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

2026-01-20

AI Summary

This work addresses the challenge in medical image segmentation where large anatomical structures often dominate model predictions due to significant organ volume disparities and imbalanced sample distributions, leading to poor segmentation of small or sparse regions. To mitigate this bias, the authors propose PDANet, a lightweight network that integrates a partial decoder attention mechanism with a model-agnostic contour-weighted loss function to emphasize boundary information and enhance segmentation accuracy for fine structures. Evaluated on three public datasets, PDANet consistently outperforms nine state-of-the-art methods, achieving average Dice score improvements of 2.32%, 1.67%, and 3.60%, respectively, thereby demonstrating its effectiveness and strong generalization capability.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• data imbalance
• medical image segmentation
• small structure segmentation
• class imbalance
• anatomical structure bias

Innovation

• contour-weighted loss
• data imbalance
• medical image segmentation
• partial decoder attention network
• small structure segmentation