Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses

TL;DR

This paper introduces M-SYNTH, a synthetic dataset generated via in silico models to evaluate mammography AI, revealing how model performance varies with breast density, lesion conspicuity, and dose levels.

Contribution

It presents a novel in silico evaluation framework and dataset for assessing mammography AI across diverse breast characteristics and imaging conditions.

Findings

AI performance decreases with higher breast density.

Performance improves with increased lesion conspicuity.

Lower exposure levels reduce AI accuracy.

Abstract

To generate evidence regarding the safety and efficacy of artificial intelligence (AI) enabled medical devices, AI models need to be evaluated on a diverse population of patient cases, some of which may not be readily available. We propose an evaluation approach for testing medical imaging AI models that relies on in silico imaging pipelines in which stochastic digital models of human anatomy (in object space) with and without pathology are imaged using a digital replica imaging acquisition system to generate realistic synthetic image datasets. Here, we release M-SYNTH, a dataset of cohorts with four breast fibroglandular density distributions imaged at different exposure levels using Monte Carlo x-ray simulations with the publicly available Virtual Imaging Clinical Trial for Regulatory Evaluation (VICTRE) toolkit. We utilize the synthetic dataset to analyze AI model performance and find that model performance decreases with increasing breast density and increases with higher mass density, as expected. As exposure levels decrease, AI model performance drops with the highest performance achieved at exposure levels lower than the nominal recommended dose for the breast type.