Deciphering multiple sclerosis disability with deep learning attention maps on clinical MRI
Coll, Llucia (Hospital Universitari Vall d'Hebron)
Pareto, Deborah (Hospital Universitari Vall d'Hebron)
Carbonell-Mirabent, Pere (Hospital Universitari Vall d'Hebron)
Cobo-Calvo, Álvaro (Hospital Universitari Vall d'Hebron)
Arrambide, Georgina (Hospital Universitari Vall d'Hebron)
Vidal-Jordana, Angela (Hospital Universitari Vall d'Hebron)
Comabella, Manuel (Hospital Universitari Vall d'Hebron)
Castilló, Joaquín (Hospital Universitari Vall d'Hebron)
Rodríguez Acevedo, Breogán (Hospital Universitari Vall d'Hebron)
Zabalza, Ana (Hospital Universitari Vall d'Hebron)
Galan, Ingrid (Hospital Universitari Vall d'Hebron)
Midaglia, Luciana (Hospital Universitari Vall d'Hebron)
Nos, Carlos (Hospital Universitari Vall d'Hebron)
Salerno, Annalaura (Hospital Universitari Vall d'Hebron)
Auger, Cristina (Hospital Universitari Vall d'Hebron)
Alberich, Manel (Hospital Universitari Vall d'Hebron)
Río, Jordi (Hospital Universitari Vall d'Hebron)
Sastre-Garriga, Jaume (Hospital Universitari Vall d'Hebron)
Oliver, Arnau (Universitat de Girona. Institut de recerca en visió per computador i robòtica (VICOROB))
Montalban, Xavier (Hospital Universitari Vall d'Hebron)
Rovira, Alex (Hospital Universitari Vall d'Hebron)
Tintoré, Mar (Hospital Universitari Vall d'Hebron)
Lladó, Xavier (Universitat de Girona. Institut de recerca en visió per computador i robòtica (VICOROB))
Tur, Carmen (Hospital Universitari Vall d'Hebron)
Universitat Autònoma de Barcelona

Fecha:	2023
Resumen:	The application of convolutional neural networks (CNNs) to MRI data has emerged as a promising approach to achieving unprecedented levels of accuracy when predicting the course of neurological conditions, including multiple sclerosis, by means of extracting image features not detectable through conventional methods. Additionally, the study of CNN-derived attention maps, which indicate the most relevant anatomical features for CNN-based decisions, has the potential to uncover key disease mechanisms leading to disability accumulation. From a cohort of patients prospectively followed up after a first demyelinating attack, we selected those with T1-weighted and T2-FLAIR brain MRI sequences available for image analysis and a clinical assessment performed within the following six months (N = 319). Patients were divided into two groups according to expanded disability status scale (EDSS) score: ≥3. 0 and < 3. 0. A 3D-CNN model predicted the class using whole-brain MRI scans as input. A comparison with a logistic regression (LR) model using volumetric measurements as explanatory variables and a validation of the CNN model on an independent dataset with similar characteristics (N = 440) were also performed. The layer-wise relevance propagation method was used to obtain individual attention maps. The CNN model achieved a mean accuracy of 79% and proved to be superior to the equivalent LR-model (77%). Additionally, the model was successfully validated in the independent external cohort without any re-training (accuracy = 71%). Attention-map analyses revealed the predominant role of frontotemporal cortex and cerebellum for CNN decisions, suggesting that the mechanisms leading to disability accrual exceed the mere presence of brain lesions or atrophy and probably involve how damage is distributed in the central nervous system.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió publicada
Materia:	Multiple sclerosis ; Structural MRI ; Deep learning ; Attention maps ; Disability
Publicado en:	NeuroImage, Vol. 38 (march 2023) , ISSN 2213-1582

DOI: 10.1016/j.nicl.2023.103376
PMID: 36940621

12 p, 4.0 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados