Saved in:
Bibliographic Details
Main Authors: Li, Jiawen, Hu, Jiali, Sun, Qiehe, Yan, Renao, Ouyang, Minxi, Guan, Tian, Han, Anjia, He, Chao, He, Yonghong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.20823
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929735440793600
author Li, Jiawen
Hu, Jiali
Sun, Qiehe
Yan, Renao
Ouyang, Minxi
Guan, Tian
Han, Anjia
He, Chao
He, Yonghong
author_facet Li, Jiawen
Hu, Jiali
Sun, Qiehe
Yan, Renao
Ouyang, Minxi
Guan, Tian
Han, Anjia
He, Chao
He, Yonghong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20823
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?
Li, Jiawen
Hu, Jiali
Sun, Qiehe
Yan, Renao
Ouyang, Minxi
Guan, Tian
Han, Anjia
He, Chao
He, Yonghong
Computer Vision and Pattern Recognition
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.
title Can We Simplify Slide-level Fine-tuning of Pathology Foundation Models?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.20823