Externally Validated Multi-Task Learning via Consistency Regularization Using Differentiable BI-RADS Features for Breast Ultrasound Tumor Segmentation
Zhang, Jingru, Moradi, Saed, Saha, Ashirbani
–arXiv.org Artificial Intelligence
Multi-task learning can suffer from destructive task interference, where jointly trained models underperform single-task baselines and limit generalization. To improve generalization performance in breast ultrasound-based tumor segmentation via multi-task learning, we propose a novel consistency regularization approach that mitigates destructive interference between segmentation and classification. The consistency regularization approach is composed of differentiable BI-RADS-inspired morphological features. We validated this approach by training all models on the BrEaST dataset (Poland) and evaluating them on three external datasets: UDIAT (Spain), BUSI (Egypt), and BUS-UCLM (Spain). Our comprehensive analysis demonstrates statistically significant (p<0.001) improvements in generalization for segmentation task of the proposed multi-task approach vs. the baseline one: UDIAT, BUSI, BUS-UCLM (Dice coefficient=0.81 vs 0.59, 0.66 vs 0.56, 0.69 vs 0.49, resp.). The proposed approach also achieves state-of-the-art segmentation performance under rigorous external validation on the UDIAT dataset.
arXiv.org Artificial Intelligence
Nov-21-2025
- Country:
- Africa > Middle East
- Egypt (0.24)
- Europe
- North America
- Canada > Ontario
- Hamilton (0.15)
- United States > Connecticut (0.04)
- Canada > Ontario
- South America > Chile
- Africa > Middle East
- Genre:
- Research Report > Experimental Study (0.35)
- Industry:
- Health & Medicine
- Diagnostic Medicine > Imaging (0.95)
- Therapeutic Area (0.70)
- Health & Medicine
- Technology: