Abstract
Glaucoma is a leading cause of blindness worldwide whose detection is based on multiple factors, including measuring the cup to disc ratio, retinal nerve fiber layer and visual field defects. Advances in image processing and machine learning have allowed the development of automated approached for segmenting objects from fundus images. However, to build a robust system, a reliable ground truth dataset is required for proper training and validation of the model. In this study, we investigate the level of agreement in properly detecting the retinal disc in fundus images using an online portal built for such purposes. Two Doctors of Optometry independently traced the discs for 159 fundus images obtained from publicly available datasets using a purpose-built online portal. Additionally, we studied the effectiveness of ellipse fitting in handling misalignments in tracing. We measured tracing precision, interobserver variability, and average boundary distance between the results provided by ophthalmologists, and optometrist tracing. We also studied whether ellipse fitting has a positive or negative impact on properly detecting disc boundaries. The overall agreement between the optometrists in terms of locating the disc region in these images was 0.87. However, we found that there was a fair agreement on the disc border with kappa = 0.21. Disagreements were mainly in fundus images obtained from glaucomatous patients. The resulting dataset was deemed to be an acceptable ground truth dataset for training a validation of models for automatic detection of objects in fundus images.
Highlights
A study by Bourne et al indicates that, as of 2015, there were approximately 444 million people living with visual impairments worldwide; 39 million of these were blind, 216 million had moderate to severe visual impairment, and 189 million had mild visual impairment [1]
We investigated whether the level of agreement between the images taken from the Drishti and ARIA databases depended on the fundus status
We should emphasize that the Drishti dataset is mainly for glaucoma while the Aria dataset is for patients with diabetic retinopathy
Summary
A study by Bourne et al indicates that, as of 2015, there were approximately 444 million people living with visual impairments worldwide; 39 million of these were blind, 216 million had moderate to severe visual impairment, and 189 million had mild visual impairment [1]. A major contribution to these statistics comes from vision loss to glaucoma. It is the world’s second leading cause of irreversible vision loss after cataracts, accounting for 12% of cases of blindness annually [2]. It is estimated that the number of people between the ages of 40–80. Machine to develop the system and conduct the analysis. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
