A multi-instance learning framework combining CNN and transformer for noninvasive coronary heart disease diagnosis using scleral images
Journal of Innovative Optical Health Sciences · 2026-05 · 19 (03)
DOI: 10.1142/s1793545826400079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Innovative Optical Health Sciences, online erschienen am 18.04.2026. Verfasst von Chuxiang Gao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: National Key Research and Development Program of China, R&D Program of Beijing Municipal Education Commission, Young Backbone Teacher Support Plan of Beijing Information Science & Technology University.
Abstract (Originalsprache)
Coronary heart disease (CHD) is a prevalent and life-threatening chronic cardiovascular condition, and early screening and diagnosis are essential for improving patient outcomes. Traditional diagnostic methods, such as electrocardiography, echocardiography, and coronary angiography, typically require specialized equipment, expert interpretation, and, in some cases, invasive procedures, thereby limiting their accessibility and scalability for population-wide screening. In this paper, we propose a novel, painless, noninvasive, and rapid auxiliary diagnostic approach for CHD based on scleral images. Specifically, we present the ScleraMIL model, a multi-instance learning framework that integrates the strengths of Convolutional Neural Networks (CNNs) and Vision Transformer (ViT) architectures to capture both local and global representations across multiple scleral images from each individual. To ensure the model focuses on scleral features, the Mamba-UNet segmentation model is first employed to precisely extract the scleral region from the raw ocular image. Then, each subject’s ten segmented scleral images (five per eye) are treated as instances forming a bag with a single patient-level label. These instances are processed through a CNN-based feature extractor, followed by a Transformer encoder that models inter-image dependencies for discriminative feature fusion, and finally passed to a classification head to predict the probability of CHD. Experimental results demonstrate that ScleraMIL achieves superior performance on key metrics such as accuracy, AUC, F1-score, and recall, significantly outperforming other deep learning and multiple instance learning methods. This work explores the feasibility of using scleral imaging as a potential biomarker for CHD classification and represents a promising step toward intelligent, accessible, and noninvasive cardiovascular risk assessment.
Förderung
- National Key Research and Development Program of China
- R&D Program of Beijing Municipal Education Commission
- Young Backbone Teacher Support Plan of Beijing Information Science & Technology University
- Fundamental Research Funds for the Beijing Municipal Universities
Zitieren
APA
Gao, C., Ma, Z., Bai, H., Shi, Y., Fan, F., Huang, G., Zhang, X., & Zhu, J. (2026). A multi-instance learning framework combining CNN and transformer for noninvasive coronary heart disease diagnosis using scleral images. Journal of Innovative Optical Health Sciences, 19(03). https://doi.org/10.1142/s1793545826400079
Vancouver
Gao C, Ma Z, Bai H, Shi Y, Fan F, Huang G, et al. A multi-instance learning framework combining CNN and transformer for noninvasive coronary heart disease diagnosis using scleral images. Journal of Innovative Optical Health Sciences. 2026;19(03). doi:10.1142/s1793545826400079
BibTeX
@article{Gao2026,
author = {Gao, Chuxiang and Ma, Zongqing and Bai, Hantao and Shi, Yixuan and Fan, Fan and Huang, Guoliang and Zhang, Xiaoqing and Zhu, Jiang},
title = {A multi-instance learning framework combining CNN and transformer for noninvasive coronary heart disease diagnosis using scleral images},
journal = {Journal of Innovative Optical Health Sciences},
year = {2026},
volume = {19},
number = {03},
doi = {10.1142/s1793545826400079}
}
EUVIMED