Automatic Prostate Segmentation on MR Images with Deeply Supervised Network

Abstract

Accurate and efficient segmentation of prostate image plays an important role in the diagnosis of prostate cancer. Since convolutional neural network demonstrates superior performance in computer vision applications, we present a multi-layer deeply supervised deconvolution network (DSDN) which completes end-to-end training to automatically segment magnetic resonance (MR) images. We put additional deeply supervised layers to supervise the performance of hidden layers. During training, the backpropagation process of gradient information in the additional deeply supervised layers accelerates the parameters update for hidden layers, which makes the trained model has strong capacity of features learning as well as passes the extracted features from shallow layers to higher layers effectively. A set of experiments using prostate magnetic resonance (MR) images is carried out to demonstrate that significant segmentation accuracy improvement has been achieved by our proposed method compared to other reported approaches.