Related Experiment Video
Updated: May 13, 2026
09:17
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Explainable retinal deep learning for cardiovascular risk stratification: a multiple modality analysis framework with
1School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, India.
BMC Medical Informatics and Decision Making
|May 12, 2026
Summary
This study introduces an explainable AI model for predicting cardiovascular risk using retinal images, improving accuracy and interpretability for early detection in diverse healthcare settings.
Area of Science:
- Ophthalmology and Cardiology
- Artificial Intelligence in Healthcare
- Medical Imaging Analysis
Background:
- Early cardiovascular risk prediction is crucial for preventive medicine, particularly in resource-limited areas.
- Retinal imaging offers insights into systemic vascular health, but current AI models lack explainability and generalizability.
- Existing methods struggle to integrate retinal biomarkers with multimodal cardiovascular data and adapt to varying conditions.
Purpose of the Study:
- To develop a comprehensive and explainable deep learning architecture for cardiovascular risk assessment using retinal images.
- To enhance the clinical adoption of AI in cardiology by improving model interpretability and robustness.
- To enable real-time, reliable cardiovascular risk prediction within next-generation healthcare infrastructures like SDN-enabled 5G.
Main Methods:
- Developed a novel deep learning framework integrating five analytical components: MARGE-Net, SCCIM, HVAAT, PaVSCM, and ReCVD-LDM.
- Incorporated clinical biomarkers, vascular topology, causal retinal features, vessel attributes, and anatomical plausibility.
- Utilized contrastive learning to differentiate imaging artifacts from anatomical predictors and designed an edge-cloud architecture for efficient deployment.
Main Results:
- Achieved an Area Under the Curve (AUC) of 0.94 on public datasets (MESSIDOR, AV-WIDE, STARE VAS).
- Demonstrated a 31% improvement in interpretability and a 26% reduction in prediction errors from imaging artifacts.
- Validated the model's accuracy, robustness, and compatibility for real-time deployment in 5G healthcare systems.
Conclusions:
- The proposed explainable AI framework significantly advances trustworthy cardiovascular risk prediction from retinal images.
- The model's interpretability and robustness make it suitable for real-time applications in advanced healthcare infrastructures.
- This research paves the way for improved non-invasive cardiovascular screening and preventive strategies.
Related Concept Videos
01:19Imaging Studies VII: Vascular Imaging
DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...
01:28Imaging Studies for Cardiovascular System V: CT
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
01:21Imaging Studies for Cardiovascular System IV: CMRI
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...