{"ID":2838854,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.15968","arxiv_id":"2511.15968","title":"Externally Validated Multi-Task Learning via Consistency Regularization Using Differentiable BI-RADS Features for Breast Ultrasound Tumor Segmentation","abstract":"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\u003c0.001) 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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.15968","url_pdf":"https://arxiv.org/pdf/2511.15968v1","authors":"[\"Jingru Zhang\",\"Saed Moradi\",\"Ashirbani Saha\"]","published":"2025-11-20T01:45:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}