Back

Lesion-Centric Latent Phenotypes from Segmentation Encoders for Breast Ultrasound Interpretability

2026-03-06 radiology and imaging Title + abstract only
View on medRxiv
Show abstract

We propose a lesion-centric phenotype learning pipeline for interpretable breast ultrasound (BUS). Predicted lesion masks are used for mask-weighted pooling of segmentation-encoder latents, producing compact embeddings that suppress background influence; a lightweight calibration step improves cross-dataset consistency. We cluster embeddings to discover latent phenotypes and relate phenotype structure to morphology descriptors (compactness, boundary sharpness). On BUSI and BUS-UCLM with external...

Predicted journal destinations