Foundation Models for Slide-level Cancer Subtyping in Digital Pathology

TL;DR

This paper demonstrates that foundation models trained on large-scale histopathology data outperform traditional ImageNet-pretrained models in slide-level skin cancer subtyping using multiple instance learning.

Contribution

It compares various feature extractors from different pretraining strategies, highlighting the superior performance of foundation models in digital pathology.

Findings

Foundation models outperform ImageNet-pretrained models in skin cancer subtyping.

Foundation models improve accuracy in WSI prediction tasks.

Large-scale in-domain pretraining enhances digital pathology analysis.

Abstract

Since the emergence of the ImageNet dataset, the pretraining and fine-tuning approach has become widely adopted in computer vision due to the ability of ImageNet-pretrained models to learn a wide variety of visual features. However, a significant challenge arises when adapting these models to domain-specific fields, such as digital pathology, due to substantial gaps between domains. To address this limitation, foundation models (FM) have been trained on large-scale in-domain datasets to learn the intricate features of histopathology images. In cancer diagnosis, whole-slide image (WSI) prediction is essential for patient prognosis, and multiple instance learning (MIL) has been implemented to handle the giga-pixel size of WSI. As MIL frameworks rely on patch-level feature aggregation, this work aims to compare the performance of various feature extractors developed under different pretraining strategies for cancer subtyping on WSI under a MIL framework. Results demonstrate the ability of foundation models to surpass ImageNet-pretrained models for the prediction of six skin cancer subtypes