Precise identification of spinal nerve rootlets is relevant to delineate spinal levels for the study of functional activity in the spinal cord. The goal of this study was to develop an automatic method for the semantic segmentation of spinal nerve rootlets from T2-weighted magnetic resonance imaging (MRI) scans. Images from two open-access 3T MRI datasets were used to train a 3D multi-class convolutional neural network using an active learning approach to segment C2-C8 dorsal nerve rootlets. Each output class corresponds to a spinal level. The method was tested on 3T T2-weighted images from three datasets unseen during training to assess inter-site, inter-session, and inter-resolution variability. The test Dice score was 0.67 ± 0.16 (mean ± standard deviation across testing images and rootlets levels), suggesting a good performance. The method also demonstrated low inter-vendor and inter-site variability (coefficient of variation ≤ 1.41%), as well as low inter-session variability (coefficient of variation ≤ 1.30%), indicating stable predictions across different MRI vendors, sites, and sessions. The proposed methodology is open-source and readily available in the Spinal Cord Toolbox (SCT) v6.2 and higher.

Center of Research in Psychology and Neuroscience CNRS Aix Marseille Université Marseille France

Centre de Recherche du CHU Sainte Justine Université de Montréal Montreal QC Canada

Department of Neuroimaging Institute of Psychiatry Psychology and Neuroscience King's College London London United Kingdom

Department of Neurology Faculty of Medicine and Dentistry Palacký University Olomouc Olomouc Czechia

Department of Neurosurgery Faculty of Medicine and Dentistry Palacký University Olomouc Olomouc Czechia

Functional Neuroimaging Unit CRIUGM Université de Montréal Montreal QC Canada

Mila Quebec AI Institute Montreal QC Canada

NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal Montreal QC Canada

Wellcome Centre for Human Neuroimaging University College London London United Kingdom

Zobrazit více v PubMed

Azad , R. , Rouhier , L. , & Cohen-Adad , J. ( 2021. ). Stacked hourglass network with a multi-level attention mechanism: Where to look for intervertebral disc labeling . Lecture Notes in Computer Science , 12966 LNCS , 406 – 415 . 10.1007/978-3-030-87589-3_42 DOI

Bédard , S. , Bouthillier , M. , & Cohen-Adad , J. ( 2023. ). Pontomedullary junction as a reference for spinal cord cross-sectional area: Validation across neck positions . Scientific Reports , 13 ( 1 ), 13527 . 10.1038/s41598-023-40731-3 PubMed DOI PMC

Bédard , S. , & Cohen-Adad , J. ( 2022. ). Automatic measure and normalization of spinal cord cross-sectional area using the pontomedullary junction . Frontiers in Neuroimaging , 1 , 43 . 10.3389/fnimg.2022.1031253 PubMed DOI PMC

Boudreau , M. , Karakuzu , A. , Boré , A. , Pinsard , B. , Zelenkovski , K. , Alonso-Ortiz , E. , Boyle , J. , Bellec , P. , & Cohen-Adad , J. ( 2023. ). Longitudinal stability of brain and spinal cord quantitative MRI measures . NeuroLibre Reproducible Preprints , DOI

Bozorgpour , A. , Azad , B. , Azad , R. , Velichko , Y. , Bagci , U. , & Merhof , D. ( 2023. ). HCA-Net: Hierarchical context attention network for intervertebral disc semantic labeling . In arXiv [cs.CV]. arXiv . http://arxiv.org/abs/2311.12486

Branco , L. de M. T. , Rezende , T. J. R. , Reis , F. , & França , M. C., Jr. ( 2023. ). Advanced structural magnetic resonance imaging of the spinal cord: Technical aspects and clinical use . Seminars in Ultrasound, CT, and MR , 44 ( 5 ), 464 – 468 . 10.1053/j.sult.2023.03.016 PubMed DOI

Budd , S. , Robinson , E. C. , & Kainz , B. ( 2021. ). A survey on active learning and human-in-the-loop deep learning for medical image analysis . Medical Image Analysis , 71 , 102062 . 10.1016/j.media.2021.102062 PubMed DOI

Cadotte , D. W. , Cadotte , A. , Cohen-Adad , J. , Fleet , D. , Livne , M. , Wilson , J. R. , Mikulis , D. , Nugaeva , N. , & Fehlings , M. G. ( 2015. ). Characterizing the location of spinal and vertebral levels in the human cervical spinal cord . AJNR. American Journal of Neuroradiology , 36 ( 4 ), 803 – 810 . 10.3174/ajnr.a4192 PubMed DOI PMC

Cohen-Adad , J. , Alonso-Ortiz , E. , Abramovic , M. , Arneitz , C. , Atcheson , N. , Barlow , L. , Barry , R. L. , Barth , M. , Battiston , M. , Büchel , C. , Budde , M. , Callot , V. , Combes , A. J. E. , De Leener , B. , Descoteaux , M. , de Sousa , P. L. , Dostál , M. , Doyon , J. , Dvorak , A. , … Xu , J . ( 2021a. ). Generic acquisition protocol for quantitative MRI of the spinal cord . Nature Protocols , 16 ( 10 ), 4611 – 4632 . 10.1038/s41596-021-00588-0 PubMed DOI PMC

Cohen-Adad , J. , Alonso-Ortiz , E. , Abramovic , M. , Arneitz , C. , Atcheson , N. , Barlow , L. , Barry , R. L. , Barth , M. , Battiston , M. , Büchel , C. , Budde , M. , Callot , V. , Combes , A. J. E. , De Leener , B. , Descoteaux , M. , de Sousa , P. L. , Dostál , M. , Doyon , J. , Dvorak , A. , … Xu , J . ( 2021b. ). Open-access quantitative MRI data of the spinal cord and reproducibility across participants, sites and manufacturers . Scientific Data , 8 ( 1 ), 219 . 10.1038/s41597-021-01044-0 PubMed DOI PMC

Cohen-Adad , J. , Alonso-Ortiz , E. , Alley , S. , Lagana , M. M. , Baglio , F. , Vannesjo , S. J. , Karbasforoushan , H. , Seif , M. , Seifert , A. C. , Xu , J. , Kim , J.-W. , Labounek , R. , Vojtíšek , L. , Dostál , M. , Valošek , J. , Samson , R. S. , Grussu , F. , Battiston , M. , Gandini Wheeler-Kingshott , C. A. M. , … Prados , F . ( 2022. ). Comparison of multicenter MRI protocols for visualizing the spinal cord gray matter . Magnetic Resonance in Medicine , 88 ( 2 ), 849 – 859 . 10.1002/mrm.29249 PubMed DOI

Dauleac , C. , Frindel , C. , Pélissou-Guyotat , I. , Nicolas , C. , Yeh , F.-C. , Fernandez-Miranda , J. , Cotton , F. , & Jacquesson , T. ( 2022. ). Full cervical cord tractography: A new method for clinical use . Frontiers in Neuroanatomy , 16 , 993464 . 10.3389/fnana.2022.993464 PubMed DOI PMC

De Leener , B. , Fonov , V. S. , Collins , D. L. , Callot , V. , Stikov , N. , & Cohen-Adad , J. ( 2018. ). PAM50: Unbiased multimodal template of the brainstem and spinal cord aligned with the ICBM152 space . NeuroImage , 165 , 170 – 179 . 10.1016/j.neuroimage.2017.10.041 PubMed DOI

De Leener , B. , Lévy , S. , Dupont , S. M. , Fonov , V. S. , Stikov , N. , Collins Louis , D., Callot , V. , & Cohen-Adad , J. ( 2017. ). SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data . NeuroImage , 145 , 24 – 43 . 10.1016/j.neuroimage.2016.10.009 PubMed DOI

Diaz , E. , & Morales , H. ( 2016. ). Spinal cord anatomy and clinical syndromes . Seminars in Ultrasound, CT, and MR , 37 ( 5 ), 360 – 371 . 10.1053/j.sult.2016.05.002 PubMed DOI

Dou , Q. , Chen , H. , Yu , L. , Zhao , L. , Qin , J. , Wang , D. , Mok , V. C. , Shi , L. , & Heng , P.-A. ( 2016. ). Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks . IEEE Transactions on Medical Imaging , 35 ( 5 ), 1182 – 1195 . 10.1109/tmi.2016.2528129 PubMed DOI

Frostell , A. , Hakim , R. , Thelin , E. P. , Mattsson , P. , & Svensson , M. ( 2016. ). A review of the segmental diameter of the healthy human spinal cord . Frontiers in Neurology , 7 , 238 . 10.3389/fneur.2016.00238 PubMed DOI PMC

Galley , J. , Sutter , R. , Germann , C. , Wanivenhaus , F. , & Nanz , D. ( 2021. ). High-resolution in vivo MR imaging of intraspinal cervical nerve rootlets at 3 and 7 Tesla . European Radiology , 31 ( 7 ), 4625 – 4633 . 10.1007/s00330-020-07557-3 PubMed DOI

Gasparotti , R. , Lodoli , G. , Meoded , A. , Carletti , F. , Garozzo , D. , & Ferraresi , S. ( 2013. ). Feasibility of diffusion tensor tractography of brachial plexus injuries at 1.5 T . Investigative Radiology , 48 ( 2 ), 104 – 112 . 10.1097/rli.0b013e3182775267 PubMed DOI

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 . 10.1016/j.neuroimage.2018.09.081 PubMed DOI PMC

Gros , C. , De Leener , B , Dupont , S. M. , Martin , A. R. , Fehlings , M. G. , Bakshi , R. , Tummala , S. , Auclair , V. , McLaren , D. G. , Callot , V. , Cohen-Adad , J. , & Sdika , M. ( 2018. ). Automatic spinal cord localization, robust to MRI contrasts using global curve optimization . Medical Image Analysis , 44 , 215 – 227 . 10.1016/j.media.2017.12.001 PubMed DOI

Isensee , F. , Jaeger , P. F. , Kohl , S. A. A. , Petersen , J. , & Maier-Hein , K. H. ( 2021. ). nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation . Nature Methods , 18 ( 2 ), 203 – 211 . 10.1038/s41592-020-01008-z PubMed DOI

Jamaludin , A. , Kadir , T. , & Zisserman , A. ( 2017. ). SpineNet: Automated classification and evidence visualization in spinal MRIs . Medical Image Analysis , 41 , 63 – 73 . 10.1016/j.media.2017.07.002 PubMed DOI

Kinany , N. , Landelle , C. , De Leener , B. , Lungu , O. , Doyon , J. , & Van De Ville , D . ( 2024. ). In vivo parcellation of the human spinal cord functional architecture . Imaging Neuroscience , 2 , 1 – 17 . 10.1162/imag_a_00059 DOI

Kinany , N. , Pirondini , E. , Mattera , L. , Martuzzi , R. , Micera , S. , & Van De Ville , D . ( 2022. ). Towards reliable spinal cord fMRI: Assessment of common imaging protocols . NeuroImage , 250 , 118964 . 10.1016/j.neuroimage.2022.118964 PubMed DOI

Kinany , N. , Pirondini , E. , Micera , S. , & Van De Ville , D . ( 2020. ). Dynamic functional connectivity of resting-state spinal cord fMRI reveals fine-grained intrinsic architecture . Neuron , 108 ( 3 ), 424 – 435.e4 . 10.1016/j.neuron.2020.07.024 PubMed DOI

Kinany , N. , Pirondini , E. , Micera , S. , & Van De Ville , D . ( 2023. ). Spinal Cord fMRI: A new window into the central nervous system . The Neuroscientist: A Review Journal Bringing Neurobiology, Neurology and Psychiatry , 29 ( 6 ), 715 – 731 . 10.1177/10738584221101827 PubMed DOI PMC

Lemay , A. , Gros , C. , Zhuo , Z. , Zhang , J. , Duan , Y. , Cohen-Adad , J. , & Liu , Y. ( 2021. ). Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning . NeuroImage. Clinical , 31 , 102766 . 10.1016/j.nicl.2021.102766 PubMed DOI PMC

Mbarki , W. , Bouchouicha , M. , Frizzi , S. , Tshibasu , F. , Farhat , L. B. , & Sayadi , M. ( 2020. ). Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI . Interdisciplinary Neurosurgery , 22 , 100837 . 10.1016/j.inat.2020.100837 DOI

Mendez , A. , Islam , R. , Latypov , T. , Basa , P. , Joseph , O. J. , Knudsen , B. , Siddiqui , A. M. , Summer , P. , Staehnke , L. J. , Grahn , P. J. , Lachman , N. , Windebank , A. J. , & Lavrov , I. A. ( 2021. ). Segment-specific orientation of the dorsal and ventral roots for precise therapeutic targeting of human spinal cord . Mayo Clinic Proceedings. Mayo Clinic , 96 ( 6 ), 1426 – 1437 . 10.1016/j.mayocp.2020.07.039 PubMed DOI

Naga Karthik , E. , Valosek , J. , Smith , A. C. , Pfyffer , D. , Schading-Sassenhausen , S. , Farner , L. , Weber , K. A. , II , Freund, P. , & Cohen-Adad , J. ( 2024. ). SCIseg: Automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury . In bioRxiv . 10.1101/2024.01.03.24300794 PubMed DOI PMC

Powers , J. , Ioachim , G. , & Stroman , P. ( 2018. ). Ten key insights into the use of spinal cord fMRI . Brain Sciences , 8 ( 9 ), 173 . 10.3390/brainsci8090173 PubMed DOI PMC

Rouhier , L. , Romero , F. P. , Cohen , J. P. , & Cohen-Adad , J. ( 2020. ). Spine intervertebral disc labeling using a fully convolutional redundant counting model . In arXiv [eess.IV] . arXiv. http://arxiv.org/abs/2003.04387

Seifert , A. C. , Xu , J. , Kong , Y. , Eippert , F. , Miller , K. L. , Tracey , I. , & Vannesjo , S. J. ( 2023. ). Thermal stimulus task fMRI in the cervical spinal cord at 7 Tesla . bioRxiv: The Preprint Server for Biology . 10.1101/2023.01.31.526451 PubMed DOI PMC

Shorten , C. , & Khoshgoftaar , T. M. ( 2019. ). A survey on image data augmentation for deep learning . Journal of Big Data , 6 ( 1 ), 1 – 48 . 10.1186/s40537-019-0197-0 PubMed DOI PMC

Standring , S. ( 2020. ). Gray’s anatomy, 42nd ed., p. 1606 . Elsevier; . 10.1016/j.jhsb.2005.06.012 DOI

Tubbs , R. S. , Loukas , M. , Slappey , J. B. , Shoja , M. M. , Oakes , W. J. , & Salter , E. G. ( 2007. ). Clinical anatomy of the C1 dorsal root, ganglion, and ramus: A review and anatomical study . Clinical Anatomy , 20 ( 6 ), 624 – 627 . 10.1002/ca.20472 PubMed DOI

Ullmann , E. , Paquette Pelletier , F. J. , Thong , W. E. , & Cohen-Adad , J. ( 2014. ). Automatic labeling of vertebral levels using a robust template-based approach . International Journal of Biomedical Imaging , 2014 , 719520 . 10.1155/2014/719520 PubMed DOI PMC

Vania , M. , & Lee , D. ( 2021. ). Intervertebral disc instance segmentation using a multistage optimization mask-RCNN (MOM-RCNN) . Finite Elements in Analysis and Design: The International Journal of Applied Finite Elements and Computer Aided Engineering , 8 ( 4 ), 1023 – 1036 . 10.1093/jcde/qwab030 DOI

Warfield , S. K. , Zou , K. H. , & Wells , W. M. ( 2004. ). Simultaneous truth and performance level estimation (STAPLE): An algorithm for the validation of image segmentation . IEEE Transactions on Medical Imaging , 23 ( 7 ), 903 – 921 . 10.1109/tmi.2004.828354 PubMed DOI PMC

Weber , K. A. , 2nd , Chen, Y. , Paliwal , M. , Law , C. S. , Hopkins , B. S. , Mackey , S. , Dhaher , Y. , Parrish , T. B. , & Smith , Z. A. ( 2020. ). Assessing the spatial distribution of cervical spinal cord activity during tactile stimulation of the upper extremity in humans with functional magnetic resonance imaging . NeuroImage , 217 , 116905 . 10.1016/j.neuroimage.2020.116905 PubMed DOI PMC

Weber , K. A. , 2nd , Chen, Y. , Wang , X. , Kahnt , T. , & Parrish , T. B. ( 2016. ). Functional magnetic resonance imaging of the cervical spinal cord during thermal stimulation across consecutive runs . NeuroImage , 143 , 267 – 279 . 10.1016/j.neuroimage.2016.09.015 PubMed DOI PMC

Zhao , W. , Cohen-Adad , J. , Polimeni , J. R. , Keil , B. , Guerin , B. , Setsompop , K. , Serano , P. , Mareyam , A. , Hoecht , P. , & Wald , L. L. ( 2014. ). Nineteen-channel receive array and four-channel transmit array coil for cervical spinal cord imaging at 7T . Magnetic Resonance in Medicine: Official Journal of the Society of Magnetic Resonance in Medicine / Society of Magnetic Resonance in Medicine , 72 ( 1 ), 291 – 300 . 10.1002/mrm.24911 PubMed DOI PMC

Rootlets-based registration to the PAM50 spinal cord template