Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification

TL;DR

This paper introduces a task-specific fine-tuning framework for pathology Whole Slide Image classification that leverages the Variational Information Bottleneck to improve accuracy and generalization, addressing computational and domain gap challenges.

Contribution

It proposes a novel WSI fine-tuning method based on the Information Bottleneck theory, enabling efficient, task-specific representation learning from weak labels.

Findings

Significant accuracy improvements over previous methods.

Enhanced generalization across multiple datasets.

Efficient fine-tuning reduces computational costs.

Abstract

While Multiple Instance Learning (MIL) has shown promising results in digital Pathology Whole Slide Image (WSI) classification, such a paradigm still faces performance and generalization problems due to challenges in high computational costs on Gigapixel WSIs and limited sample size for model training. To deal with the computation problem, most MIL methods utilize a frozen pretrained model from ImageNet to obtain representations first. This process may lose essential information owing to the large domain gap and hinder the generalization of model due to the lack of image-level training-time augmentations. Though Self-supervised Learning (SSL) proposes viable representation learning schemes, the improvement of the downstream task still needs to be further explored in the conversion from the task-agnostic features of SSL to the task-specifics under the partial label supervised learning. To alleviate the dilemma of computation cost and performance, we propose an efficient WSI fine-tuning framework motivated by the Information Bottleneck theory. The theory enables the framework to find the minimal sufficient statistics of WSI, thus supporting us to fine-tune the backbone into a task-specific representation only depending on WSI-level weak labels. The WSI-MIL problem is further analyzed to theoretically deduce our fine-tuning method. Our framework is evaluated on five pathology WSI datasets on various WSI heads. The experimental results of our fine-tuned representations show significant improvements in both accuracy and generalization compared with previous works. Source code will be available at https://github.com/invoker-LL/WSI-finetuning.