SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation

TL;DR

This paper introduces SelfReg-UNet, a novel self-regularization method that balances supervision and reduces feature redundancy in UNet, leading to improved medical image segmentation performance across multiple datasets.

Contribution

The paper proposes a plug-and-play self-regularization technique for UNet that enhances segmentation accuracy by balancing supervision and reducing feature redundancy.

Findings

Consistent performance improvement on four datasets

Effective reduction of feature redundancy

Easy integration with existing UNet models

Abstract

Since its introduction, UNet has been leading a variety of medical image segmentation tasks. Although numerous follow-up studies have also been dedicated to improving the performance of standard UNet, few have conducted in-depth analyses of the underlying interest pattern of UNet in medical image segmentation. In this paper, we explore the patterns learned in a UNet and observe two important factors that potentially affect its performance: (i) irrelative feature learned caused by asymmetric supervision; (ii) feature redundancy in the feature map. To this end, we propose to balance the supervision between encoder and decoder and reduce the redundant information in the UNet. Specifically, we use the feature map that contains the most semantic information (i.e., the last layer of the decoder) to provide additional supervision to other blocks to provide additional supervision and reduce feature redundancy by leveraging feature distillation. The proposed method can be easily integrated into existing UNet architecture in a plug-and-play fashion with negligible computational cost. The experimental results suggest that the proposed method consistently improves the performance of standard UNets on four medical image segmentation datasets. The code is available at \url{https://github.com/ChongQingNoSubway/SelfReg-UNet}