High-resolution fundus images for ophthalmomics and early cardiovascular disease prediction

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: April 3, 2025

Cardiovascular diseases (CVDs) remain the foremost cause of mortality globally, emphasizing imperative for early detection to improve patient outcomes and mitigate healthcare burdens. Carotid intima-media thickness (CIMT) serves as a well-established predictive marker atherosclerosis cardiovascular risk assessment. Fundus imaging offers non-invasive modality investigate microvascular pathology systemic vascular health. However, paucity high-quality, publicly available datasets linking fundus images with CIMT measurements has hindered progression AI-driven models CVDs. Addressing this gap, we introduce China-Fundus-CIMT dataset, comprising bilateral high-resolution images, measurements, clinical data-including age gender-from 2,903 patients. Our experiments multimodal reveal that integrating information substantially enhances performance, yielding AUC-ROC increases 3.22% 7.83% on validation test sets, respectively, compared unimodal models. This dataset constitutes vital resource developing validating AI-based screening CVDs using is now accessible research community.

Language: Английский

Changes in retinal capillary density in female with type 2 diabetes and gestational diabetes—an analysis based on OCTA technology

International Journal of Ophthalmology, Journal Year: 2025, Volume and Issue: 18(3), P. 435 - 448

Published: Feb. 20, 2025

To evaluate alterations in conjunctival vascular density (CVD) and macular capillary (MCD) female patients with type 2 diabetes mellitus (T2DM) gestational (GDM) using optical coherence tomography angiography (OCTA). A total of 60 participants were recruited, comprising 20 T2DM, GDM, healthy age-matched controls (HCs). OCTA was used to assess superficial deep retinal plexuses. Subsequently, changes MCD analyzed a circular segmentation method (C1-C6), hemispheric quadrant [superior right (SR), superior left (SL), inferior (IL), (IR)], the early treatment diabetic retinopathy study (ETDRS) (S, I, R, L). unequivocally demonstrated that variations CVD among HCs, GDM groups statistically significant (P<0.001). In plexus (sRCP), differences observed densities microvascular (TMI), microvasculature (MIR), macrovascular (MAR) between T2DM HCs (P<0.05). Furthermore, group exhibited more substantial reduction MIR compared (P<0.01). (dRCP), TMI identified (P<0.05), notable difference also receiver operating characteristic (ROC) curve analysis, area under ROC (AUC) for sRCP 0.975, 95% confidence interval (CI) 0.941-1. The AUC highest dRCP, an value 0.914 95%CI ranging from 0.847 0.981. comparing groups, I region maximized sRCP, achieving 0.978 0.953-1. Additionally, R reaching 0.99 0.975 1. dRCP show higher diagnostic sensitivity GDM. holds potential as instrument diagnosis differentiation

Language: Английский