Abstract
Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. Due to the SAP test’s innate difficulty and its high test-retest variability, we propose the RetiNerveNet, a deep convolutional recursive neural network for obtaining estimates of the SAP visual field. RetiNerveNet uses information from the more objective Spectral-Domain Optical Coherence Tomography (SDOCT). RetiNerveNet attempts to trace-back the arcuate convergence of the retinal nerve fibers, starting from the Retinal Nerve Fiber Layer (RNFL) thickness around the optic disc, to estimate individual age-corrected 24-2 SAP values. Recursive passes through the proposed network sequentially yield estimates of the visual locations progressively farther from the optic disc. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the “floor effect” for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. We further augment the proposed network to additionally predict the SAP Mean Deviation values and also facilitate the assignment of higher weightage to the underrepresented groups in the data. We then study the resulting performance trade-offs of the RetiNerveNet on the early, moderate and severe disease groups.
Highlights
Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people
Using the Spectral-Domain Optical Coherence Tomography (SDOCT) peripapillary scan, it is possible to measure the thickness of the Retinal Nerve Fiber Layer (RNFL) at evenly spaced points on a circle centered around the opening of the optic disc
We propose RetiNerveNet, a deep fully convolutional neural architecture for obtaining estimates of Standard Automated Perimetry (SAP) visual field values based on RNFL thickness values obtained from the more objective SDOCT tests
Summary
Glaucoma is the leading cause of irreversible blindness in the world, affecting over 70 million people. The cumbersome Standard Automated Perimetry (SAP) test is most frequently used to detect visual loss due to glaucoma. While all the methods used for our experiments exhibit lower performance for the advanced disease group (possibly due to the “floor effect” for the SDOCT test), the proposed network is observed to be more accurate than all the baselines for estimating the individual visual field values. Investigation and monitoring of patients with glaucoma involves evaluation of the visual field using Standard Automated Perimetry (SAP), and evaluation of the optic disc and Retinal Nerve Fiber Layer (RNFL) using Optical Coherence Tomography (OCT). The dimmest stimulus which is detected at least 50% of the time by the patient, in each visual field location, is recorded using a logarithmic scale, where higher values represent lower brightness, and better results. The SDOCT suffers from the well known “floor effect”, where extreme structural damage beyond a certain point is no longer detectable, possibly due to the presence of residual tissues and/or due to the failure of segmentation m ethods[8]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
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.
