Edge-Texture and Transformer Enhanced Dual-Path Networks for Breast Mass Segmentation in Mammograms

Accurate segmentation of breast masses in mammograms is essential for early detection and effective treatment of breast cancer. We propose three lightweight dual-path architectures—ETDP-U \(^2\) -Net, DPCA-U \(^2\) -Net, and DPTrans-U \(^2\) -Net—that integrate edge–texture fusion, cross-attention, and transformer-based encoding to enhance feature representation while drastically reducing model size. On the CBIS-DDSM dataset, our models consistently outperform U-Net variants despite being up to three times smaller. ETDP-U \(^2\) -Net achieved the best performance (Dice: 0.9162, IoU: 0.8485), while DPTrans-U \(^2\) -Net delivered comparable accuracy with only 4.2M parameters. These results highlight the potential of the proposed architectures to combine efficiency and accuracy, making them promising candidates for real-world computer-aided diagnosis in breast cancer screening.