Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays

Dylan Saeed, Ramtin Gharleghi, Susann Beier, Sonit Singh
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:215-231, 2026.

Abstract

Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with computed tomography (CT)-based Agatston scoring widely regarded as the clinical gold standard. However, CT is costly and impractical for large-scale screening, while chest X-rays (CXRs) are inexpensive but lack reliable ground truth labels, constraining deep learning development. Digitally reconstructed radiographs (DRRs) offer a scalable alternative by projecting CT volumes into CXR-like images while inheriting precise labels. In this work, we provide the first systematic evaluation of DRRs as a surrogate training domain for CAC detection. Using 667 CT scans from the COCA dataset, we generate synthetic DRRs (posterior–anterior and lateral views per scan) and assess model capacity, super-resolution (SR) fidelity enhancement, preprocessing, and training strategies. Lightweight convolutional neural networks (CNNs) trained from scratch outperform large pretrained networks (DenseNet121, ResNet18); pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean area under the receiver operating characteristic curve (AUC) of 0.754, comparable to or exceeding prior CXR-based studies. These results establish DRRs as a scalable, label-rich foundation for CAC detection, while laying the foundation for future transfer learning and domain adaptation to real CXRs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-saeed26a, title = {Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays}, author = {Saeed, Dylan and Gharleghi, Ramtin and Beier, Susann and Singh, Sonit}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {215--231}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/saeed26a/saeed26a.pdf}, url = {https://proceedings.mlr.press/v315/saeed26a.html}, abstract = {Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with computed tomography (CT)-based Agatston scoring widely regarded as the clinical gold standard. However, CT is costly and impractical for large-scale screening, while chest X-rays (CXRs) are inexpensive but lack reliable ground truth labels, constraining deep learning development. Digitally reconstructed radiographs (DRRs) offer a scalable alternative by projecting CT volumes into CXR-like images while inheriting precise labels. In this work, we provide the first systematic evaluation of DRRs as a surrogate training domain for CAC detection. Using 667 CT scans from the COCA dataset, we generate synthetic DRRs (posterior–anterior and lateral views per scan) and assess model capacity, super-resolution (SR) fidelity enhancement, preprocessing, and training strategies. Lightweight convolutional neural networks (CNNs) trained from scratch outperform large pretrained networks (DenseNet121, ResNet18); pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean area under the receiver operating characteristic curve (AUC) of 0.754, comparable to or exceeding prior CXR-based studies. These results establish DRRs as a scalable, label-rich foundation for CAC detection, while laying the foundation for future transfer learning and domain adaptation to real CXRs.} }
Endnote
%0 Conference Paper %T Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays %A Dylan Saeed %A Ramtin Gharleghi %A Susann Beier %A Sonit Singh %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-saeed26a %I PMLR %P 215--231 %U https://proceedings.mlr.press/v315/saeed26a.html %V 315 %X Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with computed tomography (CT)-based Agatston scoring widely regarded as the clinical gold standard. However, CT is costly and impractical for large-scale screening, while chest X-rays (CXRs) are inexpensive but lack reliable ground truth labels, constraining deep learning development. Digitally reconstructed radiographs (DRRs) offer a scalable alternative by projecting CT volumes into CXR-like images while inheriting precise labels. In this work, we provide the first systematic evaluation of DRRs as a surrogate training domain for CAC detection. Using 667 CT scans from the COCA dataset, we generate synthetic DRRs (posterior–anterior and lateral views per scan) and assess model capacity, super-resolution (SR) fidelity enhancement, preprocessing, and training strategies. Lightweight convolutional neural networks (CNNs) trained from scratch outperform large pretrained networks (DenseNet121, ResNet18); pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean area under the receiver operating characteristic curve (AUC) of 0.754, comparable to or exceeding prior CXR-based studies. These results establish DRRs as a scalable, label-rich foundation for CAC detection, while laying the foundation for future transfer learning and domain adaptation to real CXRs.
APA
Saeed, D., Gharleghi, R., Beier, S. & Singh, S.. (2026). Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:215-231 Available from https://proceedings.mlr.press/v315/saeed26a.html.

Related Material