Training state-of-the-art pathology foundation models with orders of magnitude less data
Preprint
Abstract
The field of computational pathology has recently seen rapid advances driven by the development of modern vision foundation models (FMs), typically trained on vast collections of pathology images. Recent studies demonstrate that increasing the training data set and model size and integrating domain-specific image processing techniques can significantly enhance the model's performance on downstream tasks. Building on these insights, our work incorporates several recent modifications to the standard DINOv2 framework from the literature to optimize the training of pathology FMs. We also apply a post-training procedure for fine-tuning models on higher-resolution images to further enrich the information encoded in the embeddings. We present three novel pathology FMs trained on up to two orders of magnitude fewer WSIs than those used to train other state-of-the-art FMs while demonstrating a comparable or superior performance on downstream tasks. Even the model trained on TCGA alone (12k WSIs) outperforms most existing FMs and, on average, matches Virchow2, the second-best FM published to date. This suggests that there still remains a significant potential for further improving the models and algorithms used to train pathology FMs to take full advantage of the vast data collections.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- A whole-slide foundation model for digital pathology from real-world dataNature, 2024
- Towards a general-purpose foundation model for computational pathologyNature Medicine, 2024
- Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challengeNature Medicine, 2022
- Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology imagesMedical Image Analysis, 2019
- Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathologyMedical Image Analysis, 2019
- BACH: Grand challenge on breast cancer histology imagesMedical Image Analysis, 2019
- Rotation Equivariant CNNs for Digital Pathology2018
- Automated Gleason grading of prostate cancer tissue microarrays via deep learningScientific Reports, 2018
- Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast CancerJAMA, 2017
- The CPTAC Data Portal: A Resource for Cancer Proteomics ResearchJournal of Proteome Research, 2015