Summary of Detection Of Subclinical Atherosclerosis by Image-based Deep Learning on Chest X-ray, By Guglielmo Gallone et al.
Detection of subclinical atherosclerosis by image-based deep learning on chest x-ray
by Guglielmo Gallone, Francesco Iodice, Alberto Presta, Davide Tore, Ovidio de Filippo, Michele Visciano, Carlo Alberto Barbano, Alessandro Serafini, Paola Gorrini, Alessandro Bruno, Walter Grosso Marra, James Hughes, Mario Iannaccone, Paolo Fonio, Attilio Fiandrotti, Alessandro Depaoli, Marco Grangetto, Gaetano Maria de Ferrari, Fabrizio D’Ascenzo
First submitted to arxiv on: 27 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a deep-learning based system for recognizing subclinical atherosclerosis on plain frontal chest x-rays. The authors developed a deep-learning algorithm, dubbed the AI-CAC model, which predicts coronary artery calcium (CAC) score from chest x-ray images. The model was trained and validated on large cohorts of patients with available paired chest x-ray and computed tomography (CT) scans. The primary outcome measures include the diagnostic accuracy of the AI-CAC model, assessed by the area under the curve (AUC). The results show that the model has high sensitivity in identifying a CAC score greater than zero, with an AUC of 0.90 in the internal validation cohort and 0.77 in the external validation cohort. The study also finds that patients with AI-CAC scores above zero have significantly higher rates of adverse cardiovascular events compared to those with AI-CAC scores of zero. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about a new way to use computers to look at chest x-rays and see if people might get heart problems in the future. The researchers made a special computer program that can look at x-ray pictures and figure out how likely someone is to have hidden heart blockages. They tested this program on lots of x-ray pictures and it seemed to be really good at finding these blockages. It also looked like the program could help doctors predict who might get serious heart problems in the future. |
Keywords
* Artificial intelligence * Auc * Deep learning
