Brain image classification method and device based on magnetic resonance imaging and deep learning

Abstract

The invention relates to a brain image classification method and device based on magnetic resonance imaging and deep learning, and the method comprises the following steps: obtaining original MRI scanning image data to be classified, and carrying out the preprocessing, and obtaining a three-dimensional MRI image; taking the three-dimensional MRI image as an input of a trained classification network model to obtain a final classification result; wherein the classification network model carries out 3D to 2D feature dimension conversion on the three-dimensional MRI image along an axial plane, a sagittal plane and a coronal plane respectively, corresponding initial classification results are obtained through an axial locus base classifier, a sagittal locus base classifier and a coronal locus base classifier respectively, and integrating and fusing the multiple initial classification results to acquire the final classification result. Compared with the prior art, the invention has the advantages of high classification precision, low model complexity and the like.

Description

technical field [0001] The present invention relates to the technical field of computer-aided information processing, in particular to a brain image classification method and device based on magnetic resonance imaging and deep learning. Background technique [0002] Parkinson's disease, the second most common neurological disorder in the world's elderly population, is caused by the progressive loss of dopaminergic neurons in the substantia nigra compacta (SNc) of the midbrain. Its clinical manifestations mainly include trembling, stiffness, slowness of movement, difficulty walking, posture and balance disturbance and other activity disturbances. In 2015, 6.2 million people worldwide were infected with Parkinson's disease, resulting in about 117,400 deaths. In addition, as the world's aging population surges, it imposes a huge economic burden on governments. Therefore, early detection and monitoring of the disease is of great significance. [0003] Magnetic resonance imagi...

AI Technical Summary

Problems solved by technology

At present, some research has been devoted to establishing an MRI-based deep learning model for PD information processing, but there are still the following problems: (1) Using the entire 3D MRI as input to construct a 3D CNN model, due to high memory usage and computational cost , which increases the difficulty of model optimization; (2) using two-dimensional MRI as input to construct a 2D CNN model cannot provide sufficient information due to the absence of nuclear sharing in the third dimension; (3) brain lesions in early PD patients only Occurs in a local area, the target area is small, the noise information is large, and the deep convolutional network model is extremely easy to overfit

Therefore, it is still a challenging task to construct a deep learning network structure based on brain MRI imaging to classify brain lesions.

Images