Optical coherence tomography angiography (OCTA) can deliver enhanced diagnosis for diabetic retinopathy (DR). This study evaluated a deep learning (DL) algorithm for automatic DR severity assessment using high-resolution and ultra-widefield (UWF) OCTA. Diabetic patients were examined with mm high-resolution OCTA and mm UWF-OCTA using PLEX®Elite 9000. A novel DL algorithm was trained for automatic DR severity inference using both OCTA acquisitions. The algorithm employed a unique hybrid fusion framework, integrating structural and flow information from both acquisitions. It was trained on data from 875 eyes of 444 patients. Tested on 53 patients (97 eyes), the algorithm achieved a good area under the receiver operating characteristic curve (AUC) for detecting DR (0.8868), moderate non-proliferative DR (0.8276), severe non-proliferative DR (0.8376), and proliferative/treated DR (0.9070). These results significantly outperformed detection with the mm (AUC = 0.8462, 0.7793, 0.7889, and 0.8104, respectively) or mm (AUC = 0.8251, 0.7745, 0.7967, and 0.8786, respectively) acquisitions alone. Thus, combining high-resolution and UWF-OCTA acquisitions holds the potential for improved early and late-stage DR detection, offering a foundation for enhancing DR management and a clear path for future works involving expanded datasets and integrating additional imaging modalities.
Objectives: This study aimed to describe the clinical, optical coherence tomography (OCT) and OCT angiography (OCTA) findings and characteristics in patients with perifoveal exudative vascular anomalous complex (PEVAC) and compare the macular vascular density with the age-matched control group. Methods: We conducted a case–control study to compare demographic information, clinical observations, and OCT/OCTA findings in eyes with PEVAC (n = 5 eyes in 5 patients) and a control group of subjects matched for age (n = 9). The Advanced Retina Imaging (ARI) network algorithms were utilized to evaluate OCTA observations. Statistical analysis was performed by the nonparametric Mann–Whitney U test. Results: Patients with PEVAC had a mean (±SD) age at presentation of 70 ± 12.6 years, the mean follow-up period was 7.8 ± 5.2 months, and unilateral disease was observed. Four out of the five patients in our cohort had a history of systemically treated hypertension and dyslipidemia. Three eyes had lesions in the inner temporal retinal zone, while the remaining two eyes had lesions in the inner inferior or central zone. Retina slab analysis using OCTA showed no significant difference in vascular density parameters between the PEVAC and control groups. Conclusions: Although limited by a small sample size, our study suggests that macular vessel density shows no significant difference between PEVAC cases and control eyes.