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

Martí Juan, Gerard; Frías Nestares, Marcos; Garcia Vidal, Aran; Vidal Jordana, Angela; Alberich, Manel; Calderon, Willem; Piella Fenoy, Gemma; Camara, Oscar; Montalbán Gairín, Xavier; Sastre-Garriga, Jaume; Rovira, Àlex; Pareto, Deborah

doi:http://dx.doi.org/10.1016/j.nicl.2022.103187

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

License

Citation

Martí-Juan G, Frías M, Garcia-Vidal A, Vidal-Jordana A, Alberich M, Calderon W, Piella G, Camara O, Montalban X, Sastre-Garriga J, Rovira A, Pareto D. Detection of lesions in the optic nerve with magnetic resonance imaging using a 3D convolutional neural network. Neuroimage Clin. 2022;36:103187. DOI: 10.1016/j.nicl.2022.103187

Abstract

Background: 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. Objectives: We aim to create an automated, interpretable method for optic nerve lesion detection from MRI scans. Materials and Methods: 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. Results: 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. Conclusions: 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.