Hybrid Attention Network for Accurate Breast Tumor Segmentation in Ultrasound Images

TL;DR

This paper introduces a hybrid attention network that combines advanced attention mechanisms and a DenseNet encoder to improve the accuracy of breast tumor segmentation in ultrasound images, addressing noise and fuzzy boundaries.

Contribution

The proposed architecture uniquely integrates global spatial attention, positional encoding, and a spatial feature enhancement block within a multi-branch decoder for improved segmentation.

Findings

Outperforms existing methods on public datasets

Enhances focus on tumor regions through attention mechanisms

Achieves higher accuracy and robustness in segmentation

Abstract

Breast ultrasound imaging is a valuable tool for early breast cancer detection, but automated tumor segmentation is challenging due to inherent noise, variations in scale of lesions, and fuzzy boundaries. To address these challenges, we propose a novel hybrid attention-based network for lesion segmentation. Our proposed architecture integrates a pre-trained DenseNet121 in the encoder part for robust feature extraction with a multi-branch attention-enhanced decoder tailored for breast ultrasound images. The bottleneck incorporates Global Spatial Attention (GSA), Position Encoding (PE), and Scaled Dot-Product Attention (SDPA) to learn global context, spatial relationships, and relative positional features. The Spatial Feature Enhancement Block (SFEB) is embedded at skip connections to refine and enhance spatial features, enabling the network to focus more effectively on tumor regions. A hybrid loss function combining Binary Cross-Entropy (BCE) and Jaccard Index loss optimizes both pixel-level accuracy and region-level overlap metrics, enhancing robustness to class imbalance and irregular tumor shapes. Experiments on public datasets demonstrate that our method outperforms existing approaches, highlighting its potential to assist radiologists in early and accurate breast cancer diagnosis.