Background: Gestational diabetes mellitus (GDM) is a temporary metabolic disorder in which small retinal vessels may have experience subtle changes before clinical lesions of the fundus retina appear. An innovative artificial intelligence image processing technology was applied to locate and analyze the small retinal vessel morphology and accurately evaluate the changes of the small retinal vessels in GDM patients and pregnant women with normal blood glucose and non-pregnant women with normal blood glucose.Methods: The subjects were divided into three groups:GDM group, pregnant control group (PC), and normal control group (NC). Use optical coherence tomography angiography (OCTA) to collect OCT images of subjects,and perform quantitative identification and analysis of retinal vessel parameters based on artificial intelligence measurement software integrated the prior knowledge supervised edge-aware multi-task network (PKSEA-Net): Retinal arteriolar lumen diameter (RALD), retinal arteriolar outer diameter (RAOD), retinal venular lumen diameter (RVLD),retinal venular outer diameter (RVOD),arterial wall thickness (AWT),venular wall thickness (VWT),arterial wall to lumen ratio (AWLR),venular wall to lumen ratio (VWLR),arterial wall cross-sectional area (AWCSA),venular wall cross-sectional area (VWCSA), arteriovenous ratio (AVR).Results: This study revealed significant differences in RVOD, RVLD, VWT, VWCSA and AVR between the GDM group and the PC group (p = 0.005, p < 0.027, p = 0.008, p = 0.001, p = 0.022), significant differences in RVOD, RVLD, VWT, VWCSA and AVR between the GDM group and the NC group (p < 0.001, p = 0.001, p < 0.001, p < 0.001, p = 0.001). In GDM group, RVOD, RVLD, VWT and VWCSA increased, while AVR decreased. There were no significant differences in RVOD, RVLD, VWT, VWCSA and AVR between PC group and NC group (p = 0.139, p = 0.263, p = 0.107, p = 0.059, p = 0.218), and no significant differences in VWLR among the three groups (p > 0.05). No significant difference was observed in retinal artery vascular parameters (RAOD, RALD, AWT, AWLR, AWCSA) across the three groups (p > 0.05).Conclusion: There were increases in RVOD, RVLD, VWT, and VWCSA, decrease in AVR in patients with GDM. However, no significant difference of retinal vascular parameters was shown between normal pregnant women and normal non-pregnant women. PKSEA-Net can assist to identify changes in retinal vascular morphology and diagnose micro-vascular lesion early in normal pregnant women and high-risk groups of GDM.

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.

Hypertension during pregnancy, which is essentially a microvascular disease that destroys the end‐organ microcirculation, should not be underestimated, as it could lead to organ failure in the kidneys, lungs, and brain. Preassessment of the microcirculatory state through systematic observation of the fundus has been proven to be noninvasive and feasible. Although hypertension in preeclampsia patients will resolve after childbirth, the sticking point is determining the best termination moment. Early diagnosis and treatment can prevent long‐term ocular complications and cardiovascular risks for pregnant women in the future. In order to adjust the treatment strategy through more sensitive and precise fundus changes, we comprehensively summarized the common structural changes in the fundus in preeclampsia patients, including changes in the blood vessels, choroid, and retina, as well as the application of quantitative observation for chorioretinal alterations in recent years.