EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Global and Regional Deep Learning Models for Multiple Sclerosis Stratification From MRI

Llucia Coll iD, Deborah Pareto, Pere Carbonell-Mirabent, Álvaro Cobo-Calvo, Georgina Arrambide, Ángela Vidal-Jordana, Manuel Comabella, Joaquín Castilló, Breogán Rodrı Guez-Acevedo, Ana Zabalza, Ingrid Galán, Luciana Midaglia und 11 weitere

Journal of Magnetic Resonance Imaging · 2024-07 · 60 (1) · 258-267

DOI: 10.1002/jmri.29046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 06.10.2023. Verfasst von Llucia Coll und 22 weiteren Autor:innen. Beteiligte Einrichtung: Multiple Sclerosis Centre of Catalonia (Cemcat), Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain. Hauptthemen laut MEDLINE: Deep Learning, Multiple Sclerosis, Magnetic Resonance Imaging, Brain. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: 'la Caixa' Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The combination of anatomical MRI and deep learning‐based methods such as convolutional neural networks (CNNs) is a promising strategy to build predictive models of multiple sclerosis (MS) prognosis. However, studies assessing the effect of different input strategies on model's performance are lacking.

Purpose

To compare whole‐brain input sampling strategies and regional/specific‐tissue strategies, which focus on a priori known relevant areas for disability accrual, to stratify MS patients based on their disability level. Study Type Retrospective. Subjects Three hundred nineteen MS patients (382 brain MRI scans) with clinical assessment of disability level performed within the following 6 months (~70% training/~15% validation/~15% inference in‐house dataset) and 440 MS patients from multiple centers (independent external validation cohort). Field Strength/Sequence Single vendor 1.5 T or 3.0 T. Magnetization‐Prepared Rapid Gradient‐Echo and Fluid‐Attenuated Inversion Recovery sequences. Assessment A 7‐fold patient cross validation strategy was used to train a 3D‐CNN to classify patients into two groups, Expanded Disability Status Scale score (EDSS) ≥ 3.0 or EDSS < 3.0. Two strategies were investigated: 1) a global approach, taking the whole brain volume as input and 2) regional approaches using five different regions‐of‐interest: white matter, gray matter, subcortical gray matter, ventricles, and brainstem structures. The performance of the models was assessed in the in‐house and the independent external cohorts. Statistical Tests Balanced accuracy, sensitivity, specificity, area under receiver operating characteristic (ROC) curve (AUC).

Results

With the in‐house dataset, the gray matter regional model showed the highest stratification accuracy (81%), followed by the global approach (79%). In the external dataset, without any further retraining, an accuracy of 72% was achieved for the white matter model and 71% for the global approach. Data Conclusion The global approach offered the best trade‐off between internal performance and external validation to stratify MS patients based on accumulated disability. Evidence Level 4 Technical Efficacy Stage 2

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMultiple SclerosisMagnetic Resonance ImagingBrainHumansFemaleMaleRetrospective StudiesAdultMiddle AgedNeural Networks, ComputerReproducibility of ResultsImage Processing, Computer-AssistedROC CurvePrognosis

Stichwörter der Autor:innen

classificationdeep learninginput samplingmultiple sclerosisstructural MRI

Autor:innen und Institutionen

  • Multiple Sclerosis Centre of Catalonia (Cemcat), Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain.
  • Section of Neuroradiology, Department of Radiology, Hospital Universitari Vall d'Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain.
  • Research Institute of Computer Vision and Robotics, University of Girona, Girona, Spain.

ORCID-Profile: Llucia Coll

Förderung

  • 'la Caixa' Foundation

Zitieren

APA

Coll, L., Pareto, D., Carbonell-Mirabent, P., Cobo-Calvo, Á., Arrambide, G., Vidal-Jordana, Á., Comabella, M., Castilló, J., Rodrı Guez-Acevedo, B., Zabalza, A., Galán, I., Midaglia, L., Nos, C., Auger, C., Alberich, M., Río, J., Sastre-Garriga, J., Oliver, A., Montalban, X., …, & Tur, C. (2024). Global and Regional Deep Learning Models for Multiple Sclerosis Stratification From MRI. Journal of Magnetic Resonance Imaging, 60(1), 258-267. https://doi.org/10.1002/jmri.29046

Vancouver

Coll L, Pareto D, Carbonell-Mirabent P, Cobo-Calvo Á, Arrambide G, Vidal-Jordana Á, et al. Global and Regional Deep Learning Models for Multiple Sclerosis Stratification From MRI. Journal of Magnetic Resonance Imaging. 2024;60(1):258-267. doi:10.1002/jmri.29046

BibTeX
@article{Coll2024,
  author = {Coll, Llucia and Pareto, Deborah and Carbonell-Mirabent, Pere and Cobo-Calvo, Álvaro and Arrambide, Georgina and Vidal-Jordana, Ángela and Comabella, Manuel and Castilló, Joaquín and Rodrı Guez-Acevedo, Breogán and Zabalza, Ana and Galán, Ingrid and Midaglia, Luciana and Nos, Carlos and Auger, Cristina and Alberich, Manel and Río, Jordi and Sastre-Garriga, Jaume and Oliver, Arnau and Montalban, Xavier and Rovira, Àlex and Tintoré, Mar and Lladó, Xavier and Tur, Carmen},
  title = {Global and Regional Deep Learning Models for Multiple Sclerosis Stratification From MRI},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2024},
  volume = {60},
  number = {1},
  pages = {258--267},
  doi = {10.1002/jmri.29046}
}
Kostenlos starten →