AI-Based Classification of Multiple Sclerosis Using OCT Retinal Layer Thickness Across Two Centers.
AI model distinguishes multiple sclerosis eyes from healthy eyes using retinal optical coherence tomography scans.
AI-Based Classification of Multiple Sclerosis Using OCT Retinal Layer Thickness Across Two Centers.
The latest revision of the McDonald criteria for diagnosis of multiple sclerosis (multiple sclerosis) establishes that the optic nerve can serve as a fifth anatomical location within the central nervous system for diagnosis.
To assess the accuracy of automated artificial-intelligence-based classification of multiple sclerosis patients using optical coherence tomography data obtained from two different centers.
Optical coherence tomography data were collected from two centers using standardized APOSTEL-based protocols and similar equipment.
The database drawn from two hospitals comprised 112 eyes with multiple sclerosis without prior history of optic neuritis and 193 eyes of control subjects.
The mean and standard deviation metrics had similar importance, with the most influential layers being the ganglion cell layer, inner plexiform layer, and the inner retinal layer complex.
Key regions included the papillomacular bundle and the superior temporal perimacular area.
Optical coherence tomography data facilitates highly accurate multiple sclerosis diagnosis across different centers. Artificial intelligence assessment could facilitate automated classification.
These findings provide evidence of the important role of the optic nerve in multiple sclerosis diagnosis.