机构：[a]NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada[b]Department of Neuroscience, Faculty of Medicine, University of Montreal, Montreal, QC, Canada[c]Department of Radiology and Biomedical Imaging, Zuckerberg San Francisco General Hospital, University of California, San Francisco, CA, USA[d]McConnell Brain Imaging Centre, Montreal Neurological Institute, Montreal, Canada[e]Department of Radiology, Xuanwu Hospital, Capital Medical University, Beijing, 100053, PR China放射科[f]Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, 100050, PR China[g]Department of Clinical Neuroscience, Karolinska Institutet, Stockholm, Sweden[h]Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, USA[i]CHU Rennes, Radiology Department, France[j]Univ Rennes, Inria, CNRS, Inserm, IRISA UMR, 6074, Visages U1128, France[k]CHU Rennes, Neurology Department, France[l]MS Unit, DPT of Neurology, University Hospital of Montpellier, France[m]Aix Marseille Univ, CNRS, CRMBM, Marseille, France[n]APHM, CHU Timone, CEMEREM, Marseille, France[o]APHM, Department of Neurology, CHU Timone, APHM, Marseille, France[p]Observatoire Franais de la Sclerose en Plaques (OFSEP), Univ Lyon, Universite Claude Bernard Lyon 1, Hospices Civils de Lyon, CREATIS-LRMN, UMR 5220 CNRS & U 1044 INSERM, Lyon, France[q]Neuroimaging Research Unit, INSPE, Division of Neuroscience, San Raffaele Scientific Institute, Vita-Salute San Raffaele University, Milan, Italy[r]Brigham and Women's Hospital, Harvard Medical School, Boston, USA[s]Queen Square MS Centre, UCL Institute of Neurology, Faculty of Brain Sciences, University College London, London, UK[t]Vanderbilt University, Tennessee, USA[u]National Institute of Neurological Disorders and Stroke, National Institutes of Health, Maryland, USA[v]National Institute of Radiological Sciences, Chiba, Chiba, Japan[w]Juntendo University Hospital, Tokyo, Japan[x]Hospital Cochin, Paris, France[y]Functional Neuroimaging Unit, CRIUGM, Universite de Montreal, Montreal, QC, Canada[z]Center for Medical Image Computing (CMIC), Department of Medical Physics and Biomedical Engineering, University College London, London, United Kingdom[aa]Biospective Inc., Montreal, QC, Canada[ab]Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON, Canada[ac]Neurology Department, Stanford University, USA[ad]NYU Langone Medical Center, New York, USA
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-1-, T-2-, and T-2*-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.
语种：
外文
高被引：
被引次数：
WOS：
PubmedID：
中科院(CAS)分区：
出版当年[2018]版：
大类|2 区医学
小类|1 区神经成像2 区神经科学2 区核医学
最新[2023]版：
大类|2 区医学
小类|1 区神经成像2 区神经科学2 区核医学
JCR分区：
出版当年[2017]版：
Q1NEUROSCIENCESQ1NEUROIMAGINGQ1RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
最新[2023]版：
Q1NEUROIMAGINGQ1NEUROSCIENCESQ1RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
第一作者机构：[a]NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
通讯作者：
通讯机构：[a]NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada[*1]Dept. Genie Electrique, L5610 Ecole Polytechnique 2900 Edouard-Montpetit Bld Montreal, QC, H3T 1J4, Canada.[y]Functional Neuroimaging Unit, CRIUGM, Universite de Montreal, Montreal, QC, Canada
推荐引用方式(GB/T 7714)：
Charley Gros,Benjamin De Leener,Atef Badji,et al.Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks[J].NEUROIMAGE.2019,184:901-915.doi:10.1016/j.neuroimage.2018.09.081.
APA：
Charley Gros,Benjamin De Leener,Atef Badji,Josefina Maranzano,Dominique Eden...&Julien Cohen-Adad.(2019).Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks.NEUROIMAGE,184,
MLA：
Charley Gros,et al."Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks".NEUROIMAGE 184.(2019):901-915
医学