Macular Ganglion Cell Layer May Provide Multiple Sclerosis Biomarker

OCT imaging, evaluated by a deep learning model, may be able to diagnose and predict the progression of multiple sclerosis.

Macular ganglion cell layer (mGCL) thicknesses, as measured using optical coherence tomography (OCT) and evaluated with a deep learning technique, may have the capacity to reveal both a diagnosis and prognosis of multiple sclerosis (MS), according to the results of a study published in Acta Ophthalmology.

Retinal nerve fiber layer (RNFL) thickness is well established as a biomarker to diagnose MS. Thickness of the macular ganglion cell layer is also associated with MS-related neurodegeneration, but it is unclear whether this biomarker can be used for diagnosis and prognosis. The study therefore aimed to evaluate the diagnostic and prognostic potential of mGCL thickness using OCT and deep learning techniques.

The study combined a cross-sectional and longitudinal design to evaluate 1 randomly selected eye from 72 patients with MS and 30 participants used as a healthy control group. Macular volume (0.88±0.14 mm3 vs 1.10±0.10 mm3; P <.001) and macular ganglion cell layer thicknesses (P <.001; except for central fovea and center thicknesses) were significantly lower in patients with MS compared with the healthy control participants.

Deep learning techniques achieved a diagnostic accuracy of 90.3% with 6 false positives and 8 false negatives. Deep learning was also used to predict long-term disability progression in multiple sclerosis with an accuracy of 81.9%.

The use of the non-invasive OCT test to measure thickness as an MS biomarker would reduce the need for many invasive tests and would facilitate early diagnosis.

These findings indicate that mGCL thickness is a valuable biomarker for diagnosis and evaluation of the progression of MS. In the context of other research, although RNFL thickness is more robust for diagnostic and prognostic purposes, both RNFL and macular ganglion cell layer metrics are valuable biomarkers. 

Traditionally, multiple sclerosis is diagnosed using extensive, invasive testing. OCT would provide an early, noninvasive testing option. 

“Including the use of OCT technology in the treatment of MS would bring great benefits to clinicians, who would make early and comprehensive diagnosis and would select the most specific treatments with which to improve patients’ lives,” according to the researchers. “The use of the non-invasive OCT test to measure thickness as an MS biomarker would reduce the need for many invasive tests and would facilitate early diagnosis.”

These results are limited by the small and unbalanced data set and lack of control for treatment. 


Montolío A, Cegoñino J, Garcia-Martin E, Pérez Del Palomar A. The macular retinal ganglion cell layer as a biomarker for diagnosis and prognosis in multiple sclerosis: A deep learning approach. Acta Ophthalmol. 2023;10.1111/aos.15722. doi:10.1111/aos.15722