Automated Thalamus Segmentation in MR Images Using Convolutional Networks

Thalamus segmentation in Magnetic Resonance Image is a challenging task because of the high inter-patient anatomical variability in both shape and size between patients. In this work, we proposed a fast and robust segmentation of thalamus using convolutional neural networks. First, cropped image which included the thalamus are extracted. Convolutional neural network (CNN) is then trained to segment the whole thalamus region. Intensity constrained model is constructed to obtain the final segmentation. Our method performs better than other state-of-the-art methods. The experiment results show that our approach achieves the highest dice scores than other methods.