Deep learning model to quantify left atrium volume on routine non-contrast chest CT and predict adverse outcomes
Journal of Cardiovascular Computed Tomography(2022)
Abstract
Table of Contents Summary: We aimed to validate a deep learning model to automatically quantify left atrial (LA) volumes from routine non-contrast chest CT and evaluate prediction for cardiovascular outcomes. We 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. There was excellent correlation between AI and expert results. AI-derived LA volumes were associated with increased risk of major adverse cardiac events, heart failure hospitalization, and new-onset atrial fibrillation within five years.
MoreTranslated text
Key words
Low-dose computed tomography,Artificial intelligence,Deep learning,Left atrium volume,Heart failure,Atrial fibrillation,Major adverse cardiac and cerebrovascular events,Lung cancer screening
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined