Clinical Validation and Prospective Deployment of an Automated Deep Learning-Based Coronary Segmentation and Cardiac Toxicity Risk Prediction System
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915626612686848 |
|---|---|
| author | Guthier, Christian V. Kehayias, Christopher E Ciausu, Cosmin Gasho, Jordan O. He, John Oorloff, Maria Zhang, Samuel C. Bitterman, Danielle S. Bredfeldt, Jeremy S. Fitzgerald, Kelly Kann, Benjamin H. Kozono, David E. Steers, Jennifer Tonneau, Marion Nohria, Anju Aerts, Hugo J. W. L. Atkins, Katelyn M. Mak, Raymond H. |
| author_facet | Guthier, Christian V. Kehayias, Christopher E Ciausu, Cosmin Gasho, Jordan O. He, John Oorloff, Maria Zhang, Samuel C. Bitterman, Danielle S. Bredfeldt, Jeremy S. Fitzgerald, Kelly Kann, Benjamin H. Kozono, David E. Steers, Jennifer Tonneau, Marion Nohria, Anju Aerts, Hugo J. W. L. Atkins, Katelyn M. Mak, Raymond H. |
| contents | Importance: Coronary algorithm for cardiac sub structures and prospective real-time surveillance of cardiac dose exposure. Methods: Retro and prospective study to validate AI auto-segmentation. A 3D UNet was trained on 560 thoracic CT scans from a single institution (2003-2014) and validated internally (n=70). External validation was performed in 283 patients treated at an independent institution (2005-2020). Clinical implementation comprised (1) retrospective analysis of 3,399 lung cancer patients treated in 2014-2022 and (2) prospective surveillance of 1,386 consecutive patients in 2023. Geometric accuracy, concordance of dose-volume parameters; association of AI-derived substructure metrics with outcome; temporal dose trends; and the proportion of patients exceeding prespecified risk. Results: Median (inter-quartile range) Dice/ASSD were 0.95 (0.94-0.96)/1.1 mm for the heart and 0.87 (0.82-0.90)/1.9 mm for the LAD; the median absolute difference between AI and manual LAD V15 was 1%. AI-derived LAD V15 remained independently associated with MACE (sub distribution hazard ratio [HR], 1.03%; 95% CI, 1.01-1.05) and ACM (adjusted HR, 1.02; 95% CI, 1.00-1.03), internally and externally. Retrospective deployment showed a 32% relative decline in median LAD V15 from 2014 to 2022 (12% to 8%) and identified high- risk doses in 1,086 of 3,399 patients (32%). Prospective surveillance flagged 264 contemporary patients (19%) for potential cardiology referral. Conclusions: A validated AI system accurately segments cardiac substructures, reproduces dose-outcome relationships, enables large-scale surveillance, and point-of-care alerts for high-risk patients. Automated cardiac dose monitoring could facilitate adoption of coronary-sparing therapy and follow-up. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14971 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Clinical Validation and Prospective Deployment of an Automated Deep Learning-Based Coronary Segmentation and Cardiac Toxicity Risk Prediction System Guthier, Christian V. Kehayias, Christopher E Ciausu, Cosmin Gasho, Jordan O. He, John Oorloff, Maria Zhang, Samuel C. Bitterman, Danielle S. Bredfeldt, Jeremy S. Fitzgerald, Kelly Kann, Benjamin H. Kozono, David E. Steers, Jennifer Tonneau, Marion Nohria, Anju Aerts, Hugo J. W. L. Atkins, Katelyn M. Mak, Raymond H. Medical Physics Importance: Coronary algorithm for cardiac sub structures and prospective real-time surveillance of cardiac dose exposure. Methods: Retro and prospective study to validate AI auto-segmentation. A 3D UNet was trained on 560 thoracic CT scans from a single institution (2003-2014) and validated internally (n=70). External validation was performed in 283 patients treated at an independent institution (2005-2020). Clinical implementation comprised (1) retrospective analysis of 3,399 lung cancer patients treated in 2014-2022 and (2) prospective surveillance of 1,386 consecutive patients in 2023. Geometric accuracy, concordance of dose-volume parameters; association of AI-derived substructure metrics with outcome; temporal dose trends; and the proportion of patients exceeding prespecified risk. Results: Median (inter-quartile range) Dice/ASSD were 0.95 (0.94-0.96)/1.1 mm for the heart and 0.87 (0.82-0.90)/1.9 mm for the LAD; the median absolute difference between AI and manual LAD V15 was 1%. AI-derived LAD V15 remained independently associated with MACE (sub distribution hazard ratio [HR], 1.03%; 95% CI, 1.01-1.05) and ACM (adjusted HR, 1.02; 95% CI, 1.00-1.03), internally and externally. Retrospective deployment showed a 32% relative decline in median LAD V15 from 2014 to 2022 (12% to 8%) and identified high- risk doses in 1,086 of 3,399 patients (32%). Prospective surveillance flagged 264 contemporary patients (19%) for potential cardiology referral. Conclusions: A validated AI system accurately segments cardiac substructures, reproduces dose-outcome relationships, enables large-scale surveillance, and point-of-care alerts for high-risk patients. Automated cardiac dose monitoring could facilitate adoption of coronary-sparing therapy and follow-up. |
| title | Clinical Validation and Prospective Deployment of an Automated Deep Learning-Based Coronary Segmentation and Cardiac Toxicity Risk Prediction System |
| topic | Medical Physics |
| url | https://arxiv.org/abs/2511.14971 |