Related Experiment Video
Updated: Oct 26, 2025
12:23
Dynamic Visual Tests to Identify and Quantify Visual Damage and Repair Following Demyelination in Optic Neuritis Patients
Published on: April 14, 2014
14.3K
Retinal OCT Texture Analysis for Differentiating Healthy Controls from Multiple Sclerosis (MS) with/without Optic
Hamidreza Dehghan Tazarjani1, Zahra Amini1, Rahele Kafieh1
1Medical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
Biomed Research International
|August 2, 2021
Summary
Texture features from Optical Coherence Tomography (OCT) images show promise for diagnosing multiple sclerosis (MS). Combining texture analysis with retinal layer thickness improves diagnostic accuracy for MS, including cases with and without optic neuritis (ON).
Area of Science:
- Ophthalmology
- Neurology
- Medical Imaging
Background:
- Multiple sclerosis (MS) is a central and peripheral nervous system inflammatory disease.
- Optic neuritis (ON) is a common ocular manifestation of MS.
- Current MS diagnosis relies on MRI, but Optical Coherence Tomography (OCT) shows potential for early detection.
Purpose of the Study:
- To introduce a novel pipeline for constructing layer-stacked (LS) images from OCT data.
- To extract and evaluate texture features from LS images for differentiating healthy controls (HC) from MS patients (with and without ON).
- To assess the combined diagnostic power of texture features and conventional retinal layer thickness values.
Main Methods:
- Development of a pipeline to create LS images from OCT scans, isolating data from specific neural retinal layers.
- Extraction of a comprehensive set of tailored texture features from LS images.
- Comparative analysis of texture features and thickness values for classifying HC, MS (ON), and MS (None-ON) groups.
Main Results:
- Texture features extracted from LS images demonstrate significant ability in diagnosing MS cases.
- The combination of texture features and conventional thickness values substantially enhances discrimination between HC and MS groups (including HC vs. MS-ON and HC vs. MS-None-ON).
Conclusions:
- Texture analysis of OCT-derived LS images offers a powerful tool for MS diagnosis.
- Integrating texture features with thickness measurements improves diagnostic performance, aiding in the differentiation of healthy individuals from MS patients.
