the normal plane of each voxel on the central axis.

[0068] Step 104: For each voxel on the central axis, fit a maximum circle in the corresponding normal plane, and determine the diameter of the circle corresponding to the voxel.

[0069] Step 105: Perform a 3D reconstruction of the tubular tree-like structure in the segmented cerebral vessel image using the central axis and diameter to obtain a 3D segmented cerebral vessel image. This step effectively prevents small local errors introduced by the structural segmentation algorithm from being amplified during vascular feature estimation, thereby ensuring the robustness of the 3D reconstruction.

[0070] Step 106: Extract multi-level standardized imaging features based on the segmented 3D cerebral vascular image. The multi-level standardized imaging features include basic cerebral vascular features, geometric features, topological features, and morphological features. Basic cerebral vascular features include the length and volume of cerebral vessels, as well as the diameter and length of local brain regions. Local brain regions are determined on a voxel basis. Geometric features include the radius of curvature and the degree of tortuosity. Topological features include the angle of cerebral vascular bifurcation points and the density of cerebral vascular bifurcations. Morphological features include the distribution density of cerebral vessels in the standard atlas space.

[0071] Step 107: Obtain the age of the user to be determined.

[0072] Step 108: Construct a cerebrovascular biological age prediction model. The cerebrovascular biological age prediction model is a neural network model constructed based on a generalized linear model.

[0073] Step 109: Input the multi-level standardized imaging features into the cerebrovascular biological age prediction model to obtain a cerebrovascular biological age prediction result.

[0074] Step 110: Obtain a cerebrovascular aging index based on the cerebrovascular biological age prediction result and age.

[0075] In another exemplary embodiment of the present application, the magnetic resonance image obtained is a TOF-MRA (Time-of-Flight Magnetic Resonance Angiography) magnetic resonance image as an example, and the implementation process of the above step 101 is described, including:

[0076] 1. Preprocess the TOF-MRA magnetic resonance image to obtain a preprocessed image, for example:

[0077] 11. Perform brain tissue-specific segmentation on the TOF-MRA image, removing non-brain structures such as the scalp, skull, facial features, and neck to obtain a brain tissue structure image. This step is performed to eliminate interference from non-brain tissue image signals on subsequent processing.

[0078] 12. Use linear rigid body transformation and spline interpolation to transform brain tissue structural images to the same anatomical coordinates to obtain a transformed image. For example, for TOF-MRA magnetic resonance images, a linear rigid body transformation with 6 degrees of freedom and spline interpolation are used to align T1-weighted images of the same individual and resample them to the same image space. The purpose of this step is to transform each sequence image at different voxel coordinates to the same anatomical coordinates, facilitating the integration of cross-sequence signal information.

[0079] 13. Use the adaptive non-local means algorithm to perform image denoising on the converted image to obtain a denoised image to remove Gaussian noise that may exist in TOF-MRA magnetic resonance images.

[0080] 14. The signal intensity remapping method after Gaussian deconvolution is used to remove the magnetic resonance image artifacts caused by B0 field inhomogeneity in the denoised image, and an intermediate image is obtained to remove the common artifact signals in TOF-MRA magnetic resonance images and improve the image signal-to-noise ratio.

[0081] 15. Use the contrast-limited adaptive histogram equalization method to process the intermediate image to obtain a first signal-enhanced image.

[0082] Due to the limitations of vascular imaging magnetic resonance sequences such as TOF-MRA, the signal enhancement amplitude of small blood vessels is significantly lower than that of large vessels, making it difficult to identify small blood vessels. To address this issue, step 15 is performed to ensure that the signals of cerebral vessels of different scales can achieve similar enhancement amplitudes.

[0083] 16. Due to the partial volume effect, the signal at the edge of a vessel is significantly lower than that at its center, making it difficult to identify. To address this issue, this embodiment uses the Sobel convolution method to identify edge locations where sudden changes in signal intensity occur in the first signal-enhanced image. This method achieves specific enhancement of the vessel edge signal, improving the contrast between the vessel and surrounding non-vascular tissue. A second signal-enhanced image is generated based on the identified edge locations. This step ensures that cerebral vessels at different distances from the centerline achieve similar signal enhancement.

[0084] 17. Gamma correction is used to process the second signal-enhanced image to obtain a preprocessed image. Gamma correction nonlinearly enhances the vascular tissue signal (high signal) and suppresses the non-vascular tissue signal (low signal) in the MRI image by adjusting the transformation coefficient Gamma. The transformation coefficient Gamma acts as a processing hyperparameter, controlling the relative magnitude of the enhanced and suppressed signals based on the nature of the processed image to achieve better image contrast.

[0085] 2. Construct a cerebrovascular tissue segmentation model. The cerebrovascular tissue segmentation model is a trained network model constructed by introducing an attention gating module into the skip connections of the 3D-UNet convolutional neural network.

[0086] In practical applications, specific implementation methods for constructing a cerebral vascular tissue segmentation model may include:

[0087] 21. Build training and testing datasets.

[0088] Collect T1-weighted imaging and TOF-MRA paired data from multiple (e.g., 100) healthy individuals acquired using routine clinical scanning sequences using different equipment. After preprocessing the image data according to steps 11-17 above, multiple (e.g., two) neuroradiologists with extensive image annotation experience can independently annotate the cerebrovascular tissue signals in the MRI images. At least one senior neuroradiologist will conduct a comprehensive review and evaluation of the annotation results to complete the cerebrovascular tissue signal annotation of the multimodal MRI image data, ensuring the consistency and accuracy of the data annotation, and ultimately constructing the training and testing datasets.

[0089] 22. Build a deep neural network architecture.

[0090] A deep neural network model was constructed using a basic architecture combining 3D-UNet and an attention gating module, serving as the initial cerebrovascular tissue segmentation model. The overall 3D-UNet convolutional neural network employs an adaptive design, automatically adjusting hyperparameters such as batch size and network depth and width based on the spatial resolution and size of the input image. Furthermore, an attention gating module was introduced within the skip connections of the 3D-UNet convolutional neural network. Its basic form can be expressed as follows:

[0091] .

[0092] Where, and Represent the feature tensors of the encoding module and decoding module connected by the jump, represents the RELU activation function, represents the Sigmoid activation function, 、 and represents the linear transformation coefficient, as well as represents the bias coefficient, represents the processed image, Represents the SAct image after resampling.

[0093] Finally, the resampled SAct image is combined with the feature tensor on the decoding module Multiplying them together can fuse feature information at different scales and reduce background noise to a great extent.

[0094] 23. Training and testing of the initial cerebral vascular tissue segmentation model.

[0095] The initial cerebrovascular tissue segmentation model is trained and tested using a five-fold cross-validation approach based on the training and testing dataset constructed in step 21 above. To address the differences in specificity and sensitivity of vascular segmentation results at different scales during the vascular segmentation process, the Tversky function is introduced as the loss function for the initial cerebrovascular tissue segmentation model. Based on the Tversky function, a weighted Tversky loss is further proposed. This uses the inverse of the Euclidean distance between the voxel and the centerline as the mismatch loss weight, strengthening the topological structure constraints of the segmentation results and ensuring more consistent vascular segmentation results at all scales. By default, this algorithm selects the initial cerebrovascular tissue segmentation model with the best results as the final output model (i.e., the cerebrovascular tissue segmentation model). Users can also choose to deploy an average model.

[0096] 3. Input the preprocessed image into the cerebral vascular tissue segmentation model to obtain a segmented image.

[0097] 4. Post-process the segmented image to obtain a cerebral vascular segmentation image, for example:

[0098] 41. In the post-processing of the segmented image, a three-dimensional conditional random field model is used to penalize adjacent points with similar signal intensities on the segmented image to obtain a three-dimensional spatial segmented image. Adjacent points with similar signal intensities refer to pixels whose signal intensity difference is within a set range.

[0099] The three-dimensional conditional random field model takes into account the spatial continuity of vascular tissue. By establishing potential functions between pairs and at individual points, and penalizing adjacent points with similar signal intensities on magnetic resonance images with different segmentation labels on the segmented images, a more continuous and reasonable segmentation image in three-dimensional space (i.e., a three-dimensional spatial segmentation image) can be obtained.

[0100] 42. Find the three-dimensional maximum connected component on the three-dimensional spatial segmentation image (i.e., the cerebral vascular segmentation image after three-dimensional conditional random field post-processing), and remove the unconnected small blocks of signal noise in the three-dimensional spatial segmentation image based on the three-dimensional maximum connected component to obtain the cerebral vascular segmentation image.

[0101] In another exemplary embodiment of the present application, the basic features of cerebral blood vessels are mainly obtained by extracting the length and volume of individual tubular structures and the diameter and length of local brain regions. Based on this, the process of extracting the basic features of cerebral blood vessels based on the 3D image of cerebral blood vessel segmentation in step 106 includes:

[0102] 11) Count the number of voxels with positive labels in the 3D image of cerebral vascular segmentation, and obtain the absolute length of the cerebral vessels based on the number of voxels.

[0103] 12) Obtaining the individual's brain tissue volume, and calculating the relative cerebral vascular length based on the absolute cerebral vascular length and the individual's brain tissue volume, defining the relative cerebral vascular length as the cerebral vascular length. Considering that the size of an individual's brain tissue can significantly affect the length of cerebral vascular structures, this embodiment divides the absolute length by the individual's brain tissue volume to obtain the relative cerebral vascular length.

[0104] 13) Determine the voxel volume based on the voxel resolution, and obtain the absolute volume of the cerebral blood vessels in the cerebral blood vessel segmentation three-dimensional image based on the statistical number of voxels.

[0105] 14) Based on the absolute cerebral vascular volume and the individual brain tissue volume, a relative cerebral vascular volume is obtained, and the relative cerebral vascular volume is used as the cerebral vascular volume. For example, considering that the size of individual brain tissue can significantly affect the volume of cerebral vascular structures, this embodiment can also divide the absolute cerebral vascular volume by the individual brain tissue volume to obtain a relative volume, reflecting the average distribution density of cerebral vascular tissue in the entire brain tissue.

[0106] Furthermore, to determine the length and diameter of cerebral vessels in local brain regions, a two-step registration method can be used to nonlinearly register the MNI standard brain template with the cerebral vascular MRI images. The Harvard-Oxford brain parcellation map in the MNI standard brain space is then converted to the individual-level MRI image space. The local vessel length and diameter are calculated for each brain parcellation according to the process described above, steps 11) through 14), reflecting the heterogeneity of the spatial distribution of basic vascular characteristics across brain regions.

[0107] In another exemplary embodiment of the present application, the process of extracting cerebral blood vessel geometric features based on the cerebral blood vessel segmentation three-dimensional image in step 106 includes:

[0108] 21) In the three-dimensional image of cerebral vascular segmentation, the curvature radius and bending degree of each voxel on the central axis in three-dimensional space are determined based on the tangent vector flip angle and the Frenet frame.

[0109] 22) Determine the average vascular curvature radius and the average vascular tortuosity in each brain region of the 3D cerebral vascular segmentation image (or each brain region corresponding to the Harvard-Oxford brain partition map).

[0110] 23) The cerebral vascular curvature radius is obtained based on the curvature radius of each voxel in three-dimensional space and the average vascular curvature radius of the brain region.

[0111] 24) The degree of curvature of cerebral blood vessels is obtained based on the curvature of each voxel in three-dimensional space and the average curvature of blood vessels in the brain region to measure the geometric distribution characteristics of cerebral blood vessels in brain regions.

[0112] In another exemplary embodiment of the present application, the process of extracting cerebral vascular topological features based on the cerebral vascular segmentation three-dimensional image in step 106 includes:

[0113] 31) Based on the 3D image of cerebral vascular segmentation, the tree structure is used to represent the adjacency relationship of each voxel on the central axis to obtain the bifurcation points, and the number of bifurcations and the spatial distribution of bifurcation points are counted, thereby realizing the automatic identification of bifurcation points in the vascular tree structure.

[0114] 32) Determine the angle between the tangent vectors of the adjacent voxels at the bifurcation point. This angle is the bifurcation angle of the bifurcation point.

[0115] 33) Based on the number of bifurcations and the spatial distribution of bifurcation points, the average bifurcation angle and cerebrovascular bifurcation density are determined in each brain region of the cerebrovascular segmentation three-dimensional image.

[0116] 34) Based on the angle between the tangent vectors of adjacent voxels and the average bifurcation angle, the overall bifurcation angle characteristics of cerebral blood vessels are determined to reflect the distribution characteristics of vascular bifurcation statistics in the brain region space.

[0117] In another exemplary embodiment of the present application, the process of extracting Voxel based morphometry (VBM) features based on the 3D cerebral vessel segmentation image in step 106 includes:

[0118] 41) Obtain cerebral vascular segmentation images of healthy people, and iteratively align the cerebral vascular segmentation images of healthy people to obtain a population cerebral vascular distribution density map.

[0119] 42) Nonlinear registration is performed on the 3D image of cerebral vascular segmentation and the population cerebral vascular distribution density map, and the transformed Jacobian matrix is ​​obtained.

[0120] 43) Using Jacobian matrix-normalized registration of 3D cerebral vascular segmentation images, we can obtain the distribution density of cerebral vessels in the standard atlas space. This distribution density can be used to quantitatively assess differences in individual vascular network density and between groups at the local or global level.

[0121] In another exemplary embodiment of the present application, the implementation process of the above step 108 may include:

[0122] Step 1: Data collation and quality control:

[0123] The multi-level standardized imaging feature set data provided above was aligned with basic demographic indicators such as gender and age of the subjects. Outliers were detected and removed using the median absolute deviation (MAD). Finally, the data was structured into a data frame to facilitate subsequent downstream analysis.

[0124] Step 2: Construct a cerebrovascular biological age prediction model:

[0125] To ensure the interpretability of the cerebrovascular biological age prediction model and realize its direct clinical application value, this example uses a generalized linear model as the basic framework of the cerebrovascular biological age prediction model. On this basis, to prevent overfitting of the cerebrovascular biological age prediction model, the lasso method is used to apply an L1 norm penalty to the generalized linear model parameters. The specific formula cost function form is as follows:

[0126] .

[0127] Where, Representative About The cost function of are the parameters in the generalized linear model, represents the outcome variable of the i-th sample (i.e., physical age), Represents the imaging feature group data of the i-th sample, T Represents a matrix transpose operation. Represents the penalty hyperparameter, which needs to be set manually to control the feature L1 norm The degree of punishment.

[0128] In order to fully train the constructed initial model using data, the ensemble learning method can be used to perform bootstrap sampling on the training set data constructed in step 1 to obtain multiple subsets of the training set. Initial model training is performed on each subset to obtain multiple trained linear models (i.e., cerebrovascular biological age prediction models). Finally, the output results of these linear models are weighted averaged to obtain the final output result.

[0129] The data set is randomly divided into a training set and a test set. A ten-fold cross-validation training is performed on multiple models in the training set. The optimal model is selected as the cerebrovascular biological age prediction model (the model accepts individual-level imaging feature group data and basic demographic indicators such as gender and age as model input). The model is then validated in the test set. The model output is the biological age of the cerebrovascular vessels. The difference between the biological age of the cerebrovascular vessels and the individual's physical age is the cerebrovascular aging index proposed in this application, which can quantitatively and objectively measure the degree of cerebrovascular aging in patients' imaging. At the same time, the effect coefficient corresponding to each imaging feature in the cerebrovascular biological age prediction model is obtained. This coefficient can quantitatively evaluate the contribution of the imaging feature to the overall cerebrovascular aging index, indicating the imaging feature that has the greatest impact on vascular aging, which has extremely strong clinical indicative significance.

[0130] Based on the above description, compared to the current technology for evaluating cerebral vascular function based on single image analysis, this application integrates a multi-feature fusion index based on cerebral vascular function. Since aging is not reflected in only one aspect, by adopting this multi-feature fusion index, its accuracy is qualitatively improved compared to cerebral vascular aging that only reflects one aspect. By defining the model output as the biological age of the cerebral vessels and comparing it with the individual's physical age, a cerebral vascular aging index is obtained. This can quantitatively and objectively measure the degree of cerebral vascular aging in patients' imaging, providing clinicians with a new tool to assess the patient's vascular health status.

[0131] Furthermore, the present application combines technologies such as generalized linear models (GLM), LASSO regularization, and ensemble learning, and has significant innovation and advantages. Among them, the generalized linear model (GLM), as a classic statistical model, has strong interpretability. Through LASSO regularization, the generalized linear model can automatically select the most important imaging features, and each feature has a corresponding effect coefficient. This allows the present application to clearly know which imaging features have the greatest impact on the cerebrovascular aging index, thereby providing clinicians with intuitive explanations and guidance. LASSO regularization not only prevents the generalized linear model from overfitting, but also quantifies the contribution of each imaging feature to the cerebrovascular aging index through the effect coefficient. This quantitative assessment helps to identify the imaging features that have the greatest impact on vascular aging, provides a basis for exploring the potential mechanisms of vascular aging, and provides important clues for subsequent clinical research and optimization of treatment plans.

[0132] Furthermore, generalized linear models have a simple structure, are easy to implement and deploy, and are suitable for widespread application across diverse medical institutions. Compared to deep learning models, generalized linear models and LASSO regularization provide a more transparent model structure, enabling physicians to understand the model's decision-making process. This is particularly important in the medical field, as physicians need to have full confidence in the model's predictions. This allows the model to be more widely applied in clinical practice, avoiding the uncertainty inherent in the "black box" problem.

[0133] Going further, this application uses a basic structure that combines 3D-UNet and an attention gating module to construct a deep neural network model, which can not only achieve multi-scale end-to-end segmentation, but also improve the segmentation performance of the model. The multi-scale feature extraction capability of 3D-UNet combined with the dynamic weight adjustment of the attention gating module can better handle small or fuzzy boundaries while maintaining the global structure, thereby improving the accuracy of segmentation. The attention gating module can help the network reduce its dependence on noise and irrelevant areas, making the model more robust when facing low-quality or uneven medical images, reducing the risk of mis-segmentation. Attention mechanisms can help the network converge to the optimal solution faster because they can guide the network to focus on important features and optimize feature extraction efficiency.

[0134] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 2As shown. The computer device includes a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface and the input / output interface are connected to the system bus together. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data for determining the cerebral vascular aging index. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for determining the cerebral vascular aging index is implemented.

[0135] Those skilled in the art will understand that Figure 2 The structure shown in the figure is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0136] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0137] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0138] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0139] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0140] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processors involved in the various embodiments provided herein include, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), and data processing logic based on quantum computing.

[0141] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for determining a cerebral vascular aging index, characterized in that: include: Obtaining a magnetic resonance image of the brain of the user to be determined; Magnetic resonance images are TOF-MRA images; Preprocessing a TOF-MRA magnetic resonance image to obtain a preprocessed image includes: performing brain tissue-specific identification and segmentation on the TOF-MRA magnetic resonance image to obtain a brain tissue structure image; using a linear rigid body transformation and spline interpolation method to transform the brain tissue structure image to the same anatomical coordinates to obtain a transformed image; using an adaptive non-local means algorithm to perform image denoising on the transformed image to obtain a denoised image; using a signal intensity remapping method after Gaussian deconvolution to remove magnetic resonance image artifacts caused by B0 field inhomogeneity in the denoised image to obtain an intermediate image; using a limited contrast adaptive histogram equalization method to process the intermediate image to obtain a first signal enhanced image; using a Sobel convolution method to identify edge positions where signal intensity mutations occur in the first signal enhanced image, and obtaining a second signal enhanced image based on the identified edge positions; using a gamma correction method to process the second signal enhanced image to obtain a preprocessed image; A cerebral vascular tissue segmentation model is constructed; the cerebral vascular tissue segmentation model is a network model constructed and trained by introducing an attention gating module into the skip connections of a 3D-UNet convolutional neural network; wherein, the initial cerebral vascular tissue segmentation model is trained and tested based on a training and testing dataset using a five-fold cross-validation approach; the process of constructing the training and testing dataset includes: collecting T1-weighted imaging and TOF-MRA paired data from multiple healthy subjects acquired using conventional clinical scanning sequences using different equipment, preprocessing the image data, and independently annotating the cerebral vascular tissue signals in the magnetic resonance images to complete the cerebral vascular tissue signal annotation of the multimodal magnetic resonance image data, thereby constructing the training and testing dataset; Inputting the preprocessed image into the cerebral vascular tissue segmentation model to obtain a segmented image; performing post-processing on the segmented image to obtain a cerebral blood vessel segmentation image; The central axis of the cerebral vascular segmentation image was extracted using Voronoi covariance; The λ-maximum segment tangent method is used to determine the tangent line corresponding to each voxel on the central axis, and the normal plane on each voxel is determined based on the tangent line; For each voxel on the central axis, fit the largest circle in the corresponding normal plane and determine the diameter of the circle corresponding to the voxel; The tubular tree structure in the cerebral vascular segmentation image is reconstructed in three dimensions by combining the central axis and diameter to obtain a 3D cerebral vascular segmentation image. Extract multi-level standardized imaging features based on 3D images of cerebral vascular segmentation; Get the age of the user to be determined; Constructing a cerebrovascular biological age prediction model; the cerebrovascular biological age prediction model is a neural network model constructed based on a generalized linear model; Multi-level standardized imaging features were input into the cerebrovascular biological age prediction model to obtain the cerebrovascular biological age prediction results; The cerebrovascular aging index was obtained based on the cerebrovascular biological age prediction results and age.

2. The method for determining the cerebral vascular aging index according to claim 1, wherein: Post-processing the segmented image to obtain the cerebral blood vessel segmented image includes: A three-dimensional conditional random field model is used to penalize adjacent points with similar signal intensities on the segmented image to obtain a three-dimensional spatial segmented image; the adjacent points with similar signal intensities are pixels whose signal intensity difference is within a set range; The 3D maximum connected component is found on the 3D space segmentation image, and unconnected signal noise in the 3D space segmentation image is removed based on the 3D maximum connected component to obtain the cerebral blood vessel segmentation image.

3. The method for determining the cerebral vascular aging index according to claim 1, wherein: The process of extracting basic features of the cerebral blood vessels based on the cerebral blood vessel segmentation three-dimensional image includes: Counting the number of voxels with positive labels in the cerebral blood vessel segmentation three-dimensional image, and obtaining the absolute length of the cerebral blood vessels based on the number of voxels; Acquiring an individual brain tissue volume, and obtaining a relative cerebral blood vessel length based on the absolute cerebral blood vessel length and the individual brain tissue volume, and using the relative cerebral blood vessel length as the cerebral blood vessel length; determining a voxel volume based on an image resolution, and obtaining an absolute volume of cerebral blood vessels in the cerebral blood vessel segmentation three-dimensional image based on a statistical number of the voxels; A relative cerebral vascular volume is obtained based on the absolute cerebral vascular volume and the individual brain tissue volume, and the relative cerebral vascular volume is used as the volume of the cerebral vascular.

4. The method for determining the cerebral vascular aging index according to claim 1, wherein: The process of extracting cerebral blood vessel geometric features based on the cerebral blood vessel segmentation three-dimensional image includes: In the 3D image of cerebral vascular segmentation, the curvature radius and curvature degree of each voxel on the central axis in 3D space are determined according to the tangent vector flip angle and Frenet frame respectively. Determining the average vascular curvature radius and the average vascular tortuosity of each brain region in the 3D cerebral vascular segmentation image; The cerebral vascular curvature radius is obtained based on the curvature radius of each voxel in three-dimensional space and the average vascular curvature radius of the brain region; The curvature of cerebral blood vessels is obtained based on the curvature of each voxel in three-dimensional space and the average curvature of blood vessels in the brain region.

5. The method for determining the cerebral vascular aging index according to claim 1, wherein: The process of extracting cerebral vascular topological features based on the cerebral vascular segmentation three-dimensional image includes: Based on the three-dimensional image of cerebral vascular segmentation, a tree structure is used to characterize the adjacency relationship of each voxel on the central axis, bifurcation points are obtained, and the number of bifurcations and the spatial distribution of the bifurcation points are counted; Determine the angle between the tangent vectors of the adjacent voxels at the bifurcation point; determining an average bifurcation angle and a cerebral vascular bifurcation density in each brain region of the cerebral vascular segmentation three-dimensional image based on the number of bifurcations and the spatial distribution of bifurcation points; The overall bifurcation angle characteristics of cerebral vessels are determined based on the angle between the tangent vectors of adjacent voxels and the average bifurcation angle; The process of extracting morphological features of cerebral blood vessels based on the cerebral blood vessel segmentation three-dimensional image includes: Obtain cerebral vascular segmentation images of healthy people, and iteratively register the cerebral vascular segmentation images in healthy people to obtain a population cerebral vascular distribution density map; Nonlinearly registering the cerebral blood vessel segmentation three-dimensional image with the population cerebral blood vessel distribution density map in a nonlinear registration manner, and obtaining a transformed Jacobian matrix; The 3D image of the cerebral blood vessels segmented after normalization and registration with the Jacobian matrix is ​​used to obtain the distribution density of the cerebral blood vessels in the standard atlas space.

6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for determining the cerebral vascular aging index according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the cerebral vascular aging index according to any one of claims 1 to 5 is implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining the cerebral vascular aging index according to any one of claims 1 to 5 is implemented.

Images