Related Experiment Video
Updated: May 8, 2026
Using Optical Coherence Tomography and Optokinetic Response As Structural and Functional Visual System Readouts in Mice and Rats
Published on: January 10, 2019
Artificial neural network techniques to improve the ability of optical coherence tomography to detect optic neuritis
Elena Garcia-Martin1, Raquel Herrero, Maria P Bambo
1Ophthalmology Department, Miguel Servet University Hospital , Zaragoza , Spain .
Purpose:
To analyze the ability of Spectralis optical coherence tomography (OCT) to detect multiple sclerosis (MS) and to distinguish MS eyes with antecedent optic neuritis (ON). To analyze the capability of artificial neural network (ANN) techniques to improve the diagnostic precision.
Methods:
MS patients and controls were enrolled (n = 217). OCT was used to determine the 768 retinal nerve fiber layer thicknesses. Sensitivity and specificity were evaluated to test the ability of OCT to discriminate between MS and healthy eyes, and between MS with and without antecedent ON using ANN.
Results:
Using ANN technique multilayer perceptrons, OCT could detect MS with a sensitivity of 89.3%, a specificity of 87.6%, and a diagnostic precision of 88.5%. Compared with the OCT-provided parameters, the ANN had a better sensitivity-specificity balance.
Conclusions:
ANN technique improves the capability of Spectralis OCT to detect MS disease and to distinguish MS eyes with or without antecedent ON.
