Neurodegenerative diseases present a current challenge for accurate diagnosis and for providing precise prognostic information. Developing imaging biomarkers for multiple sclerosis (MS), Parkinson disease (PD), and Alzheimer’s disease (AD) will improve the clinical management of these patients and may be useful for monitoring treatment effectiveness. Recent research using optical coherence tomography (OCT) has demonstrated that parameters provided by this technology may be used as potential biomarkers for MS, PD, and AD. Retinal thinning has been observed in these patients and new segmentation software for the analysis of the different retinal layers may provide accurate information on disease progression and prognosis. In this review we analyze the application of retinal evaluation using OCT technology to provide better understanding of the possible role of the retinal layers thickness as biomarker for the detection of these neurodegenerative pathologies. Current OCT analysis of the retinal nerve fiber layer and, specially, the ganglion cell layer thickness may be considered as a good biomarker for disease diagnosis, severity, and progression.

The purpose of this paper is to evaluate the feasibility of diagnosing multiple sclerosis (MS) using optical coherence tomography (OCT) data and a support vector machine (SVM) as an automatic classifier. Forty-eight MS patients without symptoms of optic neuritis and forty-eight healthy control subjects were selected. Swept-source optical coherence tomography (SS-OCT) was performed using a DRI (deep-range imaging) Triton OCT device (Topcon Corp., Tokyo, Japan). Mean values (right and left eye) for macular thickness (retinal and choroidal layers) and peripapillary area (retinal nerve fibre layer, retinal, ganglion cell layer—GCL, and choroidal layers) were compared between both groups. Based on the analysis of the area under the receiver operator characteristic curve (AUC), the 3 variables with the greatest discriminant capacity were selected to form the feature vector. A SVM was used as an automatic classifier, obtaining the confusion matrix using leave-one-out cross-validation. Classification performance was assessed with Matthew’s correlation coefficient (MCC) and the AUC_CLASSIFIER. The most discriminant variables were found to be the total GCL++ thickness (between inner limiting membrane to inner nuclear layer boundaries), evaluated in the peripapillary area and macular retina thickness in the nasal quadrant of the outer and inner rings. Using the SVM classifier, we obtained the following values: MCC = 0.81, sensitivity = 0.89, specificity = 0.92, accuracy = 0.91, and AUC_CLASSIFIER = 0.97. Our findings suggest that it is possible to classify control subjects and MS patients without previous optic neuritis by applying machine-learning techniques to study the structural neurodegeneration in the retina.

Purpose: To quantify changes in visual function parameters and in the retinal nerve fiber layer and macular thickness over a 5-year period in patients with Parkinson's disease (PD). Methods: Thirty patients with PD and 30 healthy subjects underwent a complete ophthalmic evaluation, including assessment of visual acuity, contrast sensitivity vision, color vision, and retinal evaluation with spectral-domain optical coherence tomography (SD-OCT). All subjects were reevaluated after 5 years to quantify changes in visual function parameters, the retinal nerve fiber layer, and macular thickness. Association between progressive ophthalmologic changes and disease progression was analyzed. Results: Changes were detected in visual function parameters and retinal nerve fiber layer thickness in patients compared with controls. Greater changes were found during the follow-up in the PD group than healthy subjects in visual acuity, contrast sensitivity, Lanthony color test (P < 0.016), in superotemporal and temporal retinal nerve fiber layer sectors (P < 0.001), and in macular thickness (all sectors except inner superior and inner inferior sectors, P < 0.001). Progressive changes in the retinal nerve fiber layer were associated with disease progression (r = 0.389, P = 0.028). Conclusions: Progressive visual dysfunction, macular thinning, and axonal loss can be detected in PD. Analysis of the macular thickness and the retinal nerve fiber layer by SD-OCT can be useful for evaluating Parkinson's disease progression.

Purpose. To evaluate neurodegeneration in patients with type 2 diabetes mellitus (DM2) without diabetic retinopathy and to assess the possible role of systemic vascular complications in retinal changes. Methods. Sixty eyes of 60 patients with DM2 and without any signs of diabetic retinopathy and 60 eyes of 60 healthy controls underwent retinal evaluation using Spectralis optical coherence tomography. Macular ganglion cell layer (GCL) and retinal nerve fiber layer (RNFL) were evaluated. Peripapillary RNFL thickness was assessed using Glaucoma and Axonal Analytics applications. Comparison between patients with the presence/absence of systemic vascular complications and different disease duration was made. Results. Macular GCL was reduced in patients compared to controls (p<0.001). Differences in the macular RNFL thickness were only observed in the outer inferior sector (p=0.033). A reduction in the peripapillary RNFL (average, inferior, and inferotemporal thickness, p<0.05 for all three) was observed in patients using both applications. Patients with chronic systemic vascular complications presented a reduction in the temporal RNFL (p=0.019) compared to patients without complications. The superotemporal RNFL thickness was thinner in patients with longer disease duration. Conclusions. Patients with type 2 DM without diabetic retinopathy and good metabolic control present neurodegeneration affecting neurons in the macular area and axons in different sectors of the optic disc. Systemic vascular complications contributed to further axonal damage in these patients, suggesting a possible role of subclinical ischaemia to retinal neurodegeneration in type 2 DM.

Background: The aim of this paper is to implement a system to facilitate the diagnosis of multiple sclerosis (MS) in its initial stages. It does so using a convolutional neural network (CNN) to classify images captured with swept-source optical coherence tomography (SS-OCT). Methods: SS-OCT images from 48 control subjects and 48 recently diagnosed MS patients have been used. These images show the thicknesses (45 × 60 points) of the following structures: complete retina, retinal nerve fiber layer, two ganglion cell layers (GCL+, GCL++) and choroid. The Cohen distance is used to identify the structures and the regions within them with greatest discriminant capacity. The original database of OCT images is augmented by a deep convolutional generative adversarial network to expand the CNN’s training set. Results: The retinal structures with greatest discriminant capacity are the GCL++ (44.99% of image points), complete retina (26.71%) and GCL+ (22.93%). Thresholding these images and using them as inputs to a CNN comprising two convolution modules and one classification module obtains sensitivity = specificity = 1.0. Conclusions: Feature pre-selection and the use of a convolutional neural network may be a promising, nonharmful, low-cost, easy-to-perform and effective means of assisting the early diagnosis of MS based on SS-OCT thickness data.