Multi-head Attention-based Deep Multiple Instance Learning

TL;DR

MAD-MIL introduces a multi-head attention-based deep learning model for weakly supervised classification of Whole Slide Images in digital pathology, achieving competitive results with fewer parameters and enhanced interpretability.

Contribution

The paper presents MAD-MIL, a novel multi-head attention-based deep multiple instance learning model that simplifies complexity while outperforming existing methods like CLAM and DS-MIL.

Findings

Outperforms ABMIL on multiple datasets

Reduces model complexity and parameters

Enhances interpretability and information diversity

Abstract

This paper introduces MAD-MIL, a Multi-head Attention-based Deep Multiple Instance Learning model, designed for weakly supervised Whole Slide Images (WSIs) classification in digital pathology. Inspired by the multi-head attention mechanism of the Transformer, MAD-MIL simplifies model complexity while achieving competitive results against advanced models like CLAM and DS-MIL. Evaluated on the MNIST-BAGS and public datasets, including TUPAC16, TCGA BRCA, TCGA LUNG, and TCGA KIDNEY, MAD-MIL consistently outperforms ABMIL. This demonstrates enhanced information diversity, interpretability, and efficiency in slide representation. The model's effectiveness, coupled with fewer trainable parameters and lower computational complexity makes it a promising solution for automated pathology workflows. Our code is available at https://github.com/tueimage/MAD-MIL.