Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.11093 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918274022768640 |
|---|---|
| author | Saeed, Dylan Gharleghi, Ramtin Beier, Susann Singh, Sonit |
| author_facet | Saeed, Dylan Gharleghi, Ramtin Beier, Susann Singh, Sonit |
| contents | Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with 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 and assess model capacity, super-resolution fidelity enhancement, preprocessing, and training strategies. Lightweight CNNs trained from scratch outperform large pretrained networks; pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11093 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays Saeed, Dylan Gharleghi, Ramtin Beier, Susann Singh, Sonit Computer Vision and Pattern Recognition Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with 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 and assess model capacity, super-resolution fidelity enhancement, preprocessing, and training strategies. Lightweight CNNs trained from scratch outperform large pretrained networks; pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean 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. |
| title | Machine-Learning Based Detection of Coronary Artery Calcification Using Synthetic Chest X-Rays |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.11093 |