Brain tissue segmentation based on convolutional neural networks

With the development and improvement of imaging technology in the medical field, image technology, which provides important scientific basis for disease analysis, has become an indispensable part of disease diagnosis. Therefore, how to dig out valuable information in these images and help doctors to make diagnosis more accurately and quickly have always been the concern of researchers. In this paper, we have made some improvements to the FCN network and incorporated Inception Architecture into it to build several convolutional neural networks. In our experiments, we trained the networks in IBSR dataset and contrasted the results with some classical methods. The results demonstrate that our improved network has high efficiency and accuracy in segmentation of MRI brain images.