Deep learning model to quantify left atrium volume on routine non-contrast chest CT and predict adverse outcomes
| Autor: | Megan Mercer, Sean Brady, Jeremy R. Burt, Mehmet Akif Gulsun, Selcuk Akkaya, Ali M. Agha, Basel Yacoub, Dhiraj Baruah, Nathan Leaphart, Madison Kocher, Michael E. Field, Gilberto J. Aquino, Jeffrey Waltz, U. Joseph Schoepf, Jordan Chamberlin, Ismail Kabakus, Puneet Sharma, Matthew Fiegel, Tilman Emrich, Vincent Giovagnoli, Stefan Zimmerman, Andrew Dippre, Pooyan Sahbaee, Athira Jacob |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Male
Lung Neoplasms Intraclass correlation Siemens Logistic regression Deep Learning Predictive Value of Tests Atrial Fibrillation Medicine Humans Radiology Nuclear Medicine and imaging Heart Atria Early Detection of Cancer Aged Retrospective Studies Body surface area Univariate analysis business.industry Atrial fibrillation medicine.disease Female Nuclear medicine business Tomography X-Ray Computed Cardiology and Cardiovascular Medicine Lung cancer screening Mace |
| Zdroj: | Journal of Cardiovascular Computed Tomography. 16:245-253 |
| ISSN: | 1934-5925 |
| DOI: | 10.1016/j.jcct.2021.12.005 |
| Popis: | Background: Non-contrast chest CTs (NCCT) are performed routinely for coronary artery calcium (CAC) scoring and lung cancer screening. However, a large amount of noncoronary and nonpulmonary data from these scans remain unassessed. We aimed to validate a deep learning model to automatically segment and measure left atrial (LA) volumes from routine NCCT and evaluate prediction for cardiovascular outcomes. Methods: We retrospectively evaluated 273 patients (median age 69 years, 55.5% male) who underwent a routine non-ECG gated NCCT for lung cancer screening. LA volumes were quantified by three expert cardiothoracic radiologists and a prototype AI algorithm. LA volumes were then indexed to the body surface area (BSA). Expert and AI LA volume index (LAVi) were compared and used to predict cardiovascular outcomes within five years. Logistic regression with appropriate univariate statistics were used for modelling outcomes. Findings: There was excellent correlation between AI and expert results with an LAV intraclass correlation of 0.950 (0.936-0.960). Bland-Altman plot demonstrated the AI underestimated LAVi by a mean 5.86 mL/m 2 . AI-LAVi was associated with new-onset atrial fibrillation (AUC 0.86; OR 1.12, 95% CI 1.08-1.18, p |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect