Detection of lesions in the optic nerve with magnetic resonance imaging using a 3D convolutional neural network

Optic neuritis (ON) is one of the first manifestations of multiple sclerosis, a disabling disease with rising prevalence. Detecting optic nerve lesions could be a relevant diagnostic marker in patients with multiple sclerosis. We aim to create an automated, interpretable method for optic nerve lesio...

Descripción completa

Detalles Bibliográficos
Autores: Martí-Juan, Gerard, Frías, Marcos, Garcia-Vidal, Aran|||0000-0003-1739-8636, Vidal-Jordana, Angela|||0000-0002-7270-5507, Alberich, Manel|||0000-0002-4132-0620, Calderon, Willem|||0000-0001-8285-5739, Piella, Gemma|||0000-0001-5236-5819, Camara, Oscar|||0000-0002-5125-6132, Montalban, Xavier|||0000-0002-0098-9918, Sastre-Garriga, Jaume|||0000-0002-1589-2254, Rovira, Alex|||0000-0002-2132-6750, Pareto, Deborah|||0000-0001-7356-3769
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:275710
Acceso en línea:https://ddd.uab.cat/record/275710
https://dx.doi.org/urn:doi:10.1016/j.nicl.2022.103187
Access Level:acceso abierto
Palabra clave:Optic nerve
Multiple sclerosis
Deep learning
CNN
MRI
Optic neuritis
Descripción
Sumario:Optic neuritis (ON) is one of the first manifestations of multiple sclerosis, a disabling disease with rising prevalence. Detecting optic nerve lesions could be a relevant diagnostic marker in patients with multiple sclerosis. We aim to create an automated, interpretable method for optic nerve lesion detection from MRI scans. We present a 3D convolutional neural network (CNN) model that learns to detect optic nerve lesions based on T2-weighted fat-saturated MRI scans. We validated our system on two different datasets (N = 107 and 62) and interpreted the behaviour of the model using saliency maps. The model showed good performance (68.11% balanced accuracy) that generalizes to unseen data (64.11%). The developed network focuses its attention to the areas that correspond to lesions in the optic nerve. The method shows robustness and, when using only a single imaging sequence, its performance is not far from diagnosis by trained radiologists with the same constraint. Given its speed and performance, the developed methodology could serve as a first step to develop methods that could be translated into a clinical setting.

Similares en LA Referencia