Lin Ma

RTCMUNet: retinex-inspired feature modulation for breast ultrasound lesion segmentation

Objective. Breast ultrasound lesion segmentation remains challenging because heterogeneous echogenicity, speckle, posterior shadowing, and weak boundaries impair lesion-margin delineation. Approach. We evaluate a CMU-Net-based implementation, termed RTCMUNet, in which the proposed ML-Retinex block modulates skip featur...

Auxiliary-Data Governance in Breast Ultrasound Segmentation: A Multi-cohort Audit of Annotation Compatibility and Negative Transfer.

Appearance-aware robustness probes for strict external breast ultrasound segmentation under multi-source joint training

A targeted source-inclusion sensitivity analysis indicates model- and cohort-dependent sensitivity to training-pool composition, rather than a universal benefit from adding data or a universally preferred configuration, in breast ultrasound segmentation.