Clustering patch embeddings from a pre-trained breast cancer risk model identifies recurring phenotypes correlated with 5-year risk, including dense tissue, microcalcifications, and shortcut artifacts.
Morón-Duran, Albert Tauler, Sara C
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Sparse autoencoders resolve superposition in image-based neural representations of neurons, recovering metric geometry and enabling de novo cross-modal alignment to scRNA-seq via Gromov-Wasserstein transport.
citing papers explorer
-
Revealing Mammographic Phenotypes in Deep Learning Breast Cancer Risk Models
Clustering patch embeddings from a pre-trained breast cancer risk model identifies recurring phenotypes correlated with 5-year risk, including dense tissue, microcalcifications, and shortcut artifacts.
-
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
Sparse autoencoders resolve superposition in image-based neural representations of neurons, recovering metric geometry and enabling de novo cross-modal alignment to scRNA-seq via Gromov-Wasserstein transport.