MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification
This work addresses computational inefficiencies in medical imaging for clinicians and researchers, though it is incremental as it builds on existing MIL and foundation model techniques.
The paper tackles the challenge of adapting foundation models to high-resolution mammography classification by proposing MIL-PF, a scalable framework that uses frozen encoders and a lightweight MIL head, achieving state-of-the-art performance with reduced training complexity.
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.