Elevated Coronary Artery Calcium Quantified by a Validated Deep Learning Model From Lung Cancer Radiotherapy Planning Scans Predicts Mortality.
Katelyn M AtkinsJakob WeissRoman ZeleznikDanielle S BittermanTafadzwa L ChaunzwaElizabeth HuynhChristian GuthierDavid E KozonoJohn H LewisBalaji K TamarappooAnju NohriaUdo HoffmannHugo J W L AertsRaymond H MakPublished in: JCO clinical cancer informatics (2022)
In this proof-of-concept study, CAC was effectively measured from routinely acquired radiotherapy planning CT scans using an automated model. Elevated CAC, as predicted by the DL model, was associated with an increased risk of mortality, suggesting a potential benefit for automated cardiac risk screening before cancer therapy begins.
Keyphrases
- deep learning
- coronary artery
- computed tomography
- cancer therapy
- early stage
- cardiovascular events
- machine learning
- locally advanced
- radiation therapy
- contrast enhanced
- risk factors
- dual energy
- type diabetes
- squamous cell carcinoma
- coronary artery disease
- left ventricular
- artificial intelligence
- pulmonary hypertension
- image quality
- climate change
- atrial fibrillation
- pet ct
- single cell