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

Research output: Contribution to journalArticlepeer-review

Standard

Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. / Gros, Charley; De Leener, Benjamin; Badji, Atef; Maranzano, Josefina; Eden, Dominique; Dupont, Sara M.; Talbott, Jason; Zhuoquiong, Ren; Liu, Yaou; Granberg, Tobias; Ouellette, Russell; Tachibana, Yasuhiko; Hori, Masaaki; Kamiya, Kouhei; Chougar, Lydia; Stawiarz, Leszek; Hillert, Jan; Bannier, Elise; Kerbrat, Anne; Edan, Gilles; Labauge, Pierre; Callot, Virginie; Pelletier, Jean; Audoin, Bertrand; Rasoanandrianina, Henitsoa; Brisset, Jean-christophe; Valsasina, Paola; Rocca, Maria A.; Filippi, Massimo; Bakshi, Rohit; Tauhid, Shahamat; Prados, Ferran; Yiannakas, Marios; Kearney, Hugh; Ciccarelli, Olga; Smith, Seth; Treaba, Constantina Andrada; Mainero, Caterina; Lefeuvre, Jennifer; Reich, Daniel S.; Nair, Govind; Auclair, Vincent; Mclaren, Donald G.; Martin, Allan R.; Fehlings, Michael G.; Vahdat, Shahabeddin; Khatibi, Ali; Doyon, Julien; Shepherd, Timothy; Charlson, Erik; Narayanan, Sridar; Cohen-adad, Julien.

In: NeuroImage, Vol. 184, 01.01.2019, p. 901-915.

Research output: Contribution to journalArticlepeer-review

Harvard

Gros, C, De Leener, B, Badji, A, Maranzano, J, Eden, D, Dupont, SM, Talbott, J, Zhuoquiong, R, Liu, Y, Granberg, T, Ouellette, R, Tachibana, Y, Hori, M, Kamiya, K, Chougar, L, Stawiarz, L, Hillert, J, Bannier, E, Kerbrat, A, Edan, G, Labauge, P, Callot, V, Pelletier, J, Audoin, B, Rasoanandrianina, H, Brisset, J, Valsasina, P, Rocca, MA, Filippi, M, Bakshi, R, Tauhid, S, Prados, F, Yiannakas, M, Kearney, H, Ciccarelli, O, Smith, S, Treaba, CA, Mainero, C, Lefeuvre, J, Reich, DS, Nair, G, Auclair, V, Mclaren, DG, Martin, AR, Fehlings, MG, Vahdat, S, Khatibi, A, Doyon, J, Shepherd, T, Charlson, E, Narayanan, S & Cohen-adad, J 2019, 'Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks', NeuroImage, vol. 184, pp. 901-915. https://doi.org/10.1016/j.neuroimage.2018.09.081

APA

Gros, C., De Leener, B., Badji, A., Maranzano, J., Eden, D., Dupont, S. M., Talbott, J., Zhuoquiong, R., Liu, Y., Granberg, T., Ouellette, R., Tachibana, Y., Hori, M., Kamiya, K., Chougar, L., Stawiarz, L., Hillert, J., Bannier, E., Kerbrat, A., ... Cohen-adad, J. (2019). Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. NeuroImage, 184, 901-915. https://doi.org/10.1016/j.neuroimage.2018.09.081

Vancouver

Author

Gros, Charley ; De Leener, Benjamin ; Badji, Atef ; Maranzano, Josefina ; Eden, Dominique ; Dupont, Sara M. ; Talbott, Jason ; Zhuoquiong, Ren ; Liu, Yaou ; Granberg, Tobias ; Ouellette, Russell ; Tachibana, Yasuhiko ; Hori, Masaaki ; Kamiya, Kouhei ; Chougar, Lydia ; Stawiarz, Leszek ; Hillert, Jan ; Bannier, Elise ; Kerbrat, Anne ; Edan, Gilles ; Labauge, Pierre ; Callot, Virginie ; Pelletier, Jean ; Audoin, Bertrand ; Rasoanandrianina, Henitsoa ; Brisset, Jean-christophe ; Valsasina, Paola ; Rocca, Maria A. ; Filippi, Massimo ; Bakshi, Rohit ; Tauhid, Shahamat ; Prados, Ferran ; Yiannakas, Marios ; Kearney, Hugh ; Ciccarelli, Olga ; Smith, Seth ; Treaba, Constantina Andrada ; Mainero, Caterina ; Lefeuvre, Jennifer ; Reich, Daniel S. ; Nair, Govind ; Auclair, Vincent ; Mclaren, Donald G. ; Martin, Allan R. ; Fehlings, Michael G. ; Vahdat, Shahabeddin ; Khatibi, Ali ; Doyon, Julien ; Shepherd, Timothy ; Charlson, Erik ; Narayanan, Sridar ; Cohen-adad, Julien. / Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. In: NeuroImage. 2019 ; Vol. 184. pp. 901-915.

Bibtex

@article{a32de61a4dfa47659c7048485aaf9ac6,
title = "Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks",
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 (T1-, T2-, and T2∗-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.",
keywords = "Convolutional neural networks, MRI, Multiple sclerosis, Segmentation, Spinal cord, Reproducibility of Results, Humans, Magnetic Resonance Imaging/methods, Multiple Sclerosis/diagnostic imaging, Spinal Cord/pathology, Sensitivity and Specificity, Image Processing, Computer-Assisted/methods, Pattern Recognition, Automated, Observer Variation, Neural Networks (Computer)",
author = "Charley Gros and {De Leener}, Benjamin and Atef Badji and Josefina Maranzano and Dominique Eden and Dupont, {Sara M.} and Jason Talbott and Ren Zhuoquiong and Yaou Liu and Tobias Granberg and Russell Ouellette and Yasuhiko Tachibana and Masaaki Hori and Kouhei Kamiya and Lydia Chougar and Leszek Stawiarz and Jan Hillert and Elise Bannier and Anne Kerbrat and Gilles Edan and Pierre Labauge and Virginie Callot and Jean Pelletier and Bertrand Audoin and Henitsoa Rasoanandrianina and Jean-christophe Brisset and Paola Valsasina and Rocca, {Maria A.} and Massimo Filippi and Rohit Bakshi and Shahamat Tauhid and Ferran Prados and Marios Yiannakas and Hugh Kearney and Olga Ciccarelli and Seth Smith and Treaba, {Constantina Andrada} and Caterina Mainero and Jennifer Lefeuvre and Reich, {Daniel S.} and Govind Nair and Vincent Auclair and Mclaren, {Donald G.} and Martin, {Allan R.} and Fehlings, {Michael G.} and Shahabeddin Vahdat and Ali Khatibi and Julien Doyon and Timothy Shepherd and Erik Charlson and Sridar Narayanan and Julien Cohen-adad",
note = "Copyright {\textcopyright} 2018 Elsevier Inc. All rights reserved.",
year = "2019",
month = jan,
day = "1",
doi = "10.1016/j.neuroimage.2018.09.081",
language = "English",
volume = "184",
pages = "901--915",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks

AU - Gros, Charley

AU - De Leener, Benjamin

AU - Badji, Atef

AU - Maranzano, Josefina

AU - Eden, Dominique

AU - Dupont, Sara M.

AU - Talbott, Jason

AU - Zhuoquiong, Ren

AU - Liu, Yaou

AU - Granberg, Tobias

AU - Ouellette, Russell

AU - Tachibana, Yasuhiko

AU - Hori, Masaaki

AU - Kamiya, Kouhei

AU - Chougar, Lydia

AU - Stawiarz, Leszek

AU - Hillert, Jan

AU - Bannier, Elise

AU - Kerbrat, Anne

AU - Edan, Gilles

AU - Labauge, Pierre

AU - Callot, Virginie

AU - Pelletier, Jean

AU - Audoin, Bertrand

AU - Rasoanandrianina, Henitsoa

AU - Brisset, Jean-christophe

AU - Valsasina, Paola

AU - Rocca, Maria A.

AU - Filippi, Massimo

AU - Bakshi, Rohit

AU - Tauhid, Shahamat

AU - Prados, Ferran

AU - Yiannakas, Marios

AU - Kearney, Hugh

AU - Ciccarelli, Olga

AU - Smith, Seth

AU - Treaba, Constantina Andrada

AU - Mainero, Caterina

AU - Lefeuvre, Jennifer

AU - Reich, Daniel S.

AU - Nair, Govind

AU - Auclair, Vincent

AU - Mclaren, Donald G.

AU - Martin, Allan R.

AU - Fehlings, Michael G.

AU - Vahdat, Shahabeddin

AU - Khatibi, Ali

AU - Doyon, Julien

AU - Shepherd, Timothy

AU - Charlson, Erik

AU - Narayanan, Sridar

AU - Cohen-adad, Julien

N1 - Copyright © 2018 Elsevier Inc. All rights reserved.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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 (T1-, T2-, and T2∗-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.

AB - 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 (T1-, T2-, and T2∗-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.

KW - Convolutional neural networks

KW - MRI

KW - Multiple sclerosis

KW - Segmentation

KW - Spinal cord

KW - Reproducibility of Results

KW - Humans

KW - Magnetic Resonance Imaging/methods

KW - Multiple Sclerosis/diagnostic imaging

KW - Spinal Cord/pathology

KW - Sensitivity and Specificity

KW - Image Processing, Computer-Assisted/methods

KW - Pattern Recognition, Automated

KW - Observer Variation

KW - Neural Networks (Computer)

UR - http://www.scopus.com/inward/record.url?scp=85054688847&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2018.09.081

DO - 10.1016/j.neuroimage.2018.09.081

M3 - Article

C2 - 30300751

VL - 184

SP - 901

EP - 915

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -