2026-04-13T12:32:21Zhttps://recercat.cat/oai/request

oai:recercat.cat:11351/86732024-12-13T10:27:04Zcom_2072_378070com_2072_378040com_2072_378071col_2072_378092col_2072_378097

2023-11-08T13:41:22Z urn:hdl:11351/8673 Detection of lesions in the optic nerve with magnetic resonance imaging using a 3D convolutional neural network Marti Juan, Gerard Frías, Marcos Garcia Vidal, Aran Vidal Jordana, Angela Alberich Jordà, Manel Calderon Miranda, Willem Guillermo Montalban Gairín, Xavier Rovira Cañellas, Alex Pareto Onghena, Deborah Sastre Garriga, Jaume Esclerosi múltiple Neuritis - Imatgeria Imatgeria per ressonància magnètica DISEASES::Nervous System Diseases::Autoimmune Diseases of the Nervous System::Demyelinating Autoimmune Diseases, CNS::Multiple Sclerosis DISEASES::Nervous System Diseases::Cranial Nerve Diseases::Optic Nerve Diseases::Optic Neuritis Other subheadings::Other subheadings::Other subheadings::/diagnostic imaging ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Tomography::Magnetic Resonance Imaging ENFERMEDADES::enfermedades del sistema nervioso::enfermedades autoinmunitarias del sistema nervioso::enfermedades autoinmunes desmielinizantes del SNC::esclerosis múltiple ENFERMEDADES::enfermedades del sistema nervioso::enfermedades de los pares craneales::enfermedades del nervio óptico::neuritis óptica Otros calificadores::Otros calificadores::Otros calificadores::/diagnóstico por imagen TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS::diagnóstico::técnicas y procedimientos diagnósticos::diagnóstico por imagen::tomografía::imagen por resonancia magnética Deep learning; Multiple sclerosis, Optic nerve Aprendizaje profundo; Esclerosis múltiple; Nervio óptico Aprenentatge profund; Esclerosi múltiple; Nervi òptic 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. This project was developed as a part of Gerard Martí-Juan ECTRIMS Research Fellowship Program 2021–2022. This study was partially supported by the Projects (PI18/00823, PI19/00950), from the Fondo de Investigación Sanitaria (FIS), Instituto de Salud Carlos III. 2023-11-08T13:41:22Z 2023-11-08T13:41:22Z 2022-12-16T08:37:27Z 2022-12-16T08:37:27Z 2022 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://hdl.handle.net/11351/8673 NeuroImage: Clinical;36 https://doi.org/10.1016/j.nicl.2022.103187 info:eu-repo/grantAgreement/ES/PE2013-2016/PI18%2F00823 info:eu-repo/grantAgreement/ES/PE2017-2020/PI19%2F00950 Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess Elsevier Scientia