Early diagnosis of multiple sclerosis by OCT analysis using Cohen's d method and a neural network as classifier. (February 2021)

• Record Type: Journal Article
• Authors: Garcia-Martin, E.; Ortiz, M.; Boquete, L.; Sánchez-Morla, E.M.; Barea, R.; Cavaliere, C.; Vilades, E.; Orduna, E.; Rodrigo, M.J.
• Is Part Of: Computers in biology and medicine. Volume 129(2021)
• Publication Date: 2021-02
• Subjects: Multiple sclerosis -- Optical coherence tomography -- Neural network -- Cohen's d -- Support vector machine; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104165
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Background: The consequences of inflammation, demyelination, axonal degeneration and neuronal loss in the central nervous system, typical of the development of multiple sclerosis (MS), are manifested in thinning of the retina and optic nerve. The purpose of this work is to diagnose early-stage MS patients based on analysis of retinal layer thickness obtained by swept-source optical coherence tomography (SS-OCT). Method: OCT (Triton® SS-OCT device -Topcon, Tokyo, Japan-) recordings were obtained from 48 control subjects and 48 recently diagnosed MS patients. The following thicknesses were measured on a 45 × 60 grid: retinal nerve fibre layer (RNFL), ganglion cell layer (GCL+), GCL++, retinal thickness and choroid. Using Cohen's d effect size, it was determined the regions and layers with greatest capacity to discriminate between control subjects and patients. Points exceeding the threshold set were used as inputs for an automatic classifier: support vector machine and feed-forward neural network. Results: In MS at clinical onset the layer with greatest discriminant capacity is GCL++ [AUC = 0.83] which exhibits a horseshoe-like macular topographic distribution. It is followed by retina, GCL+ and RNFL; choroidal thicknesses do not provide discriminatory capacity. Using a neural network as a classifier between controls and MS patients, obtains sensitivity of 0.98 and specificity of 0.98. Conclusions: This work suggest that OCT may serve as an important complementary role to other clinical tests, particularly regarding neurodegeneration. It is possible to characterise structural alterations in retina and diagnose early-stage MS with high degree of accuracy using OCT and artificial neural networks. Highlights: OCT may serve as an important complementary role to diagnose MS at early stage. In MS, at clinical onset, the GCL++ has the greatest discriminant capacity. Retinal regions and layers more altered can be detected with Cohen's d effect size. A neural network allows classify MS patients and controls with high S and E values. .