A Brain Tumor Segmentation New Method Based on Statistical Thresholding and Multiscale CNN

Brain tumor segmentation is crucial in the diagnosis of disease and radiation therapy. However, automatic or semi-automatic segmentation of the brain tumor is still a challenging task due to the high diversities and the ambiguous boundaries in the appearance of tumor tissue. To solve this problem, we propose a brain tumor segmentation method based on Statistical thresholding and Multiscale Convolutional neural networks. Firstly, the statistical threshold segmentation method was used to roughly segment the brain tumor. Then the 2D multi-modality MRI image obtained by the rough segmentation was input into the multiscale convolution neural network (MSCNN) to obtain the tumor segmentation image. Experimental results on the MICCAI BRATS2015 [1] dataset show that the proposed method can significantly improve the segmentation accuracy.