# Foundation Models -- A Panacea for Artificial Intelligence in Pathology?

arXiv: https://arxiv.org/abs/2502.21264 · HTML: https://mlsanity.com/paper/2502.21264/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2025.

## Built on by (most cited first, 10 of 10)

- [PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology](https://mlsanity.com/paper/2505.20202/) (2025)
- [Beyond the Failures: Rethinking Foundation Models in Pathology](https://mlsanity.com/paper/2510.23807/) (2025)
- [The PAR dataset: Prostate biopsy whole slide images from an underrepresented Middle Eastern population](https://mlsanity.com/paper/2512.03854/) (2025)
- [Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness](https://mlsanity.com/paper/2603.05884/) (2026)
- [Parameter-Efficient Fine-Tuning of Multispectral Foundation Models for Hyperspectral Image Classification](https://mlsanity.com/paper/2505.15334/) (2025)
- [Validation of Diagnostic Artificial Intelligence Models for Prostate Pathology in a Middle Eastern Cohort](https://mlsanity.com/paper/2512.17499/) (2025)
- [Artificial Intelligence-Assisted Prostate Cancer Diagnosis for Reduced Use of Immunohistochemistry](https://mlsanity.com/paper/2504.00979/) (2025)
- [Finding Holes: Pathologist Level Performance Using AI for Cribriform Morphology Detection in Prostate Cancer](https://mlsanity.com/paper/2510.13995/) (2025)
- [AI-based Prediction of Biochemical Recurrence from Biopsy and Prostatectomy Samples](https://mlsanity.com/paper/2601.21022/) (2026)
- [Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples](https://mlsanity.com/paper/2605.02614/) (2026)

## Abstract (arXiv)

The role of artificial intelligence (AI) in pathology has evolved from aiding diagnostics to uncovering predictive morphological patterns in whole slide images (WSIs). Recently, foundation models (FMs) leveraging self-supervised pre-training have been widely advocated as a universal solution for diverse downstream tasks. However, open questions remain about their clinical applicability and generalization advantages over end-to-end learning using task-specific (TS) models. Here, we focused on AI with clinical-grade performance for prostate cancer diagnosis and Gleason grading. We present the largest validation of AI for this task, using over 100,000 core needle biopsies from 7,342 patients across 15 sites in 11 countries. We compared two FMs with a fully end-to-end TS model in a multiple instance learning framework. Our findings challenge assumptions that FMs universally outperform TS models. While FMs demonstrated utility in data-scarce scenarios, their performance converged with - and was in some cases surpassed by - TS models when sufficient labeled training data were available. Notably, extensive task-specific training markedly reduced clinically significant misgrading, misdiagnosis of challenging morphologies, and variability across different WSI scanners. Additionally, FMs used up to 35 times more energy than the TS model, raising concerns about their sustainability. Our results underscore that while FMs offer clear advantages for rapid prototyping and research, their role as a universal solution for clinically applicable medical AI remains uncertain. For high-stakes clinical applications, rigorous validation and consideration of task-specific training remain critically important. We advocate for integrating the strengths of FMs and end-to-end learning to achieve robust and resource-efficient AI pathology solutions fit for clinical use.