A fully convolutional neural network for new T2-w lesion detection in multiple sclerosis.

Journal: NeuroImage. Clinical
Published Date: Dec 28, 2019

Abstract

INTRODUCTION: Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new T2-w lesions on brain MR scans is considered a predictive biomarker for the disease. In this study, we propose a fully convolutional neural network (FCNN) to detect new T2-w lesions in longitudinal brain MR images.

Authors

  • Mostafa Salem
    Research institute of Computer Vision and Robotics, University of Girona, Spain; Computer Science Department, Faculty of Computers and Information, Assiut University, Egypt.
  • Sergi Valverde
    Research institute of Computer Vision and Robotics, University of Girona, Spain. Electronic address: svalverde@eia.udg.edu.
  • Mariano Cabezas
    Research institute of Computer Vision and Robotics, University of Girona, Spain.
  • Deborah Pareto
    Magnetic Resonance Unit, Dept of Radiology, Vall d'Hebron University Hospital, Spain.
  • Arnau Oliver
    Research institute of Computer Vision and Robotics, University of Girona, Spain.
  • Joaquim Salvi
    Research institute of Computer Vision and Robotics, University of Girona, Spain.
  • Àlex Rovira
    Magnetic Resonance Unit, Dept of Radiology, Vall d'Hebron University Hospital, Spain.
  • Xavier Lladó
    Research institute of Computer Vision and Robotics, University of Girona, Spain.

Keywords

External Resources

Popular Topics
Recent Journals