Lesion-Centric Latent Phenotypes from Segmentation Encoders for Breast Ultrasound Interpretability
Mittal, P.; Singh, D.; Chauhan, J.
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 testing on BUS-BRA, lesion-centric pooling and calibration improve separability and enable strong malignancy probing (AUC 0.982), outperforming radiomics and a standard CNN baseline. A simple rule-gated generator further improves BI-RADS-style descriptor consistency on difficult cases.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Biologically-informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post-treatment glioblastoma 94%
- High-Sensitivity Pan-Cancer AI Assessment of Lymph Node Metastasis via Uncertainty Quantification 92%
- Understanding the robustness of vision-language models to medical image artefacts 92%
Similar papers in this journal
- Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features 94%
- Enhancing Biomedical Optical Volumetric Imaging via Self-Supervised Orthogonal Learning 90%
- Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery 90%
Similar papers in this journal
- A Deep Learning Model for Molecular Label Transfer that Enables Cancer Cell Identification from Histopathology Images 92%
- Image-Based Consensus Molecular Subtyping in Rectal Cancer Biopsies and Response to Neoadjuvant Chemoradiotherapy 91%
- Generalizing AI-driven Assessment of Immunohistochemistry across Immunostains and Cancer Types: A Universal Immunohistochemistry Analyzer 90%
Similar papers in this journal
Similar papers in this journal
- Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes 95%
- Integrated radiogenomics models predict response to neoadjuvant chemotherapy in high grade serous ovarian cancer 92%
- Weakly supervised classification of rare aortic valve malformations using unlabeled cardiac MRI sequences 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.