Clinical diagnosis of conjunctival microcirculation in hypertensive patients using shadowless imaging optical technology based on artificial intelligence

Objective To utilize artificial intelligence (AI) -based shadowless imaging optical technology to achieve high-definition collection, feature extraction, and comprehensive analysis of conjunctival microcirculation in hypertensive patients, and explore the characteristics of the scleral vasculatur...

Full description

Saved in:
Bibliographic Details
Main Authors: SONG Tianli, LI Haixia, LIU Li’an
Format: Article
Language:zho
Published: The Editorial Department of Chinese Journal of Clinical Research 2025-05-01
Series:Zhongguo linchuang yanjiu
Subjects:
Online Access:http://zglcyj.ijournals.cn/zglcyj/ch/reader/create_pdf.aspx?file_no=20250507
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Objective To utilize artificial intelligence (AI) -based shadowless imaging optical technology to achieve high-definition collection, feature extraction, and comprehensive analysis of conjunctival microcirculation in hypertensive patients, and explore the characteristics of the scleral vasculature in these patients. Methods Eye images of patients were collected, and eye image features were extracted. The MyEyeD-10 scleral shadowless imaging health intelligent analysis system, independently developed by Beijing CapitalBio Technology, was used for analysis. Results Significant morphological differences were observed in the scleral vasculature of hypertensive patients compared to normal individuals. Hypertensive patients’ scleral vasculature typically exhibited features such as “blood vessels” (bright red or dark red blood vessels appearing on the sclera) , “foggy diffusion” (a diffuse, mist - like staining extending from the coronal region across the sclera) , “dots” (shallow circular spots that do not protrude from the surface of the sclera) , and “patches” (colored irregular patches, either round or elliptical in shape). Conclusion By combining machine learning algorithms with shadowless imaging optical technology, it is possible to statistically analyze and classify parameters such as the color, location, shape, and pixel count of blood vessels in the images, thus enabling precise diagnosis of hypertensive patients.
ISSN:1674-8182