AutoMIL automates cancer image analysis with high accuracy

AutoMIL: Automated Multiple Instance Learning for Whole-Slide Image Classification

Computer Vision and Pattern RecognitionArtificial Intelligence

Summary

Classifying whole-slide medical images is very complex and often needs experts in both medicine and machine learning. The authors developed AutoMIL, a tool that automates this process, handling steps like image preparation and training without manual setup. AutoMIL performed nearly as well as specialized expert systems across several datasets, showing it can be a reliable baseline for analyzing pathology images. The tool also can adjust to different data characteristics, which improves results on unbalanced datasets.

What this means in practice

  • For medical imaging teams: Implement an automated pipeline to classify pathology whole-slide images without manual tuning, saving time and expert effort.
  • For biomedical software developers: Integrate AutoMIL into digital pathology platforms to provide ready-to-use slide classification with adaptable performance for different cancer datasets.$Commercial implications: Enables commercial pathology software providers to offer automated cancer image classification tools without extensive manual pipeline design.

Authors

Jonas Waibel, Frank Kramer, Dominik Müller

Abstract

Developing multiple instance learning pipelines for the classification of whole-slide images involves many interdependent design decisions and expertise in both pathology and machine learning. We present AutoMIL, an open-source framework that applies principles from the field of automated machine learning to tackle this task by automating integral pipeline steps, such as preprocessing, training and evaluation. In a benchmark evaluation with default settings, AutoMIL reached ROC-AUC scores of 0.94 on UBC-OCEAN, 0.99 on PCam and 0.93-0.96 on a TCGA-NSCLC subset, comparable to specialised pipelines in related work. Ensembling mainly improved performance on imbalanced data, showing that an automated pipeline must adapt to dataset characteristics. AutoMIL thus provides an accessible baseline for whole-slide image classification without manual pipeline configuration.