Toward explainable AI approaches for breast imaging: adapting foundation models to diverse populations

TL;DR

This study adapts a foundation model, BiomedCLIP, for breast imaging classification across diverse modalities, demonstrating high accuracy, strong generalization, and interpretability, thus advancing explainable AI in medical imaging.

Contribution

The paper introduces an adaptation of BiomedCLIP for BI-RADS breast density classification across multiple imaging modalities, highlighting improved generalization and interpretability in breast imaging AI.

Findings

Multi-modality training achieves similar accuracy to single-modality.

Models generalize well across external datasets with AUCs 0.80-0.93.

GradCAM visualizations show clinically relevant attention patterns.

Abstract

Foundation models hold promise for specialized medical imaging tasks, though their effectiveness in breast imaging remains underexplored. This study leverages BiomedCLIP as a foundation model to address challenges in model generalization. BiomedCLIP was adapted for automated BI-RADS breast density classification using multi-modality mammographic data (synthesized 2D images, digital mammography, and digital breast tomosynthesis). Using 96,995 images, we compared single-modality (s2D only) and multi-modality training approaches, addressing class imbalance through weighted contrastive learning. Both approaches achieved similar accuracy (multi-modality: 0.74, single-modality: 0.73), with the multi-modality model offering broader applicability across different imaging modalities and higher AUC values consistently above 0.84 across BI-RADS categories. External validation on the RSNA and EMBED datasets showed strong generalization capabilities (AUC range: 0.80-0.93). GradCAM visualizations confirmed consistent and clinically relevant attention patterns, highlighting the models interpretability and robustness. This research underscores the potential of foundation models for breast imaging applications, paving the way for future extensions for diagnostic tasks.