UGB-SegNet: Uncertainty-Guided Multi-Scale Attention and Boundary-Aware Learning for Breast Ultrasound Lesion Segmentation
- 1Feng chia university , Taichung ( Taiwan)
Abstract
Accurate breast lesion segmentation in ultrasound is difficult because speckle noise, heterogeneous lesion appearance, and poorly defined margins can obscure clinically relevant boundaries. This work presents UGB-SegNet, an uncertainty-guided breast ultrasound segmentation network that combines four components: multi-scale convolutional block attention (CBAM) at three EfficientNet-B0 encoder stages, a learnable feature pyramid network for adaptive multi-scale fusion, an entropy-guided decoder that routes fine-grained encoder information toward uncertain regions, and a boundary-aware composite loss with deep supervision. The model was evaluated on the public BUSI dataset (647 annotated lesion images) using a stratified 454/64/129 train/validation/test split. On the held-out test set, UGB-SegNet achieved 81.30% Dice, 68.49% IoU, 81.71% sensitivity, 98.14% specificity, and 15.63-pixel HD95. Under identical training conditions it outperformed five directly trained baselines: U-Net, Attention U-Net, SegNet, DeepLabV3+, and TransUNet. A five-fold resampling experiment over the development set with the held-out test set fixed yielded a mean Dice of 76.36% +/-1.66% (95% CI 74.90-77.81). Reported ablations attribute gains of +2.06 Dice points to multi-scale CBAM, +1.52 to learnable FPN fusion, +1.22 to the uncertainty-guided decoder, and +1.24 to boundary-aware training. UGB-SegNet contains 14.00M parameters and runs at 62.4 FPS at 224 x 224 resolution on the tested NVIDIA GPU, providing a compact accuracy-efficiency trade-off for future prospective clinical validation.
Related
- AMF-U-Net: an adaptive multimodal fusion residual attention 3D U-Net for boundary-aware brain tumour segmentation
- Structure-preserving lightweight skin lesion segmentation with dual-resolution attention and boundary-aware fusion
- Boundary-interior ratio: a spatially decomposed evaluation framework for CNN and mamba-based breast ultrasound segmentation
- Boundary-aware multi-scale residual learning with hybrid radiomic–deep fusion for lung tumor segmentation and classification
- Deep learning-based boundary-accurate GTV segmentation in glioblastoma using multimodal MRI: a radiotherapy-oriented evaluation
BibTeX
@misc{alam2026ugbsegnet,
title = {{UGB-SegNet: Uncertainty-Guided Multi-Scale Attention and Boundary-Aware Learning for Breast Ultrasound Lesion Segmentation}},
author = {T. Alam and F. R. Hsu},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.03.26364633},
url = {https://www.medrxiv.org/content/10.64898/2026.10.03.26364633v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - UGB-SegNet: Uncertainty-Guided Multi-Scale Attention and Boundary-Aware Learning for Breast Ultrasound Lesion Segmentation
AU - T. Alam
AU - F. R. Hsu
PY - 2026
DA - 2026/10/03
PB - medRxiv
DO - 10.64898/2026.10.03.26364633
UR - https://www.medrxiv.org/content/10.64898/2026.10.03.26364633v1
AB - Accurate breast lesion segmentation in ultrasound is difficult because speckle noise, heterogeneous lesion appearance, and poorly defined margins can obscure clinically relevant boundaries. This work presents UGB-SegNet, an uncertainty-guided breast ultrasound segmentation network that combines four components: multi-scale convolutional block attention (CBAM) at three EfficientNet-B0 encoder stages, a learnable feature pyramid network for adaptive multi-scale fusion, an entropy-guided decoder that routes fine-grained encoder information toward uncertain regions, and a boundary-aware composite loss with deep supervision. The model was evaluated on the public BUSI dataset (647 annotated lesion images) using a stratified 454/64/129 train/validation/test split. On the held-out test set, UGB-SegNet achieved 81.30% Dice, 68.49% IoU, 81.71% sensitivity, 98.14% specificity, and 15.63-pixel HD95. Under identical training conditions it outperformed five directly trained baselines: U-Net, Attention U-Net, SegNet, DeepLabV3+, and TransUNet. A five-fold resampling experiment over the development set with the held-out test set fixed yielded a mean Dice of 76.36% +/-1.66% (95% CI 74.90-77.81). Reported ablations attribute gains of +2.06 Dice points to multi-scale CBAM, +1.52 to learnable FPN fusion, +1.22 to the uncertainty-guided decoder, and +1.24 to boundary-aware training. UGB-SegNet contains 14.00M parameters and runs at 62.4 FPS at 224 x 224 resolution on the tested NVIDIA GPU, providing a compact accuracy-efficiency trade-off for future prospective clinical validation.
ER -