Deep learning-enabled ultra-widefield retinal vessel segment
A Study was conducted to demonstrate the feasibility of a deep learning-based vascular segmentation tool for UWFA and evaluate its ability to automatically identify quality-optimized phase-specific images.

Cumulative retinal vessel areas (RVA) were extracted from all available UWFA frames. Cubic splines were fitted for serial vascular assessment throughout the angiographic phases of eyes with diabetic retinopathy (DR), sickle cell retinopathy (SCR), or normal retinal vasculature. The image with maximum RVA was selected as the optimum early phase. A late phase frame was selected at a minimum of 4min that most closely mirrored the RVA from the selected early image.

--A total of 13,980 UWFA sequences from 462 sessions were used to evaluate the performance and 1578 UWFA sequences from 66 sessions were used to create cubic splines.

--Maximum RVA was detected for DR, SCR, and normals respectively.

--In 85.2% of the sessions, appropriate images for both phases were successfully identified. The individual success rate was 90.7% for early and 94.6% for late frames.

Finally, retinal vascular properties are extremely phased and field-of-view sensitive. Deep learning algorithms can extract vascular parameters that can be used for angiographic picture quality assessment and quality optimized phase selection. Clinical applications of a deep learning-based vascular segmentation and phase selection system should increase the speed, consistency, and objectivity of UWFA evaluation dramatically.