Automated AI-Based Aortic Measurements From Attenuation Correction CT as an Adjunctive Cardiovascular Risk Biomarker: An International Multicenter Study.
Authors
Affiliations (15)
Affiliations (15)
- Artificial Intelligence in Medicine Research Center, Departments of Biomedical Sciences, Medicine, and Cardiology, Cedars-Sinai Medical Center, Los Angeles, CA (A.M.M., A.S., W.Z., H.A.-J., R.Z., S.C., G.R., M.L., J.Y., W.H., V.B., J.X.L., D.S.B., D.D., R.J.H.M., P.J.S.).
- Center of Radiological Diagnostics, National Medical Institute of the Ministry of the Interior and Administration, Warsaw, Poland (A.M.M.).
- Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles (A.S.).
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN (P.C., S.W.).
- Department of Computational Biomedicine, Biostatistics Shared Resource, Cedars-Sinai Medical Center, Los Angeles, CA (V.F.C.).
- Division of Cardiology, Department of Medicine, and Department of Radiology, Columbia University Irving Medical Center and New York-Presbyterian Hospital (A.J.E.).
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, CT (E.M., A.F.).
- Division of Cardiology, University of Ottawa Heart Institute, Ontario, Canada (T.D.R.).
- Intermountain Medical Center Heart Institute, Intermountain Health, Murray, UT (V.T.L., S.M., S.K.).
- Department of Medicine, University of Utah, Salt Lake City (S.K.).
- Department of Nuclear Cardiology, National Institute of Cardiology Ignacio Chavez, Mexico (E.A., I.C.-J.).
- Division of Nuclear Medicine, Department of Radiology and Division of Cardiology, Montefiore Medical Center and the Albert Einstein College of Medicine, Bronx, NY (L.S., M.I.T.).
- Department of Cardiovascular Medicine, The University of Kansas Medical Center, Kansas City (T.L.R.).
- Division of Nuclear Medicine and Molecular Imaging, Department of Radiology, Brigham and Women's Hospital, Boston, MA (M.D.C.).
- Department of Cardiac Sciences, University of Calgary, Alberta, Canada (R.J.H.M.).
Abstract
Aortic enlargement is a powerful predictor of dissection and rupture, yet it is rarely evaluated during routine myocardial perfusion imaging, despite the widespread availability of computed tomography (CT) attenuation correction scans. The aim of this study was to determine whether fully automated, opportunistically derived, artificial intelligence-based aortic measurements from myocardial perfusion imaging CT attenuation correction scans are associated with adverse outcomes in a large multicenter cohort. Computed tomography attenuation correction scans from patients undergoing positron emission tomography/CT and single-photon emission CT/CT myocardial perfusion imaging across 10 centers were included. A deep learning model automatically segmented the thoracic aorta, and a postprocessing algorithm extracted maximum ascending and descending diameters. The aortic size index (1) was calculated by indexing the diameter to body surface area. A total of 29 339 patients (56% male; median age, 66 years [interquartile range, 58-75 years]) were included. Over a median follow-up of 3.5 years (interquartile range, 1.9-5.0 years), 5083 (17.3%) patients died. Median ascending and descending aortic size index values were 1.8 cm/m<sup>2</sup> (interquartile range, 1.6-2.0) and 1.5 cm/m<sup>2</sup> (interquartile range, 1.4-1.6), respectively, with an increase with age and higher values in females. Elevated aortic size index thresholds (ascending >2.2 cm/m<sup>2</sup>; descending >1.6 cm/m<sup>2</sup>) were significantly associated with increased all-cause mortality (ascending: adjusted hazard ratio, 1.16 [95% CI, 1.07-1.26], <i>P</i><0.001; descending: adjusted hazard ratio, 1.23 [95% CI, 1.14-1.31]; <i>P</i><0.001). Notably, the prognostic value of an abnormal aortic size index persisted independent of age, sex, and perfusion abnormalities. Artificial intelligence can unlock previously unused information within routine myocardial perfusion imaging CT attenuation correction scans by rapidly and automatically quantifying aortic size at scale. Opportunistic aortic measurements derived from CT attenuation correction may serve as an adjunctive risk biomarker and could add prognostic value to standard myocardial perfusion imaging without additional imaging or radiation.