Boundary Difference Over Union Loss For Medical Image Segmentation

TL;DR

This paper introduces Boundary DoU Loss, a simple, boundary-focused loss function for medical image segmentation that improves boundary accuracy without complex combinations of multiple losses.

Contribution

The paper proposes Boundary DoU Loss, a novel boundary-guided loss function that is easy to implement, stable during training, and adaptable to different boundary regions in medical images.

Findings

Improves boundary segmentation accuracy in medical images.

Effective across multiple models and datasets.

Stable training without additional loss functions.

Abstract

Medical image segmentation is crucial for clinical diagnosis. However, current losses for medical image segmentation mainly focus on overall segmentation results, with fewer losses proposed to guide boundary segmentation. Those that do exist often need to be used in combination with other losses and produce ineffective results. To address this issue, we have developed a simple and effective loss called the Boundary Difference over Union Loss (Boundary DoU Loss) to guide boundary region segmentation. It is obtained by calculating the ratio of the difference set of prediction and ground truth to the union of the difference set and the partial intersection set. Our loss only relies on region calculation, making it easy to implement and training stable without needing any additional losses. Additionally, we use the target size to adaptively adjust attention applied to the boundary regions. Experimental results using UNet, TransUNet, and Swin-UNet on two datasets (ACDC and Synapse) demonstrate the effectiveness of our proposed loss function. Code is available at https://github.com/sunfan-bvb/BoundaryDoULoss.