Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading
This work addresses grading accuracy in histopathology for medical diagnosis, but it is incremental as it builds on existing Multiple Instance Learning methods.
The paper tackled the problem of improving prostate cancer grading from whole slide images by introducing Whole Slide Difficulty (WSD) based on expert-non-expert disagreement, and results showed that integrating WSD during training consistently enhanced classification performance, especially for higher Gleason grades.
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).