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

Ensembling mainly improved performance on imbalanced data, showing that an automated pipeline must adapt to dataset characteristics. It comes from a paper posted to arXiv on 26 October 2026. 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. AutoMIL thus provides an accessible baseline for whole-slide image classification without manual pipeline configuration.

Why it counts

Ensembling mainly improved performance on imbalanced data, showing that an automated pipeline must adapt to dataset characteristics.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.