Star Shape Prior in Fully Convolutional Networks for Skin Lesion Segmentation
This work addresses the challenge of encoding prior knowledge into deep learning frameworks for medical image segmentation, which is incremental as it builds on existing FCN methods by adding a specific regularization term.
The authors tackled the problem of incorporating structural prior knowledge into deep learning for medical image segmentation by proposing a star shape prior loss term in a fully convolutional network, achieving first place among 21 teams on the ISBI 2017 skin lesion segmentation challenge dataset.
Semantic segmentation is an important preliminary step towards automatic medical image interpretation. Recently deep convolutional neural networks have become the first choice for the task of pixel-wise class prediction. While incorporating prior knowledge about the structure of target objects has proven effective in traditional energy-based segmentation approaches, there has not been a clear way for encoding prior knowledge into deep learning frameworks. In this work, we propose a new loss term that encodes the star shape prior into the loss function of an end-to-end trainable fully convolutional network (FCN) framework. We penalize non-star shape segments in FCN prediction maps to guarantee a global structure in segmentation results. Our experiments demonstrate the advantage of regularizing FCN parameters by the star shape prior and our results on the ISBI 2017 skin segmentation challenge data set achieve the first rank in the segmentation task among $21$ participating teams.