Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks.

Journal: NeuroImage
Published Date: Jan 1, 2019

Abstract

The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework - robust to variability in both image parameters and clinical condition - for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n = 30). Data spanned three contrasts (T-, T-, and T-weighted) for a total of 1943 vol and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p ≤ 0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of -15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.

Authors

  • Charley Gros
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.
  • Benjamin De Leener
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.
  • Atef Badji
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada; Department of Neuroscience, Faculty of Medicine, University of Montreal, Montreal, QC, Canada.
  • Josefina Maranzano
    McConnell Brain Imaging Centre, Montreal Neurological Institute, Montreal, Canada.
  • Dominique Eden
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.
  • Sara M Dupont
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada.
  • Jason Talbott
    Department of Radiology and Biomedical Imaging, Zuckerberg San Francisco General Hospital, University of California, San Francisco, CA, USA.
  • Ren Zhuoquiong
    Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, PR China.
  • Yaou Liu
    Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, PR China; Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100050, PR China.
  • Tobias Granberg
    Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden; Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA.
  • Russell Ouellette
    Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden; Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA.
  • Yasuhiko Tachibana
    National Institute of Radiological Sciences, Chiba, Chiba, Japan.
  • Masaaki Hori
  • Kouhei Kamiya
    Department of Radiology, The University of Tokyo.
  • Lydia Chougar
    AP-HP, Hôpital de la Pitié Salpêtrière, Department of Neuroradiology, Paris 75013, France.
  • Leszek Stawiarz
    Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
  • Jan Hillert
    Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden.
  • Elise Bannier
    CHU Rennes, Radiology Department, France; Univ Rennes, Inria, CNRS, Inserm, IRISA UMR, 6074, Visages U1128, France.
  • Anne Kerbrat
    Univ Rennes, Inria, CNRS, Inserm, IRISA UMR, 6074, Visages U1128, France; CHU Rennes, Neurology Department, France.
  • Gilles Edan
    Univ Rennes, Inria, CNRS, Inserm, IRISA UMR, 6074, Visages U1128, France; CHU Rennes, Neurology Department, France.
  • Pierre Labauge
    MS Unit, DPT of Neurology, University Hospital of Montpellier, France.
  • Virginie Callot
    Aix Marseille Univ, CNRS, CRMBM, Marseille, France; APHM, Hôpital de la Timone, Pôle d'imagerie médicale, CEMEREM, Marseille, France.
  • Jean Pelletier
    APHM, CHU Timone, CEMEREM, Marseille, France; APHM, Department of Neurology, CHU Timone, APHM, Marseille, France.
  • Bertrand Audoin
    APHM, CHU Timone, CEMEREM, Marseille, France; APHM, Department of Neurology, CHU Timone, APHM, Marseille, France.
  • Henitsoa Rasoanandrianina
    Aix Marseille Univ, CNRS, CRMBM, Marseille, France; APHM, CHU Timone, CEMEREM, Marseille, France.
  • Jean-Christophe Brisset
    Observatoire Français de la Sclérose en Plaques (OFSEP), Univ Lyon, Université Claude Bernard Lyon 1, Hospices Civils de Lyon, CREATIS-LRMN, UMR 5220 CNRS & U 1044 INSERM, Lyon, France.
  • Paola Valsasina
    Neuroimaging Research Unit, INSPE, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy.
  • Maria A Rocca
    Neuroimaging Research Unit, INSPE, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy.
  • Massimo Filippi
    Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, Scientific Institute and University Vita-Salute San Raffaele, Milan, Italy.
  • Rohit Bakshi
    Laboratory for Neuroimaging Research, Ann Romney Center for Neurologic Diseases, Department of Neurology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States.
  • Shahamat Tauhid
    Brigham and Women's Hospital, Harvard Medical School, Boston, USA.
  • Ferran Prados
    Queen Square MS Centre, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, UK; Center for Medical Image Computing (CMIC), Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom.
  • Marios Yiannakas
    Queen Square MS Centre, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, UK.
  • Hugh Kearney
    Department of Neuropathology, Beaumont Hospital, Dublin, Ireland. hugh.kearney.10@ucl.ac.uk.
  • Olga Ciccarelli
    Department of Neuroinflammation, Institute of Neurology, University College London, London, UK.
  • Seth Smith
    Vanderbilt University, Tennessee, USA.
  • Constantina Andrada Treaba
    Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA.
  • Caterina Mainero
    Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA.
  • Jennifer Lefeuvre
    National Institute of Neurological Disorders and Stroke, National Institutes of Health, Maryland, USA.
  • Daniel S Reich
  • Govind Nair
    National Institute of Neurological Disorders and Stroke, National Institutes of Health, Maryland, USA.
  • Vincent Auclair
    Biospective Inc., Montreal, QC, Canada.
  • Donald G McLaren
    Biospective Inc., Montreal, QC, Canada.
  • Allan R Martin
    Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON, Canada.
  • Michael G Fehlings
    Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON, Canada.
  • Shahabeddin Vahdat
    Neurology Department, Stanford University, USA; Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada.
  • Ali Khatibi
    McConnell Brain Imaging Centre, Montreal Neurological Institute, Montreal, Canada; Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada.
  • Julien Doyon
    McConnell Brain Imaging Centre, Montreal Neurological Institute, Montreal, Canada; Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada.
  • Timothy Shepherd
    NYU Langone Medical Center, New York, USA.
  • Erik Charlson
    NYU Langone Medical Center, New York, USA.
  • Sridar Narayanan
    McConnell Brain Imaging Centre, Montreal Neurological Institute, Montreal, Canada.
  • Julien Cohen-Adad
    NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada; Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada.

Keywords

External Resources

Popular Topics
Recent Journals