Multi-site validation of an interpretable model to analyze breast masses

TL;DR

This study validates a breast cancer prediction model that is both accurate and interpretable across different patient groups.

Contribution

The first external validation of an inherently interpretable deep learning model for breast lesion classification.

Findings

IAIA-BL showed reduced margin classification performance on external datasets compared to internal data.

Interpretability was preserved across all populations despite performance differences.

Model performance losses correlated with smaller malignancy classification performance drops.

Abstract

An external validation of IAIA-BL—a deep-learning based, inherently interpretable breast lesion malignancy prediction model—was performed on two patient populations: 207 women ages 31 to 96, (425 mammograms) from iCAD, and 58 women (104 mammograms) from Emory University. This is the first external validation of an inherently interpretable, deep learning-based lesion classification model. IAIA-BL and black-box baseline models had lower mass margin classification performance on the external datasets than the internal dataset as measured by AUC. These losses correlated with a smaller reduction in malignancy classification performance, though AUC 95% confidence intervals overlapped for all sites. However, interpretability, as measured by model activation on relevant portions of the lesion, was maintained across all populations. Together, these results show that model interpretability can generalize even when performance does not.

Figures