A Semantic Segmentation Algorithm for Pleural Effusion Based on DBIF-AUNet

TL;DR

This paper introduces DBIF-AUNet, a novel deep learning model that significantly improves the accuracy of pleural effusion segmentation in CT images by addressing edge ambiguity and feature gaps.

Contribution

The paper proposes a dual-branch fusion attention network with a new feature disentanglement module and hierarchical supervision, advancing medical image segmentation techniques.

Findings

Achieved IoU of 80.1% and Dice of 89.0% on pleural effusion CT images.

Outperformed U-Net++ and Swin-UNet by 5.7%/2.7% and 2.2%/1.5%.

Enhanced segmentation robustness and accuracy for complex medical images.

Abstract

Pleural effusion semantic segmentation can significantly enhance the accuracy and timeliness of clinical diagnosis and treatment by precisely identifying disease severity and lesion areas. Currently, semantic segmentation of pleural effusion CT images faces multiple challenges. These include similar gray levels between effusion and surrounding tissues, blurred edges, and variable morphology. Existing methods often struggle with diverse image variations and complex edges, primarily because direct feature concatenation causes semantic gaps. To address these challenges, we propose the Dual-Branch Interactive Fusion Attention model (DBIF-AUNet). This model constructs a densely nested skip-connection network and innovatively refines the Dual-Domain Feature Disentanglement module (DDFD). The DDFD module orthogonally decouples the functions of dual-domain modules to achieve multi-scale feature complementarity and enhance characteristics at different levels. Concurrently, we design a Branch Interaction Attention Fusion module (BIAF) that works synergistically with the DDFD. This module dynamically weights and fuses global, local, and frequency band features, thereby improving segmentation robustness. Furthermore, we implement a nested deep supervision mechanism with hierarchical adaptive hybrid loss to effectively address class imbalance. Through validation on 1,622 pleural effusion CT images from Southwest Hospital, DBIF-AUNet achieved IoU and Dice scores of 80.1% and 89.0% respectively. These results outperform state-of-the-art medical image segmentation models U-Net++ and Swin-UNet by 5.7%/2.7% and 2.2%/1.5% respectively, demonstrating significant optimization in segmentation accuracy for complex pleural effusion CT images.