Skip to main content

ORIGINAL RESEARCH article

Front. Cell Dev. Biol.
Sec. Molecular and Cellular Pathology
Volume 12 - 2024 | doi: 10.3389/fcell.2024.1467374
This article is part of the Research Topic Artificial Intelligence Applications in Chronic Ocular Diseases, Volume II View all articles

Application of the Full-Width-at-Half-Maximum Image Segmentation Method to Analyse Retinal Vascular Changes in Patients with Internal Carotid Artery Stenosis

Provisionally accepted
Ligang Jiang Ligang Jiang 1Mengting Liu Mengting Liu 2Meiting Yu Meiting Yu 1*Wei Lu Wei Lu 1*Zhe Zhang Zhe Zhang 3,4,5*Yuhua Tong Yuhua Tong 1*
  • 1 Quzhou City People's Hospital, Quzhou, China
  • 2 Central South University, Changsha, Hunan Province, China
  • 3 Jinan University, Guangzhou, Guangdong Province, China
  • 4 Shenzhen Eye Hospital, Shenzhen, China
  • 5 Shenzhen Eye Institute, Shenzhen, China

The final, formatted version of the article will be published soon.

    Background: To investigate the correlation between retinal vascular changes and ICA stenosis by measuring retinal vessels using full-width-at-half-maximum（FWHM） and intelligent image recognition. Methods:This research selected patients who were admitted to the Vascular Surgery Department of Quzhou People's Hospital from January 2018 to December 2020 and were preparing for Carotid Artery Stenting (CAS). Participants were divided into two groups: without ICA stenosis (Group 0) and with ICA stenosis (Group 1). A total of 109 cases were included in the study, with 50 cases in Group 1 and 59 cases in Group 0.Vascular images of superior temporal zone B of the retina were obtained by spectral domain optical coherence tomography (SD-OCT). The edges of retinal vessels were identified by FWHM.Each vessel of all subjects was measured three times with the FWHM, and the average value was taken to obtain the retinal arteriolar lumen diameter (RALD), retinal arteriolar outer diameter (RAOD), retinal venular lumen diameter (RVLD), and retinal venular outer diameter (RVOD),Arterial Wall Thickness（AWT),Venular Wall Thickness（VWT)＝(RVOD-RVLD)/2,Arteriovenous Ratio（AVR）=RAOD/RVOD. Results:We found that compared to Group 0, Group 1 had smaller RALD(P <0.001) and RAOD(P <0.001), and wider RVOD(P <0.001), with thicker VWT(P <0.001). When compared with the contralateral eye in Group 1, the ipsilateral eye exhibited even smaller RALD ,RAOD and AVR(P <0.001,P <0.001,P <0.001).After CAS, the RALD ,RAOD and AVR in Group 1 increased（P <0.001,P <0.001,P <0.001),while the RVLD and RVOD decreased(P <0.05,P<0.001). Our research reveals a significant correlation between retinal vascular changes and internal ICA stenosis. Conclusion:Utilizing SD-OCT in conjunction with the FWHM,we achieved a non-invasive, intelligent, stable, and precise acquisition of data pertaining to retinal vessels.These findings underscore a significant correlation between alterations in retinal vascular structure and the presence of ICA stenosis, as demonstrated by our research.

    Keywords: Spectral domain optical coherence tomography (SD-OCT)1, Full Width at Half Maximum2, Intelligent image analysis3, Internal Carotid Artery Stenosis4, Retinal arteriolar diameter5, Retinal venular diameter6

    Received: 19 Jul 2024; Accepted: 09 Aug 2024.

    Copyright: © 2024 Jiang, Liu, Yu, Lu, Zhang and Tong. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Meiting Yu, Quzhou City People's Hospital, Quzhou, China
    Wei Lu, Quzhou City People's Hospital, Quzhou, China
    Zhe Zhang, Jinan University, Guangzhou, 510632, Guangdong Province, China
    Yuhua Tong, Quzhou City People's Hospital, Quzhou, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.