Article

Extended pre-training of histopathology foundation models uncovers co-existing breast cancer archetypes characterized by RNA splicing or TGF-β dysregulation

2025-03-31

Abstract excerpt

In recent years, histopathology foundation models (hFM) have rapidly advanced in size and complexity, achieving excellent performance in tasks such as cancer diagnosis and biomarker discovery. Here, we reveal novel capabilities of these models by specializing hFMs, originally trained on diverse tissue types, specifically to invasive tumor tissue. It enables unprecedented discrimination of visually similar yet mole...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5f2bf8e8-1d2b-5466-930e-f00f8b8a9f62
DOI: 10.1101/2025.03.27.645192

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Extended pre-training of histopathology foundation models uncovers co-existing breast cancer archetypes characterized by RNA splicing or TGF-β dysregulationDOI 10.1101/2025.03.27.645192Read

Adaptive Integration of Heterogeneous Foundation Models to Find Histologically Predictable Genes in Breast CancerSemantic proximity Read

PathOmCLIP: Connecting tumor histology with spatial gene expression via locally enhanced contrastive learning of Pathology and Single-cell foundation modelSemantic proximity Read

Integrating Histology with Spatial Molecular Programs Using a Multimodal Foundation ModelSemantic proximity Read

Dissecting and directing pathology foundation modelsSemantic proximity Read

Morpho-FM: spatial molecular reconstruction from routine H&E histology using transcriptomic foundation-model priorsSemantic proximity Read

Translating Histopathology Foundation Model Embeddings into Cellular and Molecular Features for Clinical StudiesSemantic proximity Read

Multi-Modal Foundation Model with Whole-Slide Attention Enables Transferrable Digital Pathology at Single-Cell ResolutionSemantic proximity Read

Contrastive Learning for Omics-guided Whole-slide Visual Embedding RepresentationSemantic proximity Read

OpenSlideFM: A Computationally Efficient Multi-Scale Foundation Model for Computational PathologySemantic proximity Read

Multiple instance learning on tile level-pathology images provides accurate and interpretable classification for breast cancer molecular subtypesSemantic proximity Read

BRIDGE: A Multi-organ Histo-ST Foundation Model Enables Virtual Spatial Transcriptomics for Enhanced Few-shot Cancer DiagnosisSemantic proximity Read

A foundation model for generalizable cancer diagnosis and survival prediction from histopathological imagesSemantic proximity Read