Application of the Full-Width-at-Half-Maximum Image Segmentation Method to Analyse Retinal Vascular Changes in Patients with Diabetic Retinopathy.
Bo Lun XuYi Jie LiWen Li ZhouHai Jing ZhanJie Yi LuYu Hua TongPublished in: Journal of healthcare engineering (2022)
This study used spectral domain optical coherence tomography (SD-OCT) and full-width-at-half-maximum image segmentation to investigate the morphological changes of retinal blood vessels in patients with diabetic retinopathy (DR). Seventy-five patients with type 2 diabetes mellitus (T2DM) without DR and 65 patients with DR were studied. Vascular images of superior temporal region B of the retina were obtained by SD-OCT. The edges of retinal vessels were identified by the full-width-at-half-maximum image segmentation method. The lumen diameter, wall thickness (WT), wall cross-sectional area (WCSA), and wall-to-lumen ratio (WLR) were investigated. We found that, compared with the no diabetic retinopathy (NDR) group, patients in the DR group had an increased retinal arteriolar lumen diameter (RALD), retinal arteriolar outer diameter (RAOD), and WT (128.80 μ m versus 104.88 μ m; 147.01 μ m versus 135.60 μ m; 18.29 μ m versus 15.26 μ m, P < 0.05, respectively). The retinal venular lumen diameter (RVLD), retinal venular outer diameter (RVOD), and venular WT in the DR group were also increased (146.17 μ m versus 133.66 μ m; 180.20 μ m versus 156.43 μ m; 17.01 μ m versus 11.38 μ m, P < 0.05, respectively). The morphological changes in retinal vessels were significantly correlated with DR stage. In conclusion, in diabetic patients with DR, both retinal arteries and veins are widened and exhibit increased vascular thickness.
Keyphrases
- diabetic retinopathy
- optical coherence tomography
- optic nerve
- deep learning
- editorial comment
- end stage renal disease
- cross sectional
- chronic kidney disease
- convolutional neural network
- newly diagnosed
- type diabetes
- ultrasound guided
- prognostic factors
- peritoneal dialysis
- magnetic resonance
- metabolic syndrome
- magnetic resonance imaging
- insulin resistance
- high resolution
- skeletal muscle
- mass spectrometry
- patient reported
- atomic force microscopy