M. Radaelli
San Raffaele HospitalAuthor Of 2 Presentations
PS15.03 - Optical coherence tomography in aquaporin-4-IgG positive neuromyelitis optica spectrum disorders: a collaborative multi-center study
- F. Oertel
- S. Specovius
- H. Zimmermann
- C. Chien
- S. Motamedi
- L. Cook
- M. Lana-Peixoto
- M. Fontenelle
- H. Kim
- J. Hyun
- J. Palace
- A. Roca-Fernandez
- F. Ashtari
- R. Kafieh
- L. Pandit
- A. D'Cunha
- O. Aktas
- M. Ringelstein
- E. May
- C. Tongco
- L. Leocani
- M. Pisa
- M. Radaelli
- E. Martinez-Lapiscina
- H. Stiebel-Kalish
- S. Siritho
- J. De Seze
- T. Senger
- J. Havla
- R. Marignier
- E. Nerrant
- A. Cobo Calvo
- D. Bichuetti
- I. Tavares
- N. Asgari
- K. Soelberg
- A. Altintas
- U. Tanriverdi
- A. Jacob
- S. Huda
- Z. Rimler
- Y. Mao-Draayer
- I. Soto De Castillo
- A. Green
- M. Yeaman
- T. Smith
- A. Brandt
- F. Paul
Abstract
Background
Optic neuritis (ON) is a frequent manifestation in aquaporin-4 antibody (AQP4-IgG) seropositive neuromyelitis optica spectrum disorders (NMOSD). Due to limited samples, existing optical coherence tomography (OCT) studies are inconsistent regarding retinal changes in eyes with a history of ON (NMO-ON) and without a history of ON (NMO-NON), and their functional relevance.
Objectives
The CROCTINO (Collaborative Retrospective Study on retinal OCT in Neuromyelitis Optica) project aims to reveal correlates of retinal pathology and to generate hypotheses for prospective OCT studies in NMOSD. The objective of this study was to analyze retinal changes of AQP4-IgG seropositive NMO-ON and NMO-NON eyes in an international cross-sectional OCT dataset.
Methods
Of 656 subjects, we enrolled 283 AQP4-IgG seropositive NMOSD patients and 72 healthy controls (HC) from 22 international expert centers. OCT data was acquired with Spectralis SD-OCT, Cirrus HD-OCT and Topcon 3D OCT-1. Mean thickness for the combined ganglion cell and inner plexiform layer (GCIP) and inner nuclear layer (INL) were calculated from macular volume scans. Clinical, functional and laboratory testing were performed at discretion of each center.
Results
We compared NMO-ON eyes (N = 260), NMO-NON eyes (N = 241) and HC eyes (N = 136). GCIP was reduced in NMO-ON (57.4 ± 12.2 µm) compared with NMO-NON (75.9 ± 7.7 µm; p < 0.001) and HC (81.4 ± 5.7 µm; p < 0.001). NMO-NON had thinner GCIP (p < 0.001) compared with HC. INL was thicker in NMO-ON (40.3 ± 3.9 µm) compared with NMO-NON (38.6 ± 3.9µm; p < 0.001), but not HC (39.4 ± 2.6 µm). Microcystic macular edema were visible in 6.6 % of NMOSD eyes.
Conclusions
AQP4-IgG seropositive NMOSD is characterized by a functionally relevant loss of retinal neuroaxonal content and a - probably inflammatory - increase of INL after ON. Our study further supports the existence of attack-independent damage in the visual system of patients with AQP4-IgG seropositive NMOSD.
PS16.05 - Application of deep-learning to NMOSD and unclassified seronegative patients
Abstract
Background
Current diagnostic criteria of neuromyelitis optica spectrum disorders (NMOSD) allow the diagnosis of aquaporin-4 (AQP4) seropositive patients with limited manifestations, whereas seronegative patients with limited phenotypes remain unclassified and are usually considered as prodromal phases of multiple sclerosis (MS) or different entities themselves. Nowadays, there is great effort to perform an automatic diagnosis of different neurological diseases using deep-learning-based imaging diagnostics, which is a form of artificial intelligence, allowing predicting or making decisions without a priori human intervention.
Objectives
To provide a deep-learning classification of NMOSD patients with different serological profiles and to compare these results with their clinical evolution.
Methods
228 T2- and T1-weighted brain MRIs were acquired from patients with AQP4-seropositive NMOSD (n=85), early MS (n=95), AQP4-seronegative NMOSD (n=11, 3 with anti-myelin oligodendrocyte glycoprotein antibodies) and unclassified double-seronegative limited phenotypes (n=17 idiopathic recurrent optic neuritis [IRON], n=20 idiopathic recurrent myelitis [IRM]). The latter had a clinical re-evaluation after 4-year follow-up. The neural network architecture was based on four 3D convolutional layers. It was trained and validated on MRI scans (n=180) from AQP4-seropositive NMOSD and MS patients. Then, it was applied to AQP4-seronegative NMOSD and double-seronegative patients with limited phenotypes to evaluate their classification as NMOSD or MS in comparison with their clinical follow-up.
Results
The final algorithm discriminated between AQP-4-seropositive NMOSD and MS with an accuracy of 0.95. Forty-seven/48 (97.9%) seronegative patients were classified as NMOSD (one patient with IRON was classified as MS). Clinical follow-up was available in 27/37 (73%) double-seronegative limited phenotypes: one patient evolved to MS, three developed NMOSD and the others did not change phenotype.
Conclusions
Deep-learning may help in the diagnostic work-up of NMOSD. Our findings support the inclusion of AQP4-seronegative patients to the spectrum of NMO and suggest its enlargement to double-seronegative limited phenotypes.