DBF-Net: A Dual-Branch Network with Feature Fusion for Ultrasound Image Segmentation

TL;DR

This paper introduces UBBS-Net, a dual-branch neural network with feature fusion that enhances ultrasound lesion segmentation by better capturing boundary and body structure relationships, outperforming existing methods.

Contribution

The paper proposes a novel dual-branch network with feature fusion for improved boundary-aware ultrasound image segmentation, addressing limitations of previous deep learning approaches.

Findings

Achieved Dice scores of 81.05% for breast cancer segmentation

Outperformed existing methods on three public datasets

Demonstrated effectiveness of boundary and body relationship modeling

Abstract

Accurately segmenting lesions in ultrasound images is challenging due to the difficulty in distinguishing boundaries between lesions and surrounding tissues. While deep learning has improved segmentation accuracy, there is limited focus on boundary quality and its relationship with body structures. To address this, we introduce UBBS-Net, a dual-branch deep neural network that learns the relationship between body and boundary for improved segmentation. We also propose a feature fusion module to integrate body and boundary information. Evaluated on three public datasets, UBBS-Net outperforms existing methods, achieving Dice Similarity Coefficients of 81.05% for breast cancer, 76.41% for brachial plexus nerves, and 87.75% for infantile hemangioma segmentation. Our results demonstrate the effectiveness of UBBS-Net for ultrasound image segmentation. The code is available at https://github.com/apple1986/DBF-Net.