Automatic segmentation of medical images using convolutional neural networks

This paper presents a neural network architecture for segmentation of medical images. We have chosen to test and implement various Convolutional Neural Network (CNN). We chose to apply this work on a topic of cerebral images segmentation containing brain tumors. The main objective is to choose the best architecture and parameterization applied into a task of a MRI brain tumor while treating a small database. Segmentation and learning assessment tests show good performance using our personalized CNN architecture.