Trusted Multi-Scale Classification Framework for Whole Slide Image

TL;DR

This paper introduces a multi-scale WSI classification framework that mimics pathologists' analysis process, utilizing Vision Transformers, uncertainty estimation, and a novel patch selection method to improve accuracy and efficiency.

Contribution

The paper presents a novel multi-scale classification framework with uncertainty estimation and a patch selection schema, enhancing WSI classification performance and resource efficiency.

Findings

Significant improvement over state-of-the-art methods in WSI classification accuracy.

Effective uncertainty estimation for different magnifications.

Reduced computational requirements through attention-based patch selection.

Abstract

Despite remarkable efforts been made, the classification of gigapixels whole-slide image (WSI) is severely restrained from either the constrained computing resources for the whole slides, or limited utilizing of the knowledge from different scales. Moreover, most of the previous attempts lacked of the ability of uncertainty estimation. Generally, the pathologists often jointly analyze WSI from the different magnifications. If the pathologists are uncertain by using single magnification, then they will change the magnification repeatedly to discover various features of the tissues. Motivated by the diagnose process of the pathologists, in this paper, we propose a trusted multi-scale classification framework for the WSI. Leveraging the Vision Transformer as the backbone for multi branches, our framework can jointly classification modeling, estimating the uncertainty of each magnification of a microscope and integrate the evidence from different magnification. Moreover, to exploit discriminative patches from WSIs and reduce the requirement for computation resources, we propose a novel patch selection schema using attention rollout and non-maximum suppression. To empirically investigate the effectiveness of our approach, empirical experiments are conducted on our WSI classification tasks, using two benchmark databases. The obtained results suggest that the trusted framework can significantly improve the WSI classification performance compared with the state-of-the-art methods.