Article

Cracks in the Foundation: How Data-Hungry and Sensitive to Domain Shift are Vision Foundation Models for Computational Pathology?

2026-01-06

Abstract excerpt

<h4>Background</h4> Vision Foundation Models (VFM) have emerged as a promising approach for computational pathology, offering scalable feature representations that may reduce labelled-data requirements and improve robustness to variation in tissue preparation and digitisation. However, VFM decoder and dataset size requirements as well as the performance under real-world domain shifts remain unclear. <h4>Methods</...

Topics

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

Identifiers and source

Literature Corpus work: dfd580fd-8972-5940-bc58-f99618041fff
DOI: 10.64898/2026.01.06.25342815

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Cracks in the Foundation: How Data-Hungry and Sensitive to Domain Shift are Vision Foundation Models for Computational Pathology?DOI 10.64898/2026.01.06.25342815Read

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

Evaluating Vision and Pathology Foundation Models for Computational Pathology: A Comprehensive Benchmark StudySemantic proximity Read

Built to last? Reproducibility and Reusability of Deep Learning Algorithms in Computational PathologySemantic proximity Read

Dissecting and directing pathology foundation modelsSemantic proximity Read

Coreset Selection for Scalable and Efficient Prostate Cancer Grading in Digital PathologySemantic proximity Read

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

Evaluating reproducibility of AI algorithms in digital pathology with DAPPERSemantic proximity Read

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

Assessing Foundation Models for Computational Pathology in Endometrial CancerSemantic proximity Read

Transferability of Deep Learning Models for Focus Quality Assessment in Digital PathologySemantic proximity Read

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