Comprehensive automatic assessment of retinal vascular abnormalities for computer-assisted retinopathy grading

Abstract

One of the most important signs of systemic disease that presents on the retina is vascular abnormalities such as in hypertensive retinopathy. Manual analysis of fundus images by human readers is qualitative and lacks in accuracy, consistency and repeatability. Present semi-automatic methods for vascular evaluation are reported to increase accuracy and reduce reader variability, but require extensive reader interaction; thus limiting the software-aided efficiency. Automation thus holds a twofold promise. First, decrease variability while increasing accuracy, and second, increasing the efficiency. In this paper we propose fully automated software as a second reader system for comprehensive assessment of retinal vasculature; which aids the readers in the quantitative characterization of vessel abnormalities in fundus images. This system provides the reader with objective measures of vascular morphology such as tortuosity, branching angles, as well as highlights of areas with abnormalities such as artery-venous nicking, copper and silver wiring, and retinal emboli; in order for the reader to make a final screening decision. To test the efficacy of our system, we evaluated the change in performance of a newly certified retinal reader when grading a set of 40 color fundus images with and without the assistance of the software. The results demonstrated an improvement in reader's performance with the software assistance, in terms of accuracy of detection of vessel abnormalities, determination of retinopathy, and reading time. This system enables the reader in making computer-assisted vasculature assessment with high accuracy and consistency, at a reduced reading time.

Retinal vascular geometry and 6 year incidence and progression of diabetic retinopathy

“…Sixth, the retinal vascular variables were measured by a semi-automated computer-assisted program, which may introduce variability between graders and limit application in clinical settings. Newer fully automated software is currently being developed [51,52]. We are also developing 'deep learning' techniques using artificial intelligence, but this requires extremely large sample sizes, as recently demonstrated for automated diabetic retinopathy detection [53,54].…”

Potential Utility of Retinal Imaging for Alzheimer’s Disease: A Review

“…Current software programs for quantitative measurement of retinal vasculature in routine retinal image are not fully automated and therefore additional efforts are needed by technicians and clinicians. Novel software programs are being developed to fully automatically measure ocular fundus features such as calibers, tortuosity and network complexity, facilitating a more efficient assessment ( Cheung and Wong, 2012 ; Nguyen et al, 2013 ; Joshi et al, 2014 ; Cavallari et al, 2015 ; Abramoff et al, 2016 ; Walton et al, 2016 ). In addition, with the advent of the non-mydriatic ultra-wide field retinal imaging technology, up to 200°, rather than the common 45° or 60°, of the retina can be captured in a single shot for investigating peripheral lesions ( Kernt et al, 2012 ), which may provide a more comprehensive picture of the overall retinal vascular structure and retina ( Cheung et al, 2010 ).…”

Clinical utilization of automated image analysis software for improving retinal reader's performance

“…The automated methods were developed to detect vascular abnormalities such as artery-venous ratio (AVR) [16], vessel tortuosity [17], AV nicking, copper-silver wiring, and emboli [18], as described in the respective publications. The algorithms were tested on retinal images extracted from multiple datasets listed in section II.B.…”