Brain age prediction method and system based on three-dimensional convolutional neural network

Abstract

The invention relates to a brain age prediction method and system based on a three-dimensional convolutional neural network. The brain age prediction method comprises the steps: collecting a historical sample set which comprises a plurality of pairs of historical structure magnetic resonance image data and the physiological age of a corresponding tester, and dividing the historical sample set intoa training sample set and a testing sample set; preprocessing the historical structure magnetic resonance image data in the training sample set to obtain corresponding processed images; training thethree-dimensional convolutional neural network according to the processed images and the physiological ages of the corresponding testees to obtain a trained three-dimensional convolutional neural network; acquiring current structure magnetic resonance image data of a current tester; and based on the trained three-dimensional convolutional neural network, determining the brain age condition of thecurrent testee according to the current structure magnetic resonance image data, thus realizing end-to-end detection, and being high in the accuracy.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a brain age prediction method and system based on a three-dimensional convolutional neural network. Background technique [0002] The brain shows regular changes in structure and function during the process of development and aging. The pattern of this change is very complex, and it is impossible to obtain the results clinically with the naked eye. In practice, brain age is used as a measure of the pattern of change in this process. [0003] At present, the research on the development and aging trajectory of the brain is not very in-depth. We urgently need a high-precision brain age prediction model to fit the change trajectory of the brain during the development and aging process. On the one hand, it can help us understand the development and aging mechanism of the brain, and strengthen our understanding and understanding of the human brain; on the other hand, ...

AI Technical Summary

Problems solved by technology

[0005] In the existing brain age prediction models based on structural images, most of them use traditional machine learning methods. These methods need to go through the process of feature extraction, feature selection, training models, etc., rely heavily on third-party tools, and lack end-to-end convenience. , and the prediction accuracy cannot meet the needs of clinical application

Images