ProtoMIL: Multiple Instance Learning with Prototypical Parts for Whole-Slide Image Classification

TL;DR

ProtoMIL introduces a self-explainable multiple instance learning method that uses visual prototypes to achieve high accuracy and detailed interpretability in whole-slide image classification.

Contribution

It presents ProtoMIL, a novel MIL approach that combines model accuracy with fine-grained interpretability through prototypical features.

Findings

Achieves state-of-the-art accuracy on five MIL datasets.

Provides detailed explanations via visual prototypes.

Balances interpretability with predictive performance.

Abstract

Multiple Instance Learning (MIL) gains popularity in many real-life machine learning applications due to its weakly supervised nature. However, the corresponding effort on explaining MIL lags behind, and it is usually limited to presenting instances of a bag that are crucial for a particular prediction. In this paper, we fill this gap by introducing ProtoMIL, a novel self-explainable MIL method inspired by the case-based reasoning process that operates on visual prototypes. Thanks to incorporating prototypical features into objects description, ProtoMIL unprecedentedly joins the model accuracy and fine-grained interpretability, which we present with the experiments on five recognized MIL datasets.