Timing of retinal neuronal and axonal loss in MS: a longitudinal OCT study

Abstract

The objective of the study was to investigate the timing of central nervous system tissue atrophy in MS by evaluating longitudinal retinal volume changes in a broadly representative cohort with disease duration across the entire arc of disease. In this longitudinal study, 135 patients with MS and 16 healthy reference subjects underwent spectral-domain optical coherence tomography (OCT) at baseline and 2 years later. Following OCT quality control, automated segmentation of the peripapillary retinal nerve fiber layer (pRNFL), macular ganglion cell-inner plexiform layer (mGCIPL) and macular inner nuclear layer (mINL) was performed. Generalized estimation equations were used to analyze longitudinal changes and associations with disease duration and clinical measures. Participants had a median disease duration at baseline of 16.4 years (range 0.1-45.4). Nearly half (44 %) of the MS patients had previously experienced MS-related optic neuritis (MSON) more than 6 months prior. The MS patients demonstrated a significant decrease over 2 years of the pRNFL (-1.1 µm, 95 % CI 1.4-0.7, p < 0.001) and mGCIPL (-1.1 µm, 95 % CI -1.4 to -0.8, p < 0.001). This thinning was most pronounced early in the course of disease. These findings were irrespective of previous episodes of MSON. No consistent pattern of change was observed for the mINL (-0.03 µm, 95 % CI -0.2 to 0.2, p = 0.795). This longitudinal study demonstrated that injury of the innermost retinal layers is found in MS and that this damage occurs most rapidly during the early stages of disease. The attenuation of atrophy with longer disease duration is suggestive of a plateau effect. These findings emphasize the importance of early intervention to prevent such injury.

Keywords: Multiple sclerosis; Neurodegeneration; Optical coherence tomography; RNFL; Retina.

Fig. 1

Scan and segmentation protocol for the OCT scans used in this study. a The peripapillary ring scan (12° diameter) was used to quantify the global mean retinal nerve fiber layer (pRNFL) thickness. b The macular volume scan (20° × 20° field, 25 B-scans) was centered on the fovea and used to assess thickness of the macular ganglion cell + inner plexiform layer (mGCIPL) and the inner nuclear (mINL). The colored map represents a change in thickness map with a 1, 2.22 and 3.45-mm EDTRS grid of which the eight perimacular sectors were used in this study. The inner 1 mm circle was excluded from the analysis because of absence of mGCIPL and mINL in the fovea

Fig. 2

Center specific distribution of a disease duration (years) and b disease severity (MSSS score). Patients recruited from the VUMC Amsterdam had a significantly longer disease duration [22.0 years (SD 6.5)] compared with patients from UCSF [9.2 years (SD 9.6), p < 0.001]. Disease severity (MSSS score) was comparable for both centers [UCSF 3.7 (SD 2.5) and VUMC 3.8 (SD 2.4), p = 0.862]. The horizontal dotted lines indicate the mean value per center

Fig. 3

Association between disease duration and change in retinal layer thickness. Thinning of the pRNFL a and mGCIPL b is significantly associated with disease duration. For the mINL (C), no significant association was observed. * GEE, adjusted for inter-eye correlation, optic neuritis, sex

Fig. 4

Mean change and 95 % CIs (error bars) in pRNFL (a), mGCIPL (b), and mINL (c) per disease duration group. pRNFL and mGCIPL thickness changes were dependent on disease duration, as changes were most pronounced early in the disease course. The horizontal dotted reference line indicates no change from baseline [group sizes: <5 years (N = 31), 5.0–9.9 years (N = 15), 10.0–14.9 years (N = 15), 15.0–19.9 years (N = 30), 20.0–24.9 (N = 17) and ≥25 years (N = 26)]