Brain image segmentation method and system based on saliency learning convolution nerve network

Abstract

The invention discloses a brain image segmentation method and system based on a saliency learning convolution nerve network; the brain image segmentation method comprises the following steps: firstly proposing a saliency learning method to obtain a MR image saliency map; carrying out saliency enhanced transformation according to the saliency map, thus obtaining a saliency enhanced image; splitting the saliency enhanced image into a plurality of image blocks, and training a convolution nerve network so as to serve as the final segmentation model. The saliency learning model can form the saliency map, and said class information is obtained according to a target space position, and has no relation with image gray scale information; the saliency information can obviously enhance the target saliency, thus improving the target class and background class discrimination, and providing certain robustness for gray scale inhomogeneity. The convolution nerve network trained by the saliency enhanced images can be employed to learn the saliency enhanced image discrimination information, thus more effectively solving the gray scale inhomogeneity problems in the brain MR image.

Description

technical field [0001] The invention relates to the technical field of segmentation on medical images, in particular to a brain image segmentation method and system based on a saliency learning convolutional neural network. Background technique [0002] Brain diseases have become the focus of attention in today's society due to their serious harm. Magnetic resonance images (MR, magnetic resonance) have the advantages of high contrast and rich display information, and have become the main imaging method for auxiliary diagnosis of brain diseases. Using computer to automatically analyze medical images has become an important means of assisting clinical diagnosis. Medical image segmentation technology can extract the target area, which is the basis for quantitative analysis and diagnosis of the lesion area. Therefore, inventing a brain MR image segmentation method is of great significance for improving the accuracy and efficiency of brain disease diagnosis. [0003] The exist...

AI Technical Summary

Problems solved by technology

This heterogeneous distribution of samples makes it difficult to train an effective deep learning model

[0005] Based on the above analysis, it is difficult to directly use the existing deep learning model to obtain a better segmentation effect.

Images