DBMAE-Net: A dual branch multi-scale feature adaptive extraction network for retinal arteriovenous vessel segmentation

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 104, P. 107619 - 107619

Published: Jan. 29, 2025

Language: Английский

---

Comparative analysis of retinal vascular structural parameters in populations with different glucose metabolism status based on color fundus photography and artificial intelligence

Frontiers in Cell and Developmental Biology, Journal Year: 2025, Volume and Issue: 13

Published: Feb. 3, 2025

Objective Measure and analyze retinal vascular parameters in individuals with varying glucose metabolism, explore preclinical microstructure changes related to diabetic retinopathy (DR), assess metabolism’s impact on structure. Methods The study employed a cross-sectional design encompassing 4-year period from 2020 2024. Fundus photographs 320 (2020–2024) were categorized into non-diabetes, pre-diabetes, type 2 diabetes mellitus (T2DM) without DR, T2DM mild-to-moderate non-proliferative DR (NPDR) groups. An artificial intelligence (AI)-based automatic measurement system was used quantify blood vessels the fundus color photographic images, enabling inter-group parameter comparison analysis of significant differences. Results Between January June 2024, collected four groups: non-diabetes (n = 54), pre-diabetes 71), overt 144), NPDR 51). In pairwise comparisons among NPDR. Fasting (FBG), glycated hemoglobin (HbA1c), systolic pressure (SBP), diastolic (DBP) significantly different ( P < 0.05). Within population, FBG, HbA1c, age, SBP, DBP predictors for Average venous branching number (branch_avg_v) patients NPDR, length arteries (length_avg_a) average veins (length_avg_v) increased, whereas branch_avg_v, angle (angle_avg_v), asymmetry (asymmetry_avg_v),overall density (vessel_length_density), vessel area (vessel_density) decreased Logistic regression identified length_avg_a, angle_avg_v, asymmetry_avg_v, vessel_length_density, vessel_density as independent T2DM. Receiver Operating Characteristic (ROC) curve demonstrated that length_avg_v, had diagnostic value Conclusion diagnosed T2DM, specific parameters, such branch_avg_v vessel_density, demonstrate correlation These hold promise biomarkers detecting abnormalities associated DR.

Language: Английский

---

Deep learning assisted retinal microvasculature assessment and cerebral small vessel disease in Fabry disease

Orphanet Journal of Rare Diseases, Journal Year: 2025, Volume and Issue: 20(1)

Published: April 3, 2025

Abstract Purpose The aim of this study was to assess retinal microvascular parameters (RMPs) in Fabry disease (FD) using deep learning, and analyze the correlation with brain lesions related cerebral small vessel (CSVD). Methods In retrospective case control study, fundus images from 27 FD patients age- sex-matched healthy subjects were collected. RMPs, encompassing diameter, density, symmetry, bifurcation, tortuosity, quantified. Laboratory examination results, Mainz severity score index (MSSI) scores, a magnetic resonance imaging scan for CSVD scores extracted their relationships RMPs analyzed. Results Utilizing artificial intelligence-assisted analysis, compared controls, exhibited reduced diameter ( p = 0.001 central artery equivalent, 0.049 vein equivalent), density < area length density), fractal dimension 0.001), heightened arteriolar venular asymmetry ratios 0.002 0.037, respectively), curvature tortuosity 0.037), simple 0.037) networks. Gender-based differences observed among patients. Furthermore, significantly associated markers such as plasma globotriaosylsphingosine α-galactosidase A activity, well MSSI scores. Notably, there significant negative between ratio CSVD-related (age-related white matter changes: r − 0.683, 0.001; Fazekas: 0.673, Lacuna: 0.453, 0.045; diseases: 0.721, 0.012; global cortical atrophy: 0.582, 0.009). Conclusions demonstrated increased vascular asymmetry, simpler microvasculature. These characteristics may serve preliminary indicators assessing could represent potential novel biomarkers CSVD, aiding monitoring progression.

Language: Английский

---

A semantic segmentation method to analyze retinal vascular parameters of diabetic nephropathy

Frontiers in Medicine, Journal Year: 2024, Volume and Issue: 11

Published: Oct. 24, 2024

By using spectral domain optical coherence tomography (SD-OCT) to measure retinal blood vessels. The correlation between the changes of vascular structure and degree diabetic nephropathy is analyzed with a full-pixel Semantic segmentation method.

Language: Английский

---