Abstract
PurposeTo characterize the corneal and epithelial thickness at different stages of keratoconus (KC), using a deep learning based corneal segmentation algorithm for anterior segment optical coherence tomography (AS-OCT).MethodsAn AS-OCT dataset was constructed in this study with 1,430 images from 715 eyes, which included 118 normal eyes, 134 mild KC, 239 moderate KC, 153 severe KC, and 71 scarring KC. A deep learning based corneal segmentation algorithm was applied to isolate the epithelial and corneal tissues from the background. Based on the segmentation results, the thickness of epithelial and corneal tissues was automatically measured in the center 6 mm area. One-way ANOVA and linear regression were performed in 20 equally divided zones to explore the trend of the thickness changes at different locations with the KC progression. The 95% confidence intervals (CI) of epithelial thickness and corneal thickness in a specific zone were calculated to reveal the difference of thickness distribution among different groups.ResultsOur data showed that the deep learning based corneal segmentation algorithm can achieve accurate tissue segmentation and the error range of measured thickness was less than 4 μm between our method and the results from clinical experts, which is approximately one image pixel. Statistical analyses revealed significant corneal thickness differences in all the divided zones (P < 0.05). The entire corneal thickness grew gradually thinner with the progression of the KC, and their trends were more pronounced around the pupil center with a slight shift toward the temporal and inferior side. Especially the epithelial thicknesses were thinner gradually from a normal eye to severe KC. Due to the formation of the corneal scarring, epithelial thickness had irregular fluctuations in the scarring KC.ConclusionOur study demonstrates that our deep learning method based on AS-OCT images could accurately delineate the corneal tissues and further successfully characterize the epithelial and corneal thickness changes at different stages of the KC progression.
Highlights
Keratoconus (KC) is a non-inflammatory, chronic, and progressive corneal disease which is characterized by apical thinning and cone-like protrusion of the central cornea, and usually leads to irregular astigmatism and myopia (Kennedy et al, 1986; Hashemi et al, 2020)
Compared with the normal eyes, KC eyes have thinner apical corneal epithelial thickness but thicker epithelial layer superonasally, which is similar to the total corneal thickness pattern (Li et al, 2012)
We aimed to investigate the corneal and epithelial thickness profiles along the vertical and horizontal meridians in the KC eyes at different stages
Summary
Keratoconus (KC) is a non-inflammatory, chronic, and progressive corneal disease which is characterized by apical thinning and cone-like protrusion of the central cornea, and usually leads to irregular astigmatism and myopia (Kennedy et al, 1986; Hashemi et al, 2020). Reports have shown an incidence of KC to be as high as 1.38/1,000 in the general population (Hashemi et al, 2020) Whereas diagnostic criteria such as CLEK guidelines (Zadnik et al, 1998) and Amsler– Krumeich classification (Krumeich et al, 1998) have been used to grade the severity of KC, the profiles of the corneal thickness along with KC progression are yet to be defined. Recent studies have investigated corneal deformation with the presence of stromal scarring in KC patients and demonstrated a correlation between the progression of KC and a reduction in corneal thickness and volume, as well as stromal scar formation (Morishige et al, 2019) These studies provided useful insights into the potential use of corneal thickness in understanding underlying mechanisms of KC. There is no study on the quantification of the characteristics of corneal and epithelial thickness at the different stages of KC development (Zadnik et al, 1998; Morishige et al, 2019)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 call
