Related Experiment Video
Updated: Jul 9, 2026
Multimodal Study of Murine Cardiovascular Remodeling: Four-Dimensional Ultrasound and Mass Spectrometry Imaging
Published on: January 10, 2025
Non-invasive Multimodal Cardiovascular Disease Detection Method Based on Comprehensive View Analysis
Yining Xie1, Kaiwen Zhang2, Jun Long2
1College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin, China. yiningxie@nefu.edu.cn.
Insights
This study introduces a novel multimodal approach for cardiovascular disease (CVD) detection using retinal images and clinical data. The method enhances diagnostic accuracy by integrating multi-modal information for comprehensive CVD progression prediction.
Area of Science:
- Ophthalmology
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Cardiovascular disease (CVD) diagnosis is increasingly linked to retinal fundus images and clinical indicators.
- Current diagnostic methods often rely on single-modal data, limiting comprehensive CVD progression prediction.
- There is a need for non-invasive methods that integrate multi-modal information for improved CVD detection.
Purpose of the Study:
- To develop and validate a non-invasive multimodal method for cardiovascular disease (CVD) detection.
- To enhance CVD diagnosis by integrating retinal fundus images and clinical indicators.
- To improve the prediction of CVD progression through comprehensive multi-modal analysis.
Main Methods:
- A two-branch architecture was designed to extract features from retinal fundus images and clinical indicators separately.
- A comprehensive view analysis incorporating vascular segmentation maps was used for retinal image feature extraction.
- A multi-order belief interaction feature fusion method, utilizing basic belief assignment and Dempster-Shafer theory, was employed for two-stage fusion of multi-modal features.
Main Results:
- The developed multimodal model achieved an Area Under the Curve (AUC) of 0.873 (95% CI, 0.855-0.892).
- The model obtained a Precision-Recall (PR) score of 0.896 (95% CI, 0.882-0.91).
- Performance metrics were superior to single-modality methods and traditional fusion techniques, demonstrating the efficacy of the proposed approach.
Conclusions:
- The proposed non-invasive multimodal CVD detection method effectively integrates retinal fundus images and clinical indicators.
- The comprehensive view analysis and multi-order belief interaction fusion enhance the complementarity of multimodal information.
- This approach offers a promising tool for more accurate and comprehensive cardiovascular disease diagnosis and progression prediction.
Abstract:
In recent years, researchers have found that the diagnosis of cardiovascular disease (CVD) is closely related to retinal fundus images and specific clinical indicators. However, current diagnostic methods are still limited to analyzing single-modal data, lacking analysis of multi-modal diagnostic information, and unable to comprehensively predict the progression of CVD. To this end, we design a non-invasive multimodal CVD detection method based on comprehensive view analysis. This method uses retinal fundus images and non-invasive clinical indicators as analysis data. The method is divided into two branches; one branch is used to extract retinal fundus features, and the other branch is used to extract clinical indicator features. In the retinal fundus feature extraction branch, we propose a method for comprehensive view analysis, which assists in learning retinal fundus images by incorporating vascular segmentation maps. Additionally, we introduce a multi-order belief interaction feature fusion method, through the basic belief assignment and Dempster-Shafer theory, the extracted features of the two modalities are fused in two stages, thereby achieving complementarity between multimodal information. The model in this paper was developed and verified using 1870 UK Biobank data. The results show that our method achieves an area under the curve (AUC) of 0.873 (95% CI, 0.855-0.892) and a PR score of 0.896 (95% CI, 0.882-0.91), which were higher than those of the method using single modality data and traditional fusion methods.
Related Concept Videos
01:21Imaging Studies for Cardiovascular System IV: CMRI
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...
01:28Imaging Studies for Cardiovascular System V: CT
01:17Imaging Studies for Cardiovascular System I:Echocardiography
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion, evaluates...
01:23Assessment of the Cardiovascular System I: Subjective Data
Initial Enquiry
Ask the patient about their primary concern and thoroughly explore all reported symptoms.
Medical History
Investigate past illnesses affecting the cardiovascular system, such as angina, anemia, rheumatic fever, congenital heart disease, stroke, thrombophlebitis, dysrhythmias, varicosities
Inquire about symptoms...