MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification

TL;DR

This paper introduces MIL-PF, a scalable framework that leverages frozen foundation models and lightweight aggregation for efficient and accurate mammography classification, addressing challenges of high-resolution images and limited annotations.

Contribution

The paper presents a novel approach combining precomputed features with a small MIL head, enabling efficient adaptation of foundation models to mammography classification without retraining large backbones.

Findings

Achieves state-of-the-art performance on mammography classification tasks.

Reduces training complexity by only training a small aggregation module.

Explicitly models tissue context and lesion signals through attention mechanisms.

Abstract

Modern foundation models provide highly expressive visual representations, yet adapting them to high-resolution medical imaging remains challenging due to limited annotations and weak supervision. Mammography, in particular, is characterized by large images, variable multi-view studies and predominantly breast-level labels, making end-to-end fine-tuning computationally expensive and often impractical. We propose Multiple Instance Learning on Precomputed Features (MIL-PF), a scalable framework that combines frozen foundation encoders with a lightweight MIL head for mammography classification. By precomputing the semantic representations and training only a small task-specific aggregation module (40k parameters), the method enables efficient experimentation and adaptation without retraining large backbones. The architecture explicitly models the global tissue context and the sparse local lesion signals through attention-based aggregation. MIL-PF achieves state-of-the-art classification performance at clinical scale while substantially reducing training complexity. We release the code for full reproducibility.