Brain aging comprehensive index determination method and device, medium and product

Abstract

The invention discloses a brain aging comprehensive index determination method and device, a medium and a product, and relates to the field of image data processing, and the method comprises the steps: carrying out the preprocessing of T1, TOF-MRA and other images, and obtaining a brain tissue segmentation image; performing post-processing on the TOF-MRA magnetic resonance image to extract cerebrovascular image features; carrying out convolution feature extraction on the T1 and T2-FLAIR images by adopting a method of combining modules such as asymmetric convolution and the like, and compressing features to generate a convolution feature group; after the demographic indexes, the cerebrovascular image features and the convolution feature group are connected, a biological age prediction model is adopted to obtain a brain aging age prediction result, and a brain aging comprehensive index is obtained in combination with the actual age. According to the method, the change of intracranial great vessels can be identified, the early microvessel aging state can be reflected, the sensitivity to microvessel aging is improved, the limitations of low artificial feature extraction efficiency, poor consistency and the like are solved, and the comprehensive quantitative evaluation of brain aging is realized.

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 comprehensive index of brain aging. Background Art

[0002] Although some progress has been made in assessing peripheral vascular aging, the quantitative assessment technology for intracranial vascular aging still faces many challenges. Among them: (1) Limitations of single-modality imaging: Traditional imaging methods usually rely on single-modality imaging data, such as computed tomography (CT), conventional magnetic resonance imaging (MRI), etc. Although these methods can provide certain vascular morphological information, they cannot fully capture the multidimensional characteristics of vascular aging, especially for the aging state of microvessels, single-modality imaging often fails to reflect its early changes. For example, many structural features in T1-weighted imaging and magnetic resonance imaging fluid attenuated inversion recovery (FLuid Attenuated Inversion Recovery, T2-FLAIR) images are actually another manifestation of vascular aging, which may reflect an earlier state of microvascular aging. Therefore, it is difficult to fully assess the degree of cerebrovascular aging by relying solely on single-modality imaging data.

[0003] (2) Lack of sensitivity to microvascular aging: Existing imaging technologies and assessment methods mainly focus on structural changes in large blood vessels (such as wall thickening, plaque formation, etc.), while the aging state of microvessels is relatively neglected. Microvascular aging is one of the important risk factors for cerebrovascular disease, especially in the early stages, when microvascular changes may be the earliest pathological features. However, existing assessment methods are unable to effectively capture these subtle changes, resulting in an incomplete and inaccurate assessment of cerebrovascular aging.

[0004] (3) Limitations of manual feature extraction: Traditional vascular segmentation and feature extraction methods for time-of-flight magnetic resonance angiography (TOF-MRA) usually rely on manually designed algorithms. This method is not only time-consuming and labor-intensive, but also easily affected by subjective factors and difficult to fully capture the complex characteristics of vascular aging. Especially when processing multimodal imaging data, manual feature extraction methods often cannot fully utilize the complementary information between different modalities, limiting the performance and reliability of the model.

[0005] (4) Lack of quantitative assessment tools: Although there are some imaging-based vascular aging assessment methods, most of them remain at the qualitative or semi-quantitative level, lacking a unified standard that can quantitatively and objectively measure the degree of cerebrovascular aging. This means that clinicians lack a reliable reference indicator when assessing the vascular health status of patients, affecting early screening and risk assessment of the disease. Summary of the invention

[0006] In order to solve the above problems, the present application provides a method, device, medium and product for determining a comprehensive index of brain aging.

[0007] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a method for determining a comprehensive index of brain aging, comprising: Acquire T1-weighted imaging images, T2-FLAIR images, and TOF-MRA magnetic resonance images; Preprocessing the T1-weighted imaging image and the TOF-MRA magnetic resonance image to obtain a preprocessed image; Obtaining a cerebral vascular tissue segmentation image based on the preprocessed image; Post-processing the cerebral vascular tissue segmentation image based on the TOF-MRA magnetic resonance image to obtain a post-processed image; Extract cerebrovascular imaging features based on post-processed images; The convolution feature extraction of T1-weighted imaging image and T2-FLAIR image was performed by combining asymmetric convolution module and Squeeze-and-Excitation module to obtain T1-weighted imaging feature and T2-FLAIR image feature. By globally pooling and compressing T1-weighted imaging features and T2-FLAIR image features, a convolution feature group of T1-weighted imaging images and T2-FLAIR images is generated, each feature dimension of which is a set value; Obtain demographic indicators; demographic indicators include gender and age; The demographic indicators and cerebrovascular imaging features were connected with the convolutional feature groups of T1-weighted imaging images and T2-FLAIR images to generate a cerebrovascular aging imaging representation group; Construct a biological age prediction model; The cerebrovascular aging image characterization group is input into the biological age prediction model to obtain the brain aging age prediction result; The comprehensive index of brain aging was obtained based on the predicted results of brain aging age and the actual age of the evaluated subjects.

[0008] Optionally, obtaining a cerebral vascular tissue segmentation image based on the preprocessed image includes: Construct a training and testing data set; the training and testing data set includes paired data of T1-weighted imaging images and TOF-MRA magnetic resonance images; Based on the 3D-UNet convolutional neural network, the attention gating module is combined to build a deep neural network model; The deep neural network model is trained and tested using the training and testing data set until an output error of the deep neural network model after training and testing reaches a set threshold, thereby obtaining a trained deep neural network model; The trained deep neural network model is used as a cerebrovascular tissue segmentation model, and the preprocessed image is input into the cerebrovascular tissue segmentation model to obtain the cerebrovascular tissue segmentation image.

[0009] Optionally, based on the Tversky function, a weighted Tversky loss is used to construct a loss function of the cerebral vascular tissue segmentation model.

[0010] Optionally, preprocessing the T1-weighted imaging image and the TOF-MRA magnetic resonance image to obtain a preprocessed image includes: Perform brain tissue-specific identification and segmentation on TOF-MRA magnetic resonance images to obtain brain tissue structure images; Using a linear rigid body transformation and spline interpolation method, based on the brain tissue structure image, the T1-weighted imaging image and the TOF-MRA magnetic resonance image are registered, and the registered structure is resampled to the same image space to obtain a converted image; Adaptive non-local means algorithm is used to perform image denoising on TOF-MRA magnetic resonance images to obtain denoised images. Using a signal intensity remapping method after Gaussian deconvolution, magnetic resonance image artifacts caused by B0 field inhomogeneity in the denoised image are removed to obtain an intermediate image; Processing the intermediate image using a contrast-limited adaptive histogram equalization method to obtain a first signal-enhanced image; Using the Sobel convolution method, identifying edge positions 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 positions; The second signal enhanced image is processed by a gamma correction method to obtain the preprocessed image.

[0011] Optionally, post-processing the cerebral vascular tissue segmentation image to obtain a post-processed image includes: A three-dimensional conditional random field model is used to perform penalty processing on adjacent points with similar signal strength on the cerebrovascular tissue segmentation image to obtain a three-dimensional spatial segmentation image; the adjacent points with similar signal strength refer to pixel points whose signal strength difference is within a set range; The three-dimensional maximum connected component is found on the three-dimensional space segmentation image, and the unconnected signal noise in the three-dimensional space segmentation image is removed based on the three-dimensional maximum connected component to obtain the post-processing image.

[0012] Optionally, a method combining an asymmetric convolution module and a Squeeze-and-Excitation module is used to perform convolution feature extraction on the T1-weighted imaging image and the T2-FLAIR image, respectively, to obtain T1-weighted imaging features and T2-FLAIR image features, including: In the convolutional neural network encoder, two asymmetric convolution modules are connected to the Squeeze-and-Excitation module to obtain a new convolutional neural network encoder; A new convolutional neural network encoder is used to perform convolution feature extraction on the T1 weighted imaging image and the T2-FLAIR image respectively to obtain the T1 weighted imaging features and the T2-FLAIR image features.

[0013] Optionally, the biological age prediction model is constructed using a single hidden layer fully connected neural network architecture.

[0014] In a second aspect, the present application provides a computer device, including: 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 method for determining a comprehensive brain aging index provided above.

[0015] 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 method for determining a comprehensive brain aging index provided above.

[0016] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for determining a comprehensive brain aging index provided above.

[0017] According to the specific embodiments provided in this application, this application has the following technical effects: The present application provides a method, device, medium and product for determining a comprehensive index of brain aging. By extracting aging structures using T1-weighted imaging images and T2-FLAIR images, the limitations of single-modality imaging are avoided. It can not only provide richer vascular aging information, but also capture structural features that are not fully valued in other modalities, and can reflect earlier microvascular aging states, thereby improving sensitivity to microvascular aging. In addition, the present application can solve the problem of limitations in artificial feature extraction by using a neural network model for feature extraction. The present application obtains a comprehensive index of brain aging through the brain aging age prediction results and the actual age of the evaluation object, which can achieve quantitative evaluation of brain vascular aging. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative work.

[0019] Figure 1 A flowchart of a method for determining a comprehensive index of brain aging provided in one embodiment of the present application; Figure 2 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] Based on the image segmentation of magnetic resonance vascular imaging and the extraction of multi-level cerebrovascular-specific standardized image features, the method for determining the comprehensive brain aging index provided in this application integrates multimodal brain image features to construct a global image index of cerebrovascular aging. This index can be used to quantitatively and objectively evaluate the overall level of cerebrovascular aging at the individual level, thereby assisting relevant clinical scientific research work.

[0022] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0023] In an exemplary embodiment, the present application provides a method for determining a comprehensive index of brain aging, which is executed by a computer device, specifically, a terminal or a server, or a terminal and a server. In the present embodiment, the method is applied to a server as an example for explanation. Figure 1 As shown, the method includes: Step 100: Acquire T1-weighted imaging images, T2-FLAIR images, and TOF-MRA magnetic resonance images.

[0024] Step 101: preprocess the T1-weighted imaging image and the TOF-MRA magnetic resonance image to obtain a preprocessed image. In actual application, in order to ensure the accuracy of the data, the T2-FLAIR image also needs to be preprocessed, including noise reduction processing and other methods.

[0025] Step 102: Obtain a cerebral vascular tissue segmentation image based on the preprocessed image.

[0026] Step 103: post-process the cerebral vascular tissue segmentation image based on the TOF-MRA magnetic resonance image to obtain a post-processed image.

[0027] Step 104, extracting cerebrovascular image features based on the post-processed image. Cerebrovascular image features include: basic cerebrovascular features, cerebrovascular geometric features, cerebrovascular topological features and cerebrovascular morphological features. Basic cerebrovascular features include: length and volume of cerebrovascular and diameter and length of local brain area. Local brain area is determined based on voxels. Cerebrovascular geometric features include: radius of curvature of cerebrovascular and degree of curvature of cerebrovascular. Cerebrovascular topological features include: angle of cerebrovascular bifurcation point and density of cerebrovascular bifurcation. Cerebrovascular morphological features include the distribution density of cerebrovascular in standard atlas space.

[0028] Step 105: Use a combination of an asymmetric convolution module and a Squeeze-and-Excitation module to perform convolution feature extraction on the T1-weighted imaging image and the T2-FLAIR image, respectively, to obtain T1-weighted imaging features and T2-FLAIR image features.

[0029] Step 106: compress the T1-weighted imaging features and the T2-FLAIR image features by global pooling to generate a convolution feature group of a T1-weighted imaging image and a T2-FLAIR image in which each feature dimension is a set value.

[0030] Step 107: Obtain demographic indicators. Demographic indicators include gender and age.

[0031] Step 108: Connect the demographic indicators, cerebrovascular imaging features, and the convolution feature group of the T1-weighted imaging image and the T2-FLAIR image to generate a cerebrovascular aging imaging representation group.

[0032] Step 109: construct a biological age prediction model.

[0033] Step 110: Input the cerebrovascular aging image representation group into the biological age prediction model to obtain a brain aging age prediction result.

[0034] Step 111: Obtain a comprehensive brain aging index based on the brain aging age prediction result and the actual age of the evaluation object. The evaluation object refers to the user for whom the comprehensive brain aging index needs to be determined.

[0035] Based on the above description, the present application can overcome the limitations of the prior art and achieve a comprehensive and quantitative assessment of cerebrovascular aging by implementing the above steps 100 to 11. In particular, through the early assessment of microvascular aging, the present application can provide strong support for early screening, risk assessment and personalized treatment of cerebrovascular diseases, and has broad application prospects.

[0036] In another exemplary embodiment of the present application, the implementation process of step 101 may include: 11. Perform brain tissue-specific identification and segmentation on T1-weighted imaging images and TOF-MRA magnetic resonance images, remove non-brain tissue structures such as scalp, skull, facial features and neck, and obtain brain tissue structure images. Among them, implementing this step can eliminate the interference of non-brain tissue structure image signals on subsequent processing.

[0037] 12. Using the linear rigid body transformation and spline interpolation method, based on the brain tissue structure image, register the T1-weighted imaging image and the TOF-MRA magnetic resonance image, and resample the registered structure to the same image space to obtain a converted image. For example, using the linear rigid body transformation with 6 degrees of freedom and the spline interpolation method, register the T1-weighted imaging and TOF-MRA magnetic resonance images of the same individual to transform each sequence image at different voxel coordinates to the same anatomical coordinates, thereby facilitating the integration of cross-sequence signal information.

[0038] 13. Use the adaptive non-local means algorithm to perform image denoising on the TOF-MRA magnetic resonance image to obtain a denoised image to remove Gaussian noise that may exist in the image.

[0039] 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 common artifact signals in magnetic resonance images and improve the image signal-to-noise ratio.

[0040] 15. Due to the principle limitations of vascular imaging magnetic resonance sequences such as TOF-MRA, the signal enhancement amplitude of small blood vessels will be significantly lower than that of large blood vessels, making it difficult to identify small blood vessels. In order to solve this problem, this application uses a limited contrast adaptive histogram equalization method to process the intermediate image, adaptively enhance the local cerebrovascular signal, and obtain a first signal enhanced image. This step allows cerebrovascular signals of different scales to obtain similar enhancement amplitudes.

[0041] 16. Due to the existence of partial volume effect, the edge signal of the blood vessel is significantly lower than the center signal of the blood vessel, and therefore is not easy to identify. In order to solve this problem, the present application adopts the Sobel convolution method to identify the edge position where the signal intensity mutation occurs in the first signal enhanced image, and obtains the second signal enhanced image based on the identified edge position to achieve specific enhancement of the edge signal of the blood vessel and improve the contrast between the blood vessel and the surrounding non-vascular tissue. This step allows the cerebral vascular signals at different distances from the center line to obtain similar enhancements.

[0042] 17. The second signal enhancement image is processed by using the Gamma correction method. By adjusting the transformation coefficient Gamma, the vascular tissue signal (high signal) of the magnetic resonance image is nonlinearly increased and the non-vascular tissue signal (low signal) is suppressed to obtain a pre-processed image. Among them, the transformation coefficient Gamma is used as a processing hyperparameter, and the relative amplitude of the enhanced and suppressed signals can be controlled according to the nature of the processed image to obtain better image contrast.

[0043] In another exemplary embodiment of the present application, the implementation process of step 102 includes: 21. Construct a training and test data set. For example, collect T1-weighted imaging and TOF-MRA paired data of 100 healthy people acquired by different equipment using routine clinical scanning sequences. After preprocessing the image data according to the above steps 11 to 17, two neuroradiologists with rich experience in image annotation independently annotate the cerebrovascular tissue signals in the magnetic resonance images. A third senior neuroradiologist conducts a comprehensive examination and evaluation of the annotation results to complete the annotation of cerebrovascular tissue signals in multimodal magnetic resonance image data, ensure the consistency and accuracy of data annotation, and finally construct a training and test data set for the supervised model.

[0044] 22. Based on the 3D-UNet convolutional neural network, the attention gating module is combined to build a deep neural network model. Among them, the overall 3D-UNet convolutional neural network can adopt an adaptive design to automatically adjust hyperparameters such as batch size and network depth width according to the spatial resolution and size of the input image. At the same time, the attention gating module is introduced in the jump connection of the 3D-UNet convolutional neural network, and its basic form can be expressed as: .

[0045] In the formula, 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.

[0046] Finally, the resampled SAct image is combined with the feature tensor on the decoding module Multiplying together can fuse feature information at different scales and reduce background noise to a great extent.

[0047] 23. Use the training and testing data sets to train and test the deep neural network model until the output error of the deep neural network model after training and testing reaches the set threshold, thereby obtaining a trained deep neural network model.

[0048] For example, a five-fold cross-validation method is used to train and test the deep neural network model. The input of the deep neural network model is T1-weighted imaging images and TOF-MRA magnetic resonance data at the individual level, and the output is a cerebral vascular segmentation image. In order to cope with the differences in specificity and sensitivity of vascular segmentation results at different scales during vascular segmentation, the Tversky function can be introduced as the loss function of the deep neural network model. On the basis of the Tversky function, a weighted Tversky loss method is further proposed, that is, the inverse of the Euclidean distance of the voxel from the center line is used as the mismatch loss weight, which strengthens the topological structure restrictions of the segmentation results, so that the vascular segmentation results have a more consistent performance at each scale. This application selects the model with the best results as the final output model (that is, the trained deep neural network model) by default, and the user can also choose to deploy the average model.

[0049] 24. The trained deep neural network model is used as a cerebrovascular tissue segmentation model, and the preprocessed image is input into the cerebrovascular tissue segmentation model to obtain a cerebrovascular tissue segmentation image.

[0050] In another exemplary embodiment of the present application, the implementation process of step 103 includes: 31. A three-dimensional conditional random field model is used to penalize adjacent points with similar signal intensities on the cerebrovascular tissue segmentation image to obtain a three-dimensional space segmentation image. Adjacent points with similar signal intensities refer to pixel points whose signal intensity difference is within a set range. The three-dimensional conditional random field model takes into account the continuity of vascular tissue in space. By establishing potential functions between each pair and on a single point, adjacent points with similar signal intensities on magnetic resonance images with different segmentation labels on the segmentation image are penalized to obtain a more continuous and reasonable segmentation image in three-dimensional space (i.e., a three-dimensional space segmentation image).

[0051] 32. Find the three-dimensional maximum connected component on the three-dimensional space segmentation image, and remove the unconnected small blocks of signal noise in the three-dimensional space segmentation image based on the three-dimensional maximum connected component to obtain the final post-processed cerebral vascular segmentation image.

[0052] In another exemplary embodiment of the present application, the implementation process of step 104 includes: 41. Centerline, normal plane estimation and 3D reconstruction.

[0053] (1) The centerline of the post-processed image is estimated based on the Voronoi covariance measure (VCM) to stably extract the centerline of cerebrovascular segmentation and reduce the center point identification drift and voxel discontinuity problems at the cerebrovascular bifurcation.

[0054] (2) Based on the extraction of the central axis of the cerebral blood vessels, the λ-Maximal Segment Tangent (λ-MST) method is used to calculate the tangent corresponding to each voxel on the centerline, and then the normal plane on each centerline voxel is further calculated. The normal plane of each centerline voxel is robustly estimated by the weighted average method of the normal planes of adjacent voxels.

[0055] (3) For each voxel on the center line, fit the largest circle in its normal plane and calculate the diameter corresponding to the voxel.

[0056] (4) Combining the centerline and diameter information, the three-dimensional reconstruction of the tubular tree structure is realized. This step can effectively prevent the local small errors that may be introduced by the structure segmentation algorithm from being cascaded and amplified in the vascular feature estimation, thereby ensuring the robustness of the three-dimensional reconstruction.

[0057] 42. Extraction of basic features of cerebral blood vessels: length and volume of individual tubular structures, diameter and length of local brain regions.

[0058] 1) Extraction of individual cerebral vessel length and volume.

[0059] The number of voxels with positive labels in the 3D image of cerebrovascular segmentation (i.e., the image obtained by 3D reconstruction of the tubular tree structure) was counted to obtain the absolute length of the cerebrovascular vessel. At the same time, considering that the size of individual brain tissue can significantly affect the length of cerebrovascular structure, the absolute length was divided by the volume of individual brain tissue to obtain the relative length of cerebrovascular vessel.

[0060] The absolute volume of cerebrovascular tissue is obtained by multiplying the number of voxels by the size of the voxel. At the same time, considering that the size of individual brain tissue can significantly affect the volume of cerebrovascular structure, the absolute volume of cerebrovascular tissue can also be divided by the size of individual brain tissue to obtain the relative volume, which reflects the average distribution density of cerebrovascular tissue in the whole brain tissue.

[0061] 2) Extraction of length and diameter of cerebral blood vessels in local brain regions.

[0062] The MNI standard brain template and cerebrovascular MRI images were nonlinearly registered using a two-step registration method, and the Harvard-Oxford brain partition map in the MNI standard brain template space was converted to the individual-level MRI image space. The local vascular length and diameter were calculated in each brain partition according to the above step 1) to reflect the heterogeneity of the basic characteristics of blood vessels in the spatial distribution of each brain region.

[0063] 43. Extraction of cerebral vascular geometric features. The cerebral vascular geometric features mainly include the radius of curvature and the degree of curvature of the cerebral vessels.

[0064] In the cerebrovascular segmentation centerline image, the curvature radius and curvature degree of each voxel point of the centerline in three-dimensional space are calculated according to the tangent vector flip angle and the Frenet frame. The average vascular curvature radius and curvature degree of each brain region corresponding to the Harvard-Oxford brain partition map are calculated to measure the geometric brain distribution characteristics of cerebrovascular.

[0065] 44. Extraction of cerebrovascular topological features. Cerebrovascular topological features mainly refer to cerebrovascular bifurcation points.

[0066] Step (1) segmenting the centerline image of the cerebral blood vessels and using a tree structure to characterize the adjacency relationship of each centerline voxel, thereby automatically identifying bifurcation points in the vascular tree structure and counting the number of bifurcations and their spatial distribution.

[0067] Step (2), calculate the angle between the tangent vectors of the adjacent voxels at the bifurcation point, which is the bifurcation angle of the bifurcation point.

[0068] Step (3), calculating the average bifurcation angle and bifurcation density in each brain region, reflecting the distribution characteristics of the vascular bifurcation statistics in the brain region space.

[0069] 45. Voxel Based Morphometry (VBM).

[0070] Step 1), iteratively register the cerebrovascular segmentation images of healthy people to obtain a cerebrovascular distribution density map at the group level of healthy people.

[0071] Step 2) nonlinearly register the individual cerebrovascular segmentation image with the group cerebrovascular distribution density map by nonlinear registration, and obtain the transformed Jacobian matrix.

[0072] Step 3) Using the Jacobian matrix to standardize the registered individual vascular images, the distribution density of individual cerebral blood vessels in the standard atlas space is obtained. This distribution density can quantitatively evaluate the difference between the local or overall level of the individual vascular distribution network density and the group.

[0073] In another exemplary embodiment of the present application, since the T1-weighted imaging image and the T2-FLAIR image mainly reflect the overall characteristics of various tissue structures such as white matter and gray matter in the individual brain, they can reflect the impact of vascular aging on these brain tissue structures and contain rich information on cerebrovascular aging. However, since these two images are not magnetic resonance cerebrovascular-specific imaging sequences, the conventional two-step strategy of feature extraction after segmentation cannot fully extract information on brain vascular aging. In order to solve this problem, the present application takes advantage of the ability of neural networks to adaptively extract feature encoding to automatically extract vascular aging features from T1-weighted imaging images and T2-FLAIR images. Based on this, in step 105 provided in the present application, the asymmetric convolution module (Asymmetric Convolution) and the squeeze-and-excitation module are combined to perform convolution feature extraction on the T1-weighted imaging image and the T2-FLAIR image, respectively. The asymmetric convolution module improves the image receptive field of the convolution kernel, and the specific formula is as follows: .

[0074] In the formula, is the input feature map, is the output feature map, , , and The convolution kernels are 1×1×k, 1×k×1, k×1×1, and k×k×k respectively.

[0075] The Squeeze-and-Excitation module can introduce an attention mechanism into the neural network and adaptively adjust the weight parameters of each feature through the correlation between different convolutional features. The specific formula is as follows: .

[0076] In the formula, This is the output of the Squeeze-and-Excitation module. F is the input feature map, σ is the sigmoid nonlinear activation function, ReLU is the RectifiedLieanerUnit nonlinear activation function, W 1 is the linear parameter matrix of the input feature map after global pooling compression, b 1 is the bias term acting on the input feature map after global pooling compression, W 2 is the linear parameter matrix after ReLU nonlinear activation, b 2 is the corresponding bias term. GlobalAvgPool represents global pooling compression, and its specific formula is: .

[0077] This formula represents the averaging of the width and height of the input feature map. represents the i-th global pooling compression result, H represents the height of the input feature map, W represents the width of the input feature map, is the number of iterations, Represents the feature map with a height of j and a width of k for the input i-th global pooling.

[0078] Based on the above description, in actual application, two connections between an asymmetric convolution module and a Squeeze-and-Excitation module can be set in a convolutional neural network encoder to obtain a new convolutional neural network encoder to realize the extraction of convolution features of T1-weighted imaging images and T2-FLAIR images.

[0079] Furthermore, the extracted T1-weighted imaging image and T2-FLAIR image convolution features are compressed by global pooling compression to generate a unified T1-weighted imaging image and T2-FLAIR image convolution feature group with each feature dimension as a set value (assumed to be 1). Then, demographic indicators such as gender and cerebrovascular imaging features are directly connected to the T1-weighted imaging image and T2-FLAIR image convolution feature group to generate a comprehensive feature group containing two parts of information: a cerebrovascular aging image representation group that specifically reflects cerebrovascular characteristics and a T1-weighted imaging image and T2-FLAIR image image representation group that reflects the overall characteristics of cerebrovascular aging, and thus a comprehensive imaging feature group is obtained.

[0080] A simple fully connected neural network architecture with a single hidden layer was used to construct a biological age prediction model. The input of this model was a comprehensive imaging feature group, which was used to comprehensively predict the patient's brain aging age. By comparing it with the individual's physical age, an accurate estimation of the brain aging index was achieved.

[0081] Among them, the loss function of the biological age prediction model adopts the MSE loss function, which is expressed as: .

[0082] In the formula, represents the MSE loss function value, Representative model estimates of vascular age ， Represents the patient's actual physical age, Represents the total sample size.

[0083] Furthermore, in the process of constructing the biological age prediction model, training and testing are also required. Based on this, the data set is randomly divided into a training set and a test set. In the training set, multiple models are trained with ten-fold cross validation, and the optimal model is selected as the final output model (i.e., the biological age prediction model). It is verified in the test set. In order to prevent overfitting, the training early stopping method is used in training to fully train the initial model and greatly reduce the risk of model overfitting. The output of the final model is the biological age of the cerebrovascular vessels, and the difference between it and the individual's physical age is the comprehensive brain aging index proposed in this application, which realizes the effect of using multimodal magnetic resonance data to quantitatively and objectively measure the degree of brain aging in patients' imaging. At the same time, the effect coefficient corresponding to each imaging feature can also be obtained in the biological age prediction model. This coefficient can quantitatively evaluate the contribution of the imaging feature to the overall brain aging index, indicating the imaging feature that has the greatest impact on vascular aging, which has a strong clinical indication significance.

[0084] In addition to vascular segmentation and vascular feature extraction, this application also incorporates brain structural features, and achieves quantitative assessment of brain aging by fusing vascular aging features in T1-weighted imaging images and T2-FLAIR images, combined with advanced neural network technology. Based on this, compared with the existing technology, the main features of this application are: 1. Multimodal image fusion.

[0085] (1-1) Combined use of T1-weighted imaging and T2-FLAIR images: T1-weighted imaging and T2-FLAIR images reflect different characteristics of brain tissue. T1-weighted images mainly display anatomical structures, while T2-FLAIR images are more sensitive to pathological changes such as white matter lesions and edema. The combination of these two modalities can provide richer information on brain aging, including the manifestation of abnormal brain tissue structure on cerebrovascular aging, and a more comprehensive response to cerebrovascular aging.

[0086] (1-2) Adaptive feature extraction: Traditional post-segmentation feature extraction methods cannot fully capture the vascular aging features in T1-weighted imaging images and T2-FLAIR images. This application uses the adaptive feature encoding and extraction capabilities of neural networks to automatically identify and extract complex features related to vascular aging, avoiding the limitations of manually designed features.

[0087] 2. Optimize the neural network model structure.

[0088] (2-1) Asymmetric Convolution: In order to better capture the local and global features in T1-weighted imaging images and T2-FLAIR images, this application introduces an asymmetric convolution module that can extract features at different scales and enhance the model's sensitivity to vascular aging characteristics.

[0089] (2-2) Squeeze-and-Excitation mechanism: By introducing the Squeeze-and-Excitation (SE) mechanism, the weights in the feature map can be dynamically adjusted to highlight important areas and suppress irrelevant information. This helps to improve the recognition accuracy of vascular aging features, especially when dealing with complex cerebrovascular structures.

[0090] (2-3) Global pooling compression: In order to effectively fuse the convolutional features of T1-weighted imaging images and T2-FLAIR images, global pooling compression technology is used to generate a unified feature group with each feature dimension of 1. This process not only reduces the feature dimension, but also retains key information, which facilitates subsequent comprehensive analysis.

[0091] 3. Construction of comprehensive feature groups.

[0092] Multi-source information fusion: Demographic indicators such as gender and age are combined with cerebrovascular imaging features to generate an image representation group that specifically reflects cerebrovascular features. At the same time, the convolution feature group of T1-weighted imaging images and T2-FLAIR images are also included to form a comprehensive feature group. This comprehensive feature group not only includes the characteristics of the blood vessels themselves, but also reflects the impact of vascular aging on brain tissue structure, providing a more comprehensive evaluation perspective.

[0093] 4. Vascular biological age prediction.

[0094] (4-1) Single hidden layer fully connected neural network: In the final vascular biological age prediction model, a simple single hidden layer fully connected neural network architecture was used to predict the patient's cerebrovascular aging age using a comprehensive imaging feature set. By comparing it with the individual's physical age, an accurate estimate of the brain aging index was obtained.

[0095] (4-2) Ten-fold cross validation and early stopping strategy: In order to prevent the model from overfitting, ten-fold cross validation and early stopping strategy were adopted during the training process. This not only ensured the generalization ability of the model, but also greatly reduced the risk of overfitting and improved the stability and reliability of the model.

[0096] In summary, the method for determining the comprehensive index of brain aging proposed in this application has the following significant advantages: 1. Quantitative and objective evaluation: Through the fusion of multimodal imaging data and the adaptive feature extraction of neural networks, the degree of cerebrovascular aging in patients' imaging can be quantitatively and objectively measured, providing clinicians with a reliable evaluation tool.

[0097] 2. Effect coefficient analysis: The effect coefficient corresponding to each output imaging feature can quantitatively evaluate its contribution to the overall cerebrovascular aging index and reveal the imaging feature that has the greatest impact on vascular aging. This information has a strong clinical significance and can help doctors better understand the mechanism of vascular aging and provide a basis for personalized treatment.

[0098] 3. Early screening and risk assessment: Cerebrovascular aging is an important risk factor for diseases such as stroke and cognitive impairment. Through the method of this application, potential vascular problems can be discovered at an early stage, and intervention measures can be taken in time to reduce the risk of patients.

[0099] In addition, in this application, T1-weighted imaging images and T2-FLAIR images respectively reflect different characteristics of brain tissue. T1-weighted images mainly show anatomical structures, while T2-FLAIR images are more sensitive to pathological changes such as white matter lesions and edema. The combination of these two modalities can not only provide richer information on vascular aging, but also capture structural features that are not fully valued in other modalities. These features are actually another manifestation of vascular aging, which can reflect an earlier state of microvascular aging.

[0100] Microvascular aging is an important precursor to cerebrovascular disease, especially in the early stages, when changes in microvessels may be the earliest pathological features. Therefore, by fusing the features in T1-weighted imaging and T2-FLAIR images, it is possible to identify signs of microvascular aging earlier, enhance the assessment of microvascular aging, and thus more comprehensively reflect the overall aging status of cerebrovascular vessels.

[0101] Traditional feature extraction methods rely on manually designed algorithms, are easily affected by subjective factors, and have difficulty fully utilizing the complex information in multimodal images. This application utilizes the adaptive feature encoding and extraction capabilities of neural networks to automatically identify and extract complex features related to vascular aging, avoiding the limitations of manually designed features. This automated feature extraction method not only improves the accuracy of the model, but also enhances its generalization capabilities, making it suitable for different types of imaging data.

[0102] The brain aging index not only reflects the structural changes of large blood vessels, but also captures the aging characteristics of microvessels, providing a more comprehensive assessment perspective. By comparing with the individual's physical age (i.e., the age obtained in step 107 above), the brain aging index can accurately estimate the patient's cerebrovascular biological age and reveal the potential risks of vascular aging.

[0103] 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 2 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data for determining the comprehensive index of brain aging. 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 through a network connection. When the computer program is executed by the processor, a method for determining a comprehensive index of brain aging is implemented.

[0104] Those skilled in the art will understand that Figure 2The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components. In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0105] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0106] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] 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.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium 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), magnetoresistive 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).

[0109] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0110] The technical features of the above embodiments may 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.

[0111] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will 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 comprehensive index of brain aging, characterized in that: include: Acquire T1-weighted imaging images, T2-FLAIR images, and TOF-MRA magnetic resonance images; Preprocessing the T1-weighted imaging image and the TOF-MRA magnetic resonance image to obtain a preprocessed image; Obtaining a cerebral vascular tissue segmentation image based on the preprocessed image; Post-processing the cerebral vascular tissue segmentation image based on the TOF-MRA magnetic resonance image to obtain a post-processed image; Extract cerebrovascular imaging features based on post-processed images; The convolution feature extraction of T1-weighted imaging image and T2-FLAIR image was performed by combining asymmetric convolution module and Squeeze-and-Excitation module to obtain T1-weighted imaging feature and T2-FLAIR image feature. By globally pooling and compressing T1-weighted imaging features and T2-FLAIR image features, a convolution feature group of T1-weighted imaging images and T2-FLAIR images is generated, each feature dimension of which is a set value; Obtain demographic indicators; demographic indicators include gender and age; The demographic indicators and cerebrovascular imaging features were connected with the convolutional feature groups of T1-weighted imaging images and T2-FLAIR images to generate a cerebrovascular aging imaging representation group; Construct a biological age prediction model; The cerebrovascular aging image characterization group is input into the biological age prediction model to obtain the brain aging age prediction result; The comprehensive index of brain aging was obtained based on the predicted results of brain aging age and the actual age of the evaluated subjects.

2. The method for determining the comprehensive index of brain aging according to claim 1, characterized in that: The cerebral vascular tissue segmentation image is obtained based on the preprocessed image, including: Construct a training and testing data set; the training and testing data set includes paired data of T1-weighted imaging images and TOF-MRA magnetic resonance images; Based on the 3D-UNet convolutional neural network, the attention gating module is combined to build a deep neural network model; The deep neural network model is trained and tested using the training and testing data set until an output error of the deep neural network model after training and testing reaches a set threshold, thereby obtaining a trained deep neural network model; The trained deep neural network model is used as a cerebrovascular tissue segmentation model, and the preprocessed image is input into the cerebrovascular tissue segmentation model to obtain the cerebrovascular tissue segmentation image.

3. The method for determining the comprehensive index of brain aging according to claim 2, characterized in that: Based on the Tversky function, the weighted Tversky loss is used to construct the loss function of the cerebrovascular tissue segmentation model.

4. The method for determining the comprehensive index of brain aging according to claim 1, characterized in that: Preprocess the T1-weighted imaging image and the TOF-MRA magnetic resonance image to obtain a preprocessed image, including: Perform brain tissue-specific identification and segmentation on TOF-MRA magnetic resonance images to obtain brain tissue structure images; Using a linear rigid body transformation and spline interpolation method, based on the brain tissue structure image, the T1-weighted imaging image and the TOF-MRA magnetic resonance image are registered, and the registered structure is resampled to the same image space to obtain a converted image; Adaptive non-local means algorithm is used to perform image denoising on TOF-MRA magnetic resonance images to obtain denoised images. Using a signal intensity remapping method after Gaussian deconvolution, magnetic resonance image artifacts caused by B0 field inhomogeneity in the denoised image are removed to obtain an intermediate image; Processing the intermediate image using a contrast-limited adaptive histogram equalization method to obtain a first signal-enhanced image; Using the Sobel convolution method, identifying edge positions 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 positions; The second signal enhanced image is processed by a gamma correction method to obtain the preprocessed image.

5. The method for determining the comprehensive index of brain aging according to claim 1, characterized in that: Post-processing the cerebral vascular tissue segmentation image to obtain a post-processed image includes: A three-dimensional conditional random field model is used to perform penalty processing on adjacent points with similar signal strength on the cerebrovascular tissue segmentation image to obtain a three-dimensional spatial segmentation image; the adjacent points with similar signal strength refer to pixel points whose signal strength difference is within a set range; The three-dimensional maximum connected component is found on the three-dimensional space segmentation image, and the unconnected signal noise in the three-dimensional space segmentation image is removed based on the three-dimensional maximum connected component to obtain the post-processing image.

6. The method for determining the comprehensive index of brain aging according to claim 1, characterized in that: The convolution feature extraction is performed on the T1-weighted imaging image and the T2-FLAIR image respectively by using a method combining an asymmetric convolution module and a Squeeze-and-Excitation module to obtain T1-weighted imaging features and T2-FLAIR image features, including: In the convolutional neural network encoder, two asymmetric convolution modules are connected to the Squeeze-and-Excitation module to obtain a new convolutional neural network encoder; A new convolutional neural network encoder is used to perform convolution feature extraction on the T1 weighted imaging image and the T2-FLAIR image respectively to obtain the T1 weighted imaging features and the T2-FLAIR image features.

7. The method for determining the comprehensive index of brain aging according to claim 1, characterized in that: The biological age prediction model is constructed using a single hidden layer fully connected neural network architecture.

8. 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 a comprehensive brain aging index according to any one of claims 1 to 7.

9. 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 comprehensive brain aging index according to any one of claims 1 to 7 is implemented.

10. 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 comprehensive brain aging index according to any one of claims 1 to 7 is implemented.

Images