Deep learning-enabled ultra-widefield retinal vessel segmentation with an automated quality-optimized angiographic phase selection tool

Abstract

Objectives: 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.

Methods: 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 4 min that most closely mirrored the RVA from the selected early image. Trained image analysts evaluated the selected pairs.

Results: 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 at a mean of 41 ± 15, 47 ± 27, 38 ± 8 s 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.

Conclusions: Retinal vascular characteristics are highly phased and field-of-view sensitive. Vascular parameters extracted by deep learning algorithms can be used for quality assessment of angiographic images and quality optimized phase selection. Clinical applications of a deep learning-based vascular segmentation and phase selection system might significantly improve the speed, consistency, and objectivity of UWFA evaluation.

Fig. 1. Evolution of retinal vasculature segmentation.

Retinal vessel segmentation by deep neural networks (A) and conventional algorithms (C) of an arteriovenous phase UWFA frame of an eye with diabetic retinopathy (B). Microvasculature detail is significantly greater in the mask created with deep learning, enhancing the demonstration of non-perfused areas. In the temporal periphery, more microvasculature is detected due to decreased background brightness caused by inadequate retinal perfusion.

Fig. 2. Change in detectable retinal vessel areas by angiographic phase.

Blue, gray, and green circles represent the data extracted from UWFA sequences of eyes with diabetic retinopathy (DR), sickle cell retinopathy (SCR), and normal retinal vasculature respectively. Blue, red, and green lines represent the spline curves fitted to the data from DR, SCR, and normal groups respectively. In the healthy dataset, the lack of data from 100 to 200 s, affected the shape of the peak in the spline curve fit.

Fig. 3. Successful automated image selection.

Automatically selected early (A) and late (B) phase angiographic frames and corresponding retinal vessel masks (C), (D) created with deep neural networks. Non-perfused areas are more pronounced in the early phase frame whereas leakage is more pronounced in the late phase frame. Increased background fluorescence in the late phase conceals some areas of non-perfusion.

Fig. 4. Representative discordant automated image selection examples.

Expert selection of optimal early and late images compared to automated image selection. The automated early phase selection (top right) was evaluated as discordant due to a slightly noncentral field-of-view compared to expert image selection. The automated late selection was evaluated as discordant due to reduced focus compared to expert selection.

Fig. 5. Outlier example based on angiographic phase graph.

The yellow circle represents the optimal early UWFA frame with the largest vessel segmentation. The abrupt decrease in vessel area marked by a red circle is due to a change in anomalous FOV that is obstructed by the eyelid.