Density-based classification in diabetic retinopathy through thickness of retinal layers from optical coherence tomography

Abstract

Diabetic retinopathy (DR) is a severe retinal disorder that can lead to vision loss, however, its underlying mechanism has not been fully understood. Previous studies have taken advantage of Optical Coherence Tomography (OCT) and shown that the thickness of individual retinal layers are affected in patients with DR. However, most studies analyzed the thickness by calculating summary statistics from retinal thickness maps of the macula region. This study aims to apply a density function-based statistical framework to the thickness data obtained through OCT, and to compare the predictive power of various retinal layers to assess the severity of DR. We used a prototype data set of 107 subjects which are comprised of 38 non-proliferative DR (NPDR), 28 without DR (NoDR), and 41 controls. Based on the thickness profiles, we constructed novel features which capture the variation in the distribution of the pixel-wise retinal layer thicknesses from OCT. We quantified the predictive power of each of the retinal layers to distinguish between all three pairwise comparisons of the severity in DR (NoDR vs NPDR, controls vs NPDR, and controls vs NoDR). When applied to this preliminary DR data set, our density-based method demonstrated better predictive results compared with simple summary statistics. Furthermore, our results indicate considerable differences in retinal layer structuring based on the severity of DR. We found that: (a) the outer plexiform layer is the most discriminative layer for classifying NoDR vs NPDR; (b) the outer plexiform, inner nuclear and ganglion cell layers are the strongest biomarkers for discriminating controls from NPDR; and (c) the inner nuclear layer distinguishes best between controls and NoDR.

Association of Thiol–disulfide Homeostasis with Retinal Layer Thickness in Patients with Diabetes Mellitus

“…However, the GCL thickness was lesser in patients without DR compared with that in the controls. Mohammed et al reported that the GCL demonstrated the difference in its thickness in patients with DR versus that in controls [34]. In the present study, we found that the IPL thickness was similar in patients with and without DR but lower than that in the control group; however, the difference was not statistically signi cant.…”

“…Mohammed et al, in their study, suggested that the change in the INL thickness is the best indicator that distinguishes patients with DR from controls; it has an even higher discriminative power than the early loss of RNFL thickness [34]. Changes in the INL were found to be more pronounced in animal studies [35].…”

“…The hypersensitivity of Müller glial cells in the INL to hyperglycemia causes an increase in the number of cell nuclei and hypertrophy, leading to the apoptotic process [29,36,37]. Mohammed S et al, in their study, argued that the difference between patients with and without DR was best observed in terms of the OPL thickness [34]. In another study, a decrease in the RNFL and OPL thicknesses and an increase in the ONL thickness were observed in the patients without DR compared with those in controls [38].…”

A Novel Computer-Aided Diagnostic System for Early Detection of Diabetic Retinopathy Using 3D-OCT Higher-Order Spatial Appearance Model

“…The system had an AUC of . There are other works that use OCT to diagnose DR in [ 8 , 9 , 10 , 11 ].…”

Quantifying T2-FLAIR Mismatch Using Geographically Weighted Regression and Predicting Molecular Status in Lower-Grade Gliomas

“…This framework of permutation tests and classification models has also been successfully used for the analysis of imaging data in the context of diabetic retinopathy. 17,18…”