Residual Feedback Network for Breast Lesion Segmentation in Ultrasound Image

Abstract

Accurate lesion segmentation in breast ultrasound (BUS) images is of great significance for the clinical diagnosis and treatment of breast cancer. However, precise segmentation on missing/ambiguous boundaries or confusing regions remains challenging. In this paper, we proposed a novel residual feedback network, which enhances the confidence of the inconclusive pixels to boost breast lesion segmentation performance. In the proposed network, a residual representation module is introduced to learn the residual representation of missing/ambiguous boundaries and confusing regions, which promotes the network to make more efforts on those hardly-predicted pixels. Moreover, a residual feedback transmission strategy is designed to update the input of the encoder blocks by combining the residual representation with original features. This strategy could enhance the regions including hardly-predicted pixels, which makes the network can further correct the errors in initial segmentation results. Experimental results on three datasets (3813 images in total) demonstrate that our proposed network outperforms the state-of-the-art segmentation methods. Our code is available at https://github.com/mniwk/RF-Net.