Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?

TL;DR

This paper demonstrates that a simple nonlinear mapping approach, SiMLP, can effectively adapt foundation models for slide-level pathology tasks, outperforming complex MIL-based methods and offering robustness and transferability.

Contribution

Introducing SiMLP, a straightforward nonlinear mapping strategy that simplifies slide-level fine-tuning of pathology foundation models, challenging the need for complex MIL-based approaches.

Findings

SiMLP outperforms MIL-based methods by 3.52% on pan-cancer classification.

SiMLP performs well in few-shot learning scenarios.

SiMLP shows robustness and transferability in lung cancer subtyping.

Abstract

The emergence of foundation models in computational pathology has transformed histopathological image analysis, with whole slide imaging (WSI) diagnosis being a core application. Traditionally, weakly supervised fine-tuning via multiple instance learning (MIL) has been the primary method for adapting foundation models to WSIs. However, in this work we present a key experimental finding: a simple nonlinear mapping strategy combining mean pooling and a multilayer perceptron, called SiMLP, can effectively adapt patch-level foundation models to slide-level tasks without complex MIL-based learning. Through extensive experiments across diverse downstream tasks, we demonstrate the superior performance of SiMLP with state-of-the-art methods. For instance, on a large-scale pan-cancer classification task, SiMLP surpasses popular MIL-based methods by 3.52%. Furthermore, SiMLP shows strong learning ability in few-shot classification and remaining highly competitive with slide-level foundation models pretrained on tens of thousands of slides. Finally, SiMLP exhibits remarkable robustness and transferability in lung cancer subtyping. Overall, our findings challenge the conventional MIL-based fine-tuning paradigm, demonstrating that a task-agnostic representation strategy alone can effectively adapt foundation models to WSI analysis. These insights offer a unique and meaningful perspective for future research in digital pathology, paving the way for more efficient and broadly applicable methodologies.