Abstract
Glaucoma is a silent disease that leads to vision loss or irreversible blindness. Current deep learning methods can help glaucoma screening by extending it to larger populations using retinal images. Low-cost lenses attached to mobile devices can increase the frequency of screening and alert patients earlier for a more thorough evaluation. This work explored and compared the performance of classification and segmentation methods for glaucoma screening with retinal images acquired by both retinography and mobile devices. The goal was to verify the results of these methods and see if similar results could be achieved using images captured by mobile devices. The used classification methods were the Xception, ResNet152 V2 and the Inception ResNet V2 models. The models’ activation maps were produced and analysed to support glaucoma classifier predictions. In clinical practice, glaucoma assessment is commonly based on the cup-to-disc ratio (CDR) criterion, a frequent indicator used by specialists. For this reason, additionally, the U-Net architecture was used with the Inception ResNet V2 and Inception V3 models as the backbone to segment and estimate CDR. For both tasks, the performance of the models reached close to that of state-of-the-art methods, and the classification method applied to a low-quality private dataset illustrates the advantage of using cheaper lenses.
Highlights
Glaucoma is one of the main causes of vision loss, mainly due to increased fluid pressure and improper drainage of fluid in the eye
Glaucoma screening was performed by training the models with each database separately and with merged data with the K-Fold CVDB
CDRsthreshold final decision for the classification based allcases, apply the the same significantly differvalues, compared to Ref but than despite this, there is complete agreement theyCDRs, differ more the higher models used achieved state-of-the-art for the segmentation, in the final decision forThe thetwo classification based on cup-to-disc ratio (CDR) since all results apply the same threshold and the outcome was similar to the glaucoma classification based on the with the Ref masks, values, they differ more than the higher Dice cases
Summary
Glaucoma is one of the main causes of vision loss, mainly due to increased fluid pressure and improper drainage of fluid in the eye. In 2013, it was estimated that 64.3 million people aged 40–80 years were diagnosed with glaucoma worldwide This disease is expected to reach nearly 76 million by 2020 and 111.8 million by 2040. The examination of these fundus images is important because the ophthalmologist can record indicators and parameters related to cupping to detect glaucoma, such as disc diameter, the thickness of the neuroretinal rim (decreasing in the order inferior (I) > superior (S) > nasal (N) > temporal (T) (ISNT rule)), peripapillary atrophy, notching and cup-to-disc ratio (CDR), with this last indicator being the most used measurement by specialists [3,4,5]
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.
