nnMIL: A generalizable multiple instance learning framework for computational pathology

TL;DR

nnMIL is a versatile multiple-instance learning framework that effectively integrates patch-level foundation models for accurate, reliable, and generalizable slide-level predictions in computational pathology, supporting diverse clinical tasks.

Contribution

The paper introduces nnMIL, a scalable, task-aware MIL framework that enhances pathology model generalization, uncertainty estimation, and performance across multiple datasets and tasks.

Findings

Outperformed existing MIL methods across 35 clinical tasks.

Demonstrated strong cross-model and cross-cohort generalization.

Enabled reliable uncertainty quantification and survival stratification.

Abstract

Computational pathology holds substantial promise for improving diagnosis and guiding treatment decisions. Recent pathology foundation models enable the extraction of rich patch-level representations from large-scale whole-slide images (WSIs), but current approaches for aggregating these features into slide-level predictions remain constrained by design limitations that hinder generalizability and reliability. Here, we developed nnMIL, a simple yet broadly applicable multiple-instance learning framework that connects patch-level foundation models to robust slide-level clinical inference. nnMIL introduces random sampling at both the patch and feature levels, enabling large-batch optimization, task-aware sampling strategies, and efficient and scalable training across datasets and model architectures. A lightweight aggregator performs sliding-window inference to generate ensemble slide-level predictions and supports principled uncertainty estimation. Across 40,000 WSIs encompassing 35 clinical tasks and four pathology foundation models, nnMIL consistently outperformed existing MIL methods for disease diagnosis, histologic subtyping, molecular biomarker detection, and pan- cancer prognosis prediction. It further demonstrated strong cross-model generalization, reliable uncertainty quantification, and robust survival stratification in multiple external cohorts. In conclusion, nnMIL offers a practical and generalizable solution for translating pathology foundation models into clinically meaningful predictions, advancing the development and deployment of reliable AI systems in real-world settings.