Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading
2026-03-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors studied how disagreements between expert and non-expert pathologists can indicate how hard it is to diagnose prostate cancer slides. They called this concept Whole Slide Difficulty (WSD) and used it to improve machine learning methods that classify these slides. By including WSD in their models, they achieved better accuracy, especially for more severe cancer grades. This approach helps machines learn from the uncertainty in slide diagnoses.
Multiple Instance LearningWhole Slide ImagesGleason gradinghistopathologyclassification lossfeature encodersprostate cancerpathologist disagreementmulti-task learning
Authors
Marie Arrivat, Rémy Peyret, Elsa Angelini, Pietro Gori
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).