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

arXiv: https://arxiv.org/abs/2310.18494 · HTML: https://mlsanity.com/paper/2310.18494/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 27 Oct 2023.

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [Adversarial Attacks Beyond the Image Space](https://mlsanity.com/paper/1711.07183/) (2017)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [OPTIMAM Mammography Image Database: a large scale resource of mammography images and clinical data](https://mlsanity.com/paper/2004.04742/) (2020)
- [3DB: A Framework for Debugging Computer Vision Models](https://mlsanity.com/paper/2106.03805/) (2021)
- [Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks](https://mlsanity.com/paper/2106.14324/) (2021)
- [The stochastic digital human is now enrolling for in silico imaging trials -- Methods and tools for generating digital cohorts](https://mlsanity.com/paper/2301.08719/) (2023)
- [Improving Computed Tomography (CT) Reconstruction via 3D Shape Induction](https://mlsanity.com/paper/2208.10937/) (2022)

## Built on by (most cited first, 8 of 8)

- [Synthetically Enhanced: Unveiling Synthetic Data's Potential in Medical Imaging Research](https://mlsanity.com/paper/2311.09402/) (2023)
- [Synthetic Data in Radiological Imaging: Current State and Future Outlook](https://mlsanity.com/paper/2407.01561/) (2024)
- [Evaluating Explainability: A Framework for Systematic Assessment and Reporting of Explainable AI Features](https://mlsanity.com/paper/2506.13917/) (2025)
- [Skin Color Measurement from Dermatoscopic Images: An Evaluation on a Synthetic Dataset](https://mlsanity.com/paper/2504.04494/) (2025)
- [T-SYNTH: A Knowledge-Based Dataset of Synthetic Breast Images](https://mlsanity.com/paper/2507.04038/) (2025)
- [MAMBO: High-Resolution Generative Approach for Mammography Images](https://mlsanity.com/paper/2506.08677/) (2025)
- [Knowledge-based anomaly detection for identifying network-induced shape artifacts](https://mlsanity.com/paper/2511.04729/) (2025)
- [BAC-JEPA: Label-Efficient Breast Arterial Calcification Segmentation via Synthetic Mammography-Guided Supervision](https://mlsanity.com/paper/2606.22089/) (2026)

## Abstract (arXiv)

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.