MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images
This work addresses cancer diagnosis in resource-constrained settings by enabling cost-effective analysis with conventional microscopes, though it is incremental as it adapts existing MIL methods to a new data type.
The paper tackles the challenge of applying graph-based multiple instance learning to conventional light microscope images, which have redundancy and lack spatial coordinates, by introducing MicroMIL, a framework that uses a representative image extractor to reduce redundancy and build graphs without coordinates, achieving state-of-the-art performance on colon cancer and BreakHis datasets with improved diagnostic accuracy and robustness.
Cancer diagnosis has greatly benefited from the integration of whole-slide images (WSIs) with multiple instance learning (MIL), enabling high-resolution analysis of tissue morphology. Graph-based MIL (GNN-MIL) approaches have emerged as powerful solutions for capturing contextual information in WSIs, thereby improving diagnostic accuracy. However, WSIs require significant computational and infrastructural resources, limiting accessibility in resource-constrained settings. Conventional light microscopes offer a cost-effective alternative, but applying GNN-MIL to such data is challenging due to extensive redundant images and missing spatial coordinates, which hinder contextual learning. To address these issues, we introduce MicroMIL, the first weakly-supervised MIL framework specifically designed for images acquired from conventional light microscopes. MicroMIL leverages a representative image extractor (RIE) that employs deep cluster embedding (DCE) and hard Gumbel-Softmax to dynamically reduce redundancy and select representative images. These images serve as graph nodes, with edges computed via cosine similarity, eliminating the need for spatial coordinates while preserving contextual information. Extensive experiments on a real-world colon cancer dataset and the BreakHis dataset demonstrate that MicroMIL achieves state-of-the-art performance, improving both diagnostic accuracy and robustness to redundancy. The code is available at https://github.com/kimjongwoo-cell/MicroMIL