A Technical Survey on Brain Tumor Segmentation using CNN

摘要

Brain tumor is a severe disease which may lead to the end of life if not attended and treated in its early stage. To know the condition of the tumor various conventional and recently developed deep learning based segmentation and classification methods have been proposed by researchers. Deep learning is found to be efficient and robust for classification and segmentation as it finds the fine-to-coarse information about the tumors. The main component of deep learning is layered neural network architecture popularly known as convolutional neural network. Depending upon architecture distinct information from the brain images can be captured and further analyzed. Still more research is required in this area to get high segmentation and classification accuracy. In this paper various CNN architecture used by researchers in the literature has been discussed, compared and analyzed. This layered architecture performs better along with some pre-processing and post-processing stages. The researches used various datasets for their study and the qualitative segmentation and classification was evaluated by various performance measures (sensitivity, specificity, accuracy and Dice similarity coefficient). Here the detailed description about the BRATS dataset, performance measures and CNN architectures have been provided for the readers working in this area.