Method and system for predicting development of early cortical wrinkles of human brain based on neural network model

Abstract

The invention discloses a method and a system for predicting development of human brain early cortical wrinkles based on a neural network model, and belongs to the crossing field of artificial intelligence and brain science. A cortex wrinkle three-dimensional skeleton is extracted through a brain negative model skeleton technology, and a complex mode that wrinkles change along with gestational ages is captured by using a beta-VAE model, so that accurate prediction from 30-week gestational ages to 40-week gestational ages is realized; according to the method, a large amount of MRI image data is used for training the model, the accuracy of a prediction result is ensured, the expandability and maintainability are improved through system modular design for achieving the method, the real-time performance and accuracy are ensured through computer implementation, the problem that an existing model lacks neurogenesis heterogeneity information is solved, and the method is suitable for popularization and application. A new way is provided for research on development of early cortical wrinkles of human brains, and the method has wide application prospects such as evaluation of neural development of premature infants and early diagnosis of diseases.

Description

Technical Field

[0001] The present invention belongs to the intersection of artificial intelligence and brain science, and specifically relates to a method and system for predicting the development of early cortical folds in the human brain based on a neural network model. Background Art

[0002] On the complex cortical surface, the formation of gyri (outward convex parts) and sulci (inward concave parts) is a complex and delicate developmental process, which gradually unfolds between 16 and 40 weeks of pregnancy. The positions of primary gyri and sulci that appear between 16 and 29 weeks are relatively consistent among people. In the middle and late stages of cortical development (after 29 weeks), secondary and tertiary gyri and sulci appear. There are significant differences between individuals in secondary and tertiary gyri and sulci, which is related to multiple factors such as genetics and environment. This diversity increases the difficulty of studying the developmental mechanisms of these structures.

[0003] The origins of some neurodevelopmental disorders associated with abnormal folding patterns are not yet fully understood. Recent studies have shown that the formation of cortical folds is regulated by a variety of molecular and cellular processes, including neuronal proliferation, migration, differentiation, and synapse formation. In addition, mechanical force also plays an important role. The difference in growth rate of the cerebral cortex leads to an imbalance in tension between the inner and outer layers, which in turn triggers the formation of folds.

[0004] In recent years, domestic and foreign teams have established a variety of mechanical models based on different mechanical assumptions to simulate the formation of cortical folds. Because these models lack information on the spatial heterogeneity of neurogenetic phenomena, such as regional differential growth rates, they cannot fully simulate the complex changes in the cerebral cortex during development, and the simulation results of these models all show that they cannot accurately reflect the common topological structure of the human brain. Dissection data show that within 30 to 38 weeks, the cortical expansion rate of the lateral parietal, temporal, and occipital regions is significantly higher than that of the medial and insular regions. This regional difference in expansion rate is an important reason for the diversity of cortical folding patterns. In addition, during the rapid cortical expansion stage (29-38 weeks of gestational age), the growth patterns of different regions change significantly over time. For example, the expansion rate of the primary sensory, motor, and visual cortices and the insula slows down over time, while the expansion rate of the lateral temporal lobe accelerates over time.

[0005] The development of fetal cerebral cortical folds is a complex and delicate process. In the field of neuroscience, understanding the development of the fetal brain, especially the dynamic changes of cortical folds, is of great significance for diagnosing early neurodevelopmental abnormalities. The dynamic changes of cortical folds involve regulatory factors at multiple levels, and it is necessary to use a variety of methods and technical means to more comprehensively reveal its development mechanism and promote progress in related fields. However, since extremely premature infants (such as around 30 weeks) have very few folds in the cerebral cortex at birth, it is challenging to directly observe their development process. Summary of the invention

[0006] In order to address the technical problem that existing physical models lack spatial heterogeneity information on neurogenesis when simulating the development of fetal cerebral cortical folds, and such information is difficult to directly obtain in the human brain, resulting in simulation results that cannot accurately reflect the actual topological structure of the human brain, the present invention aims to provide a method and system for learning and predicting the development of early human brain cortical folds based on a neural network model.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: The present invention provides a method for predicting the development of early cortical folds in the human brain based on a neural network model, comprising: S1, obtain imaging data of adult brain, 30-week gestational age, and 40-week gestational age premature infant brain; S2, based on the brain negative skeleton technology, extracts the three-dimensional skeleton structure of cortical folds from the image data obtained from S1; S3, input the wrinkle skeleton data of S2 at 30 weeks of gestational age into the pre-trained β variational autoencoder model to predict the wrinkle skeleton morphology at 40 weeks of gestational age; S4 outputs the predicted cortical folds at 40 weeks of gestation, which are highly similar to the actual brain fold morphology.

[0008] The brain imaging data of extremely premature infants are MRI T1w imaging data: The three-dimensional skeleton structure of cortical folds extracted by S2 includes: S21, using the brain extraction algorithm to preprocess the image data in S1 and extract the cerebral cortex area; S22, based on the cerebral cortex area image data extracted in S21, reconstructing a three-dimensional surface model of the cerebral cortex using a three-dimensional reconstruction technology; S23, converting the three-dimensional surface model of the cerebral cortex reconstructed in S22 into a negative model; S24, applying the skeleton extraction algorithm on the negative model of S23 to extract the three-dimensional skeleton structure of the cortical folds; S25, post-processing the three-dimensional skeleton structure extracted by S24, optimizing and reconstructing, and obtaining the three-dimensional skeleton structure of the cortical folds.

[0009] The S3 pre-trained β variational autoencoder model includes: S31, input the three-dimensional skeleton structure of cortical folds extracted by S2 into the β variational autoencoder model; S32, construct the β-VAE model framework, which includes an encoder and a decoder. The encoder is responsible for mapping the input 3D cortical geometry information to the latent space, while the decoder is responsible for reconstructing the 3D cortical structure from the latent space. S33, using the preprocessed adult brain MRI data as the training set, the β-VAE model is trained, and the model parameters are adjusted by minimizing the reconstruction error and the KL divergence between the latent variable distribution and the prior distribution. The training model learns the skeleton topology of adult brain folds and realizes the reconstruction of adult brain folds data; the reconstruction error adopts the cross entropy loss, and the prior distribution adopts the central Gaussian distribution; the pre-trained model is evaluated using the validation set, and the pre-trained machine learning model is obtained according to the model evaluation index; S34, using the preprocessed premature infant image data as the training set, retraining the β-VAE model pre-trained in S33. By inputting the cortical fold skeleton data of infants at 30 weeks of gestation, the model learns and predicts the fold morphology of these areas at 40 weeks of gestation; S35, data partitioning and model optimization, during the training process, the data set is divided into training set, validation set and test set to adjust and optimize model parameters, evaluate the performance of the model, and finally obtain the optimal machine learning model; determine the best model hyperparameter combination, the hyperparameter combination includes β value, latent space size, batch size, number of training rounds and learning rate.

[0010] Furthermore, the S35 hyperparameter combination is: β value range is 1~8, latent space size range is 2~500, batch size range is 4~16, number of training rounds range is 500~2000, and learning rate range is 1e-4~1e-2.

[0011] Furthermore, the optimal combination of hyperparameters is: β value is 2, latent space size is 300, batch size is 8, number of training rounds is 1000, and learning rate is 1e-3.

[0012] The hyperparameter combination of the optimization model adopts any one of grid search, random search or Bayesian optimization.

[0013] The system for implementing the above-mentioned method for predicting the development of early cortical folds in the human brain based on a neural network model comprises: Data acquisition and processing module, used to acquire imaging data of 30-week fetal and adult brains, and pre-process the imaging data; 3D skeleton extraction module, used to extract the 3D skeleton structure of cortical folds; The model training and prediction module is used to input the wrinkle skeleton data at 30 weeks of gestational age into the trained model to predict the wrinkle skeleton morphology at 40 weeks of gestational age; Hyperparameter optimization module, used to obtain the best hyperparameter combination; The result evaluation and verification module is used to verify the accuracy of the model in predicting the cortical fold morphology at 40 weeks of gestational age and its effectiveness in practical applications; The user interaction and output module is used to output the prediction results to the user in graphical or tabular form.

[0014] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for predicting the development of early cortical folds in the human brain based on a neural network model are implemented.

[0015] The present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method for predicting the development of early cortical folds in the human brain based on a neural network model are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The method provided by the present invention is based on a neural network model to predict the development of early cortical folds in the human brain. The method can effectively extract the three-dimensional skeleton structure of cortical folds from complex image data through the brain negative model skeleton technology, which not only simplifies the complexity of data processing, but also retains key structural information, providing a solid foundation for subsequent model training and prediction; using the β variational autoencoder (β-VAE) model, the complex geometric characteristics of the cerebral cortical folds and the pattern of change with gestational age are captured through deep learning. The model can accurately predict the fold morphology at 40 weeks of gestation from the fold skeleton data at 30 weeks of gestational age. The prediction result is highly similar to the actual brain fold morphology, which improves the accuracy of the prediction; the method of the present invention has broad application prospects in the fields of neuroscience, medical imaging and clinical medicine. It can not only be used to evaluate the neurodevelopmental status of premature infants, but also provide important reference information for the early diagnosis and intervention of related diseases. In addition, the method can also be extended to other research fields related to brain development, such as cognitive science, psychology, etc.

[0017] Furthermore, the method of the present invention relies on a large amount of MRI image data, including MRI data of 30-week gestational age and adult brain, and MRI data of premature infants. These data provide a wealth of training samples for the model, enabling the model to learn the general laws and individual differences of cerebral cortical folds with gestational age; in the model training process, strategies such as data partitioning, model evaluation and hyperparameter optimization are adopted. By adjusting hyperparameters such as β value, latent space dimension and batch size, the performance of the model can be further optimized to make it more suitable for specific prediction tasks. This flexibility enables the model to maintain high prediction accuracy in different data sets and application scenarios.

[0018] The system provided by the present invention includes multiple modules such as data acquisition and processing, three-dimensional skeleton extraction, model training and prediction, hyperparameter optimization, result evaluation and verification, and user interaction and output. These modules are independent of each other but work closely together to achieve the function of predicting the development of early cortical folds in the human brain based on a neural network model. This design improves the scalability and maintainability of the system. By implementing the method of the present invention as a computer program and storing it on a computer-readable storage medium, it can be quickly deployed and run on a computer device. The powerful computing power of the computer device and the efficient algorithm implementation ensure the real-time and accuracy of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of the process of predicting the development of early cortical folds in the human brain based on a neural network model according to the present invention; Figure 2 It is a schematic diagram of the process of the method for identifying human cerebral cortical folds based on TI weighted MRI images of the present invention; Figure 3 The cortical fold morphology of part of the 40-week fetus output by the model trained by the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: like Figure 1 As shown, a process and method diagram for generating a three-dimensional brain fold skeleton and training a β variational autoencoder model is provided, including: 1. Data acquisition and preprocessing (1) Data acquisition Data sources: The model was pre-trained using 900 healthy adult T1-weighted MRI brain images from the Human Connectome Project (HCP) dataset, acquired on a Siemens Skyra Connectom scanner at an isotropic resolution of 0.7 mm, with subjects ranging in age from 22 to 36 years old; the model was re-trained using 71 premature infant T1-weighted MRI brain images from the Utrecht dataset, with data from these infants collected at 30 and 40 weeks of gestational age.

[0022] Data partitioning: 80% of the data are randomly selected as the training set for training the β-Variant Autoencoder (β-VAE) model; 10% of the data are used as the validation set to adjust the model parameters and prevent overfitting; the remaining 10% are used as the test set to evaluate the generalization ability and prediction accuracy of the model.

[0023] (2) Data preprocessing See attached Figure 2 Based on the negative model skeleton technology of cerebral cortical folds, the three-dimensional skeleton structure of cortical folds was extracted, including: Three-dimensional calibration: Use the DISCO+DARTEL algorithm to perform nonlinear calibration on the original T1-wMRI images to eliminate geometric differences and deformations between different scans and ensure the accuracy of subsequent analysis; Brain region identification and segmentation: Through the brain recognition algorithm, different regions of the brain are automatically identified and segmented, clearly showing the different regions of the brain and providing a basis for subsequent 3D reconstruction; Gray matter and white matter layer segmentation: Based on the brain region segmentation, gray matter and white matter layers are further distinguished to more accurately analyze cortical folds. The segmentation images of the cerebral hemispheres and gray and white matter clearly define the boundaries of gray and white matter. Negative model recognition and skeleton extraction: On the segmented white matter layer, the brain fold skeleton automatic recognition algorithm is applied to identify the negative model structure of the fold and extract the three-dimensional skeleton. This step is the core of extracting the three-dimensional structure of cortical folds. The cerebral cortical images of the left and right hemisphere posterior shells are the results of rendering or visualization after skeleton extraction; Post-processing and optimization: The extracted 3D skeleton structure is post-processed, including smoothing, denoising and optimized reconstruction, to obtain a more accurate and clear 3D skeleton structure of cortical folds. The automatically labeled fold map is for further analysis or visualization of specific areas.

[0024] 2. Model Pre-training Pre-training stage: First, the neural network β variational autoencoder model is pre-trained using the "brain negative model 3D skeleton" of the left and right hemispheres extracted based on adult brain MRI; the goal of this stage is to enable the model to learn the geometric shape and spatial distribution of the cerebral cortex, achieve accurate reconstruction of the fold skeleton, and provide a basis for subsequent research on the development process of early cortical folds in the human brain.

[0025] Model structure: The β-Variational Autoencoder (β-VAE) model is used. Compared with the traditional variational autoencoder, β-VAE introduces an adjustment term β to change the weight distribution of the loss function in the model structure, and pays more attention to learning more explanatory latent variables, especially in unsupervised learning and image generation tasks. By adjusting the value of β, a trade-off can be made between reconstruction accuracy and the interpretability of the potential representation. When β>1, the model pays more attention to decoupling. Although it may sacrifice some reconstruction quality, it has a significant advantage in generating more interpretable representations.

[0026] 3. Model retraining Target area: The central sulcus of the fetal brain and its adjacent precentral gyrus and postcentral gyrus are the focus of research. These areas play an important role in brain function, and changes in their fold morphology can reflect the development process of the early brain.

[0027] Input and output: The 3D structure of cortical folds is represented by the "negative 3D skeleton of the brain". The cortical fold skeleton data at 30 weeks of gestation is used as input, and the model is trained to predict the fold skeleton morphology of the corresponding area at 40 weeks of gestation.

[0028] 4. Hyperparameter Optimization Optimization process: Adopting Adam (Adaptive Moment Estimation) optimizer, based on gradient descent optimization algorithm and adaptive learning rate adjustment mechanism, the optimal hyperparameter combination is finally determined by debugging the initial value of model hyperparameters and a large number of experiments. Including β value, size of latent space, batch size, training rounds and learning rate, etc. In the present invention, the final β value is 2 (test range is 1-8), which performs well in balancing reconstruction accuracy and interpretability of latent representation; the dimension of latent space is 300 (test range is 2-500), which can fully capture the complex changes of brain fold morphology; the batch size is 8 (test range is 4-16) to ensure that the model is neither too conservative nor too aggressive during training; the number of training rounds is 1000 (test range is 500~2000) to ensure that the model fully converges and avoids overfitting; the learning rate is 1e-3 (test range is 1e-4~1e-2), which can ensure that the model updates parameters stably and efficiently during training.

[0029] Regularization function: By utilizing the regularization function of the β-VAE model, the overfitting problem caused by the small number of training samples is alleviated by balancing the decoupling of the reconstruction error and the latent space, thereby improving the generalization ability of the model.

[0030] 5. Model evaluation and results analysis Model output: The accuracy of the model was evaluated by comparing the model output of cortical fold morphology at 40 weeks of gestational age with the actual (target) brain fold morphology. Figure 3 As shown, some of the predicted results output by the model are highly similar to the actual results, which proves the accuracy and reliability of the model in predicting the fold morphology of the cerebral cortex of premature infants.

[0031] Input: The input refers to the skeleton data of the central sulcus and the anterior-posterior central sulcus of premature infants at 30 weeks of gestational age, which are used as input to the model to train the model to predict future fold morphology.

[0032] Output: The output is the skeletal morphology of the central sulcus and the anterior-posterior central sulcus at 40 weeks of gestation predicted by the model based on the input data. These predictions are displayed in the form of 3D skeleton diagrams in the picture, and each skeleton diagram represents the prediction result of a specific individual.

[0033] Target: The target refers to the actual, known cortical fold morphology of the corresponding region at 40 weeks of gestational age, which is used to compare with the model's prediction results to evaluate the accuracy of the model.

[0034] By the attached Figure 3 From the data, we can see that the skeleton diagrams of "Individual 1" to "Individual 6" each represent the cortical fold morphology of different premature infants under the model's prediction. The differences in the position and geometry of these skeleton diagrams reflect the individual differences in brain development of different infants. By comparing the model output (prediction results) with the target (actual results), the accuracy and reliability of the model in predicting the fold morphology of the cerebral cortex of premature infants can be evaluated. The model outputs some examples of cortical fold morphology at 40 weeks of gestation. The model is able to capture the individual differences in brain development of different premature infants and accurately predict the changing trend of fold morphology in the future. This result not only verifies the effectiveness of the model, but also provides a new perspective and tool for understanding the brain development process. For example, the predicted results of individuals 1 and 4 are compared with the actual (target) results. Comparison of brain fold morphology shows that the model prediction accuracy is high, which indicates that the model has high accuracy in predicting the fold morphology of the cerebral cortex of premature infants and can capture key features of brain development. Since the model adopts the β-VAE structure and improves performance through hyperparameter optimization, it can learn effective potential representations with limited training samples and avoid overfitting problems, which proves the effectiveness and robustness of the model in complex biological data processing tasks. The model can still learn effective potential representations and avoid overfitting problems with limited training samples, thanks to the regularization function of the β-VAE model and the fine adjustment of hyperparameter optimization; these results show that the model performs well in complex biological data processing tasks and has broad application prospects and potential.

[0035] In summary, this study successfully constructed a β-VAE model that can predict the fold morphology of the cerebral cortex of premature infants through a series of steps including data acquisition, preprocessing, model pretraining, retraining, hyperparameter optimization, model evaluation and result analysis. This model not only provides a new perspective and tool for understanding the brain development process, but also provides strong support for clinical diagnosis and treatment in related fields.

[0036] The present invention is described with reference to methods, algorithms and experimental flow charts according to embodiments of the invention.

[0037] It should be noted that, in this application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0038] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0039] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for predicting the development of early cortical folds in the human brain based on a neural network model, characterized in that: include: S1, obtain imaging data of adult brain, 30-week gestational age, and 40-week gestational age premature infant brain; S2, based on the brain negative skeleton technology, extracts the three-dimensional skeleton structure of cortical folds from the image data obtained from S1; S3, using the wrinkle skeleton data of S2 adults as input to pre-train the β variational autoencoder model to achieve wrinkle reconstruction, and then using the wrinkle skeleton data at 30 weeks of gestation as input to the pre-trained β variational autoencoder model to predict the wrinkle skeleton morphology at 40 weeks of gestation; S4 outputs the predicted cortical folds at 40 weeks of gestation, which are highly similar to the actual brain fold morphology.

2. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 1, characterized in that: The S1 brain image data are T1-weighted MRI image data of adults and extremely premature infants.

3. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 1, characterized in that: The three-dimensional skeleton structure of cortical folds extracted by S2 includes: S21, using the brain extraction algorithm to preprocess the image data in S1 and extract the cerebral cortex area; S22, based on the cerebral cortex area image data extracted in S21, reconstructing a three-dimensional surface model of the cerebral cortex using a three-dimensional reconstruction technology; S23, converting the three-dimensional surface model of the cerebral cortex reconstructed in S22 into a negative model; S24, applying the skeleton extraction algorithm on the negative model of S23 to extract the three-dimensional skeleton structure of the cortical folds; S25, post-processing the three-dimensional skeleton structure extracted by S24, optimizing and reconstructing, and obtaining the three-dimensional skeleton structure of the cortical folds.

4. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 3, characterized in that: The S3 β variational autoencoder model includes: S31, inputting the three-dimensional skeleton structure of the cortical folds extracted in S2; S32, construct the β-VAE model framework, which includes an encoder and a decoder. The encoder is responsible for mapping the input 3D cortical geometry information to the latent space, while the decoder is responsible for reconstructing the 3D cortical structure from the latent space. S33, using the preprocessed adult brain MRI data as the training set, the β-VAE model is trained, and the model parameters are adjusted by minimizing the reconstruction error and the KL divergence between the latent variable distribution and the prior distribution. The training model learns the skeleton topology of adult brain folds and realizes the reconstruction of adult brain folds data; the reconstruction error adopts the cross entropy loss, and the prior distribution adopts the central Gaussian distribution; the pre-trained model is evaluated using the validation set, and the pre-trained machine learning model is obtained according to the model evaluation index; S34, using the preprocessed premature infant image data as the training set, retraining the β-VAE model pre-trained in S33. By inputting the cortical fold skeleton data of infants at 30 weeks of gestation, the model learns and predicts the fold morphology of these areas at 40 weeks of gestation; S35, data partitioning and model optimization, during the training process, the data set is divided into training set, validation set and test set to adjust and optimize model parameters, evaluate the performance of the model, and finally obtain the optimal machine learning model; determine the best model hyperparameter combination, the hyperparameter combination includes β value, latent space size, batch size, number of training rounds and learning rate.

5. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 4, characterized in that: The S35 hyperparameter combinations are: β value range is 1~8, latent space size range is 2~500, batch size range is 4~16, number of training rounds range is 500~2000, and learning rate range is 1e-4~1e-2.

6. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 5 is characterized in that: The optimal combination of hyperparameters is: β value is 2, latent space size is 300, batch size is 8, number of training rounds is 1000, and learning rate is 1e-3.

7. The method for predicting the development of early cortical folds in the human brain based on a neural network model according to claim 1, characterized in that: The hyperparameter combination of the optimization model adopts any one of grid search, random search or Bayesian optimization.

8. A system for implementing the method for predicting the development of early cortical folds in the human brain based on a neural network model as described in any one of claims 1 to 7, characterized in that: include: The data acquisition and processing module is used to acquire the imaging data of the 30-week fetal and adult brains, and to perform nonlinear calibration and reconstruction preprocessing based on brain sulci; 3D skeleton extraction module, used to extract the 3D skeleton structure of cortical folds; The model training and prediction module is used to input the wrinkle skeleton data at 30 weeks of gestational age into the pre-trained model to predict the wrinkle skeleton morphology at 40 weeks of gestational age; Hyperparameter optimization module, used to obtain the best hyperparameter combination; The result evaluation and verification module is used to verify the accuracy of the model in predicting the cortical fold morphology at 40 weeks of gestational age and its effectiveness in practical applications; The user interaction and output module is used to output the prediction results to the user in graphical or tabular form.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for predicting the development of early cortical folds in the human brain based on a neural network model as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the development of early cortical folds in the human brain based on a neural network model as described in any one of claims 1 to 7 are implemented.

Images