Partial Decoder Attention Network with Contour-weighted Loss Function for Data-Imbalance Medical Image Segmentation

TL;DR

This paper introduces PDANet, a lightweight medical image segmentation network with a contour-weighted loss, effectively addressing data imbalance issues and improving segmentation accuracy for small and underrepresented structures across multiple datasets.

Contribution

The paper proposes a novel contour-weighted loss function and a partial decoder network, PDANet, to enhance segmentation of small and imbalanced structures in medical images, outperforming existing methods.

Findings

PDANet outperformed nine state-of-the-art methods in three segmentation tasks.

Contour-weighted loss improved Dice scores by up to 3.60%.

Method demonstrated robustness and flexibility across multiple datasets.

Abstract

Image segmentation is pivotal in medical image analysis, facilitating clinical diagnosis, treatment planning, and disease evaluation. Deep learning has significantly advanced automatic segmentation methodologies by providing superior modeling capability for complex structures and fine-grained anatomical regions. However, medical images often suffer from data imbalance issues, such as large volume disparities among organs or tissues, and uneven sample distributions across different anatomical structures. This imbalance tends to bias the model toward larger organs or more frequently represented structures, while overlooking smaller or less represented structures, thereby affecting the segmentation accuracy and robustness. To address these challenges, we proposed a novel contour-weighted segmentation approach, which improves the model's capability to represent small and underrepresented structures. We developed PDANet, a lightweight and efficient segmentation network based on a partial decoder mechanism. We evaluated our method using three prominent public datasets. The experimental results show that our methodology excelled in three distinct tasks: segmenting multiple abdominal organs, brain tumors, and pelvic bone fragments with injuries. It consistently outperformed nine state-of-the-art methods. Moreover, the proposed contour-weighted strategy improved segmentation for other comparison methods across the three datasets, yielding average enhancements in Dice scores of 2.32%, 1.67%, and 3.60%, respectively. These results demonstrate that our contour-weighted segmentation method surpassed current leading approaches in both accuracy and robustness. As a model-independent strategy, it can seamlessly fit various segmentation frameworks, enhancing their performance. This flexibility highlighted its practical importance and potential for broad use in medical image analysis.