Predicting CT-Based Coronary Artery Disease Using Vascular Biomarkers Derived from Fundus Photographs with a Graph
Fan Huang1, Jie Lian1, Kei-Shing Ng1
1Department of Diagnostic Radiology, LKS Faculty of Medicine, The University of Hong Kong, Hong Kong, China.
Insights
Retinal vascular changes are linked to coronary artery disease severity. A graph neural network model using these changes accurately predicts coronary artery disease risk.
Area of Science:
- Cardiovascular Imaging
- Ophthalmology
- Artificial Intelligence in Medicine
Background:
- Coronary artery disease (CAD) assessment often relies on invasive or complex imaging.
- Non-invasive biomarkers for early CAD detection are highly sought after.
- Retinal vasculature shares anatomical and pathological similarities with coronary vasculature.
Purpose of the Study:
- To investigate the association between retinal vascular biomarkers and coronary artery disease (CAD) severity.
- To develop and evaluate a graph neural network (GNN) model for predicting CAD risk using retinal imaging.
- To compare the GNN model's performance against traditional machine learning (ML) models.
Main Methods:
- Prospective recruitment of 145 patients for coronary CT angiography (CCTA) and fundoscopy.
- Stratification of CCTA scans by Coronary Artery Disease Reporting and Data System (CAD-RADS) scores.
- Extraction of quantitative vascular biomarkers from fundus images and association analysis with CAD-RADS.
- Development of a GNN model for CAD-RADS prediction and comparison with ML models.
Main Results:
- Significant associations found between specific retinal vascular biomarkers (arterial width, angles, fractal dimensions) and adverse CAD-RADS scores.
- The GNN model achieved high performance metrics: 0.711 sensitivity, 0.697 specificity, 0.704 accuracy, and 0.739 AUC.
- The GNN model significantly outperformed traditional ML models in predicting CAD-RADS.
Conclusions:
- Retinal vasculature serves as a potential non-invasive biomarker for coronary artery atherosclerosis.
- Graph neural network models show promise for accurate CAD risk prediction using retinal imaging.
- This approach offers a novel, accessible method for cardiovascular risk assessment.
Abstract:
The study population contains 145 patients who were prospectively recruited for coronary CT angiography (CCTA) and fundoscopy. This study first examined the association between retinal vascular changes and the Coronary Artery Disease Reporting and Data System (CAD-RADS) as assessed on CCTA. Then, we developed a graph neural network (GNN) model for predicting the CAD-RADS as a proxy for coronary artery disease. The CCTA scans were stratified by CAD-RADS scores by expert readers, and the vascular biomarkers were extracted from their fundus images. Association analyses of CAD-RADS scores were performed with patient characteristics, retinal diseases, and quantitative vascular biomarkers. Finally, a GNN model was constructed for the task of predicting the CAD-RADS score compared to traditional machine learning (ML) models. The experimental results showed that a few retinal vascular biomarkers were significantly associated with adverse CAD-RADS scores, which were mainly pertaining to arterial width, arterial angle, venous angle, and fractal dimensions. Additionally, the GNN model achieved a sensitivity, specificity, accuracy and area under the curve of 0.711, 0.697, 0.704 and 0.739, respectively. This performance outperformed the same evaluation metrics obtained from the traditional ML models (p < 0.05). The data suggested that retinal vasculature could be a potential biomarker for atherosclerosis in the coronary artery and that the GNN model could be utilized for accurate prediction.
More Related Videos
06:57Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
13:07Optical Coherence Tomography Based Biomechanical Fluid-Structure Interaction Analysis of Coronary Atherosclerosis Progression
Published on: January 15, 2022
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:19Imaging Studies VII: Vascular Imaging
01:30Coronary Artery Disease I: Introduction