Recurrent Mask Refinement for Few-Shot Medical Image Segmentation
This addresses the challenge of generalizing deep learning to unseen medical image classes with limited labeled data, representing a strong specific gain in the domain of medical imaging.
The paper tackles the problem of few-shot medical image segmentation by proposing a framework with a context relation encoder and recurrent mask refinement, achieving average improvements of 16.32%, 8.45%, and 6.24% in DSC over state-of-the-art methods on three datasets.
Although having achieved great success in medical image segmentation, deep convolutional neural networks usually require a large dataset with manual annotations for training and are difficult to generalize to unseen classes. Few-shot learning has the potential to address these challenges by learning new classes from only a few labeled examples. In this work, we propose a new framework for few-shot medical image segmentation based on prototypical networks. Our innovation lies in the design of two key modules: 1) a context relation encoder (CRE) that uses correlation to capture local relation features between foreground and background regions; and 2) a recurrent mask refinement module that repeatedly uses the CRE and a prototypical network to recapture the change of context relationship and refine the segmentation mask iteratively. Experiments on two abdomen CT datasets and an abdomen MRI dataset show the proposed method obtains substantial improvement over the state-of-the-art methods by an average of 16.32%, 8.45% and 6.24% in terms of DSC, respectively. Code is publicly available.