Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading

TL;DR

This paper introduces Whole Slide Difficulty (WSD) based on expert-non-expert disagreement to enhance prostate cancer grading in histopathology, demonstrating improved classification performance by leveraging WSD in training.

Contribution

It proposes two novel methods to incorporate WSD into MIL models, improving prostate cancer grading accuracy, especially for higher Gleason scores.

Findings

WSD integration improves classification accuracy.

Higher Gleason grades benefit most from WSD methods.

Methods are effective across different feature encoders.

Abstract

Multiple Instance Learning (MIL) has been widely applied in histopathology to classify Whole Slide Images (WSIs) with slide-level diagnoses. While the ground truth is established by expert pathologists, the slides can be difficult to diagnose for non-experts and lead to disagreements between the annotators. In this paper, we introduce the notion of Whole Slide Difficulty (WSD), based on the disagreement between an expert and a non-expert pathologist. We propose two different methods to leverage WSD, a multi-task approach and a weighted classification loss approach, and we apply them to Gleason grading of prostate cancer slides. Results show that integrating WSD during training consistently improves the classification performance across different feature encoders and MIL methods, particularly for higher Gleason grades (i.e. worse diagnosis).