Convolutional Neural Network–Based Automated Segmentation of the Spinal Cord and Contusion Injury: Deep Learning Biomarker Correlates of Motor Impairment in Acute Spinal Cord Injury

REFERENCES

1. 1.↵
   2. Ahuja CS,
   3. Wilson JR,
   4. Nori S, et al

   . Traumatic spinal cord injury. Nat Rev Dis Primers 2017;3:17018 doi:10.1038/nrdp.2017.18 pmid:28447605

   CrossRefPubMed
2. 2.↵
   2. Talekar K,
   3. Poplawski M,
   4. Hegde R, et al

   . Imaging of spinal cord injury: acute cervical spinal cord injury, cervical spondylotic myelopathy, and cord herniation. Semin Ultrasound CT MR 2016;37:431–47 doi:10.1053/j.sult.2016.05.007 pmid:27616315

   CrossRefPubMed
3. 3.↵
   2. Burns AS,
   3. Marino RJ,
   4. Flanders AE, et al

   . Clinical diagnosis and prognosis following spinal cord injury. Handb Clin Neurol 2012;109:47–62 doi:10.1016/B978-0-444-52137-8.00003-6 pmid:23098705

   CrossRefPubMed
4. 4.↵
   2. Bozzo A,
   3. Marcoux J,
   4. Radhakrishna M, et al

   . The role of magnetic resonance imaging in the management of acute spinal cord injury. J Neurotrauma 2011;28:1401–11 doi:10.1089/neu.2009.1236 pmid:20388006

   CrossRefPubMed
5. 5.↵
   2. Kurpad S,
   3. Martin AR,
   4. Tetreault LA, et al

   . Impact of baseline magnetic resonance imaging on neurologic, functional, and safety outcomes in patients with acute traumatic spinal cord injury. Global Spine J 2017;7:151S–74S doi:10.1177/2192568217703666 pmid:29164022

   CrossRefPubMed
6. 6.↵
   2. Fehlings MG,
   3. Martin AR,
   4. Tetreault LA, et al

   . A clinical practice guideline for the management of patients with acute spinal cord injury: recommendations on the role of baseline magnetic resonance imaging in clinical decision making and outcome prediction. Global Spine J 2017;7:221S–30S doi:10.1177/2192568217703089 pmid:29164028

   CrossRefPubMed
7. 7.↵
   2. Fehlings MG,
   3. Tetreault LA,
   4. Wilson JR, et al

   . A clinical practice guideline for the management of patients with acute spinal cord injury and central cord syndrome: recommendations on the timing (≤24 hours versus>24 hours) of decompressive surgery. Global Spine J 2017;7:195S–202S doi:10.1177/2192568217706367 pmid:29164024

   CrossRefPubMed
8. 8.↵
   2. Elizei SS,
   3. Kwon BK

   . The translational importance of establishing biomarkers of human spinal cord injury. Neural Regen Res 2017;12:385–38 doi:10.4103/1673-5374.202933 pmid:28469645

   CrossRefPubMed
9. 9.↵
   2. Farhadi HF,
   3. Kukreja S,
   4. Minnema A, et al

   . Impact of admission imaging findings on neurological outcomes in acute cervical traumatic spinal cord injury. J Neurotrauma 2018;35:1398–406 doi:10.1089/neu.2017.5510 pmid:29361876

   CrossRefPubMed
10. 10.↵
    2. Fonov VS,
    3. Le Troter A,
    4. Taso M, et al

    . Framework for integrated MRI average of the spinal cord white and gray matter: the MNI-Poly-AMU template. Neuroimage 2014;102(Pt 2):817–27 doi:10.1016/j.neuroimage.2014.08.057 pmid:25204864

    CrossRefPubMed
11. 11.↵
    2. De Leener B,
    3. Lévy S,
    4. Dupont SM, et al

    . SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data. Neuroimage 2017;145:24–43 doi:10.1016/j.neuroimage.2016.10.009 pmid:27720818

    CrossRefPubMed
12. 12.↵
    2. Jenkinson M,
    3. Beckmann CF,
    4. Behrens TE, et al

    . FSL. Neuroimage 2012;62:782–90 doi:10.1016/j.neuroimage.2011.09.015 pmid:21979382

    CrossRefPubMedWeb of Science
13. 13.↵
    2. Fischl B

    . FreeSurfer. Neuroimage 2012;62:774–81 doi:10.1016/j.neuroimage.2012.01.021 pmid:22248573

    CrossRefPubMedWeb of Science
14. 14.↵
    2. Martin AR,
    3. De Leener B,
    4. Cohen-Adad J, et al

    . Clinically feasible microstructural MRI to quantify cervical spinal cord tissue injury using DTI, MT, and T2*-weighted imaging: assessment of normative data and reliability. AJNR Am J Neuroradiol 2017;38:1257–65 doi:10.3174/ajnr.A5163 pmid:28428213

    Abstract/FREE Full Text
15. 15.↵
    2. McCoy DB,
    3. Talbott JF,
    4. Wilson M, et al

    . MRI atlas-based measurement of spinal cord injury predicts outcome in acute flaccid myelitis. AJNR Am J Neuroradiol 2017;38:410–17 doi:10.3174/ajnr.A5044 pmid:27979798

    Abstract/FREE Full Text
16. 16.↵
    2. De Leener B,
    3. Kadoury S,
    4. Cohen-Adad J

    . Robust, accurate and fast automatic segmentation of the spinal cord. Neuroimage 2014;98:528–36 doi:10.1016/j.neuroimage.2014.04.051 pmid:24780696

    CrossRefPubMed
17. 17.↵
    2. De Leener B,
    3. Cohen-Adad J,
    4. Kadoury S

    . Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling. IEEE Trans Med Imaging 2015;34:1705–18 doi:10.1109/TMI.2015.2437192 pmid:26011879

    CrossRefPubMed
18. 18.↵
    2. Gros C,
    3. De Leener B,
    4. Dupont SM, et al

    . Automatic spinal cord localization, robust to MRI contrasts using global curve optimization. Med Image Anal 2018;44:215–27 doi:10.1016/j.media.2017.12.001 pmid:29288983

    CrossRefPubMed
19. 19.↵
    The R Core Team. R: a language and environment for statistical computing. 2013. https://www.researchgate.net/publication/221943918_R_A_Language_And_Environment_for_Statistical_Computing_Reference_Index_2152. Accessed on January 11, 2018.
20. 20.↵
    1. Navab N,
    2. Hornegger J,
    3. Wells WM, et al.

    2. Ronneberger O,
    3. Fischer P,
    4. Brox T

    . U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, et al., eds. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany. October 5–9, 2015;234–41
21. 21.↵
    2. Nair V,
    3. Hinton GE

    . Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel. June 21–24, 2010; 807–14
22. 22.↵
    2. Srivastava N,
    3. Hinton G,
    4. Krizhevsky A, et al

    . Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 2014;15:1929–58

    CrossRef
23. 23.↵
    2. Kinga D,
    3. Adam JB

    . A method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations, San Diego, California. May 7–9, 2015
24. 24.↵
    2. Ioffe S,
    3. Szegedy C

    . Batch normalization: accelerating deep network training by reducing internal covariate shift. 2015. https://arxiv.org/abs/1502.03167. Accessed on January 11, 2018.
25. 25.↵
    2. Sukhbaatar S,
    3. Bruna J,
    4. Paluri M, et al

    . Training Convolutional Networks with Noisy Labels. 2014. https://arxiv.org/abs/1406.2080. Accessed on January 11, 2018.
26. 26.↵
    2. Dice R

    . Measures of the amount of ecologic association between species. Ecology 1945;26:297–302 doi:10.2307/1932409

    CrossRefWeb of Science
27. 27.↵
    2. Zou KH1,
    3. Warfield SK,
    4. Bharatha A, et al

    . Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2004;11:178–89 pmid:14974593

    CrossRefPubMedWeb of Science
28. 28.↵
    2. Gros C,
    3. De Leener B,
    4. Badji A, et al

    . Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks. Neuroimage 2019;184:901–15 doi:10.1016/j.neuroimage.2018.09.081 pmid:30300751

    CrossRefPubMed
29. 29.↵
    2. Haefeli J,
    3. Mabray MC,
    4. Whetstone WD, et al

    . Multivariate analysis of MRI biomarkers for predicting neurologic impairment in cervical spinal cord injury. AJNR Am J Neuroradiol 2017;38:648–55 doi:10.3174/ajnr.A5021 pmid:28007771

    Abstract/FREE Full Text
30. 30.↵
    2. Pandit P,
    3. Talbott JF,
    4. Pedoia V, et al

    . T1ρ and T2 -based characterization of regional variations in intervertebral discs to detect early degenerative changes. J Orthop Res 2016;34:1373–81 doi:10.1002/jor.23311 pmid:27227485

    CrossRefPubMed
31. 31.↵
    2. Shah LM,
    3. Ross JS

    . Imaging of spine trauma. Neurosurgery 2016;79:626–42 doi:10.1227/NEU.0000000000001336 pmid:27404215

    CrossRefPubMed
32. 32.↵
    2. Martin AR,
    3. Aleksanderek I,
    4. Cohen-Adad J, et al

    . Translating state-of-the-art spinal cord MRI techniques to clinical use: a systematic review of clinical studies utilizing DTI, MT, MWF, MRS, and fMRI. Neuroimage Clin 2016;10:192–238 doi:10.1016/j.nicl.2015.11.019 pmid:26862478

    CrossRefPubMed
33. 33.↵
    2. McCoy D,
    3. Huie R,
    4. Dupont S, et al

    . Atlas-based volumetric assessment of T2 abnormality in acute spinal cord injury predicts motor outcomes: a transforming research and clinical knowledge in SCI (TRACK-SCI) pilot study. In: Proceedings of the International Society of Magnetic Resonance in Medicine, Paris, France. June 16–21, 2018
34. 34.↵
    2. Gillies RJ,
    3. Kinahan ,
    4. Hricak H

    . Radiomics: images are more than pictures, they are data. Radiology 2016;278:563–77 doi:10.1148/radiol.2015151169 pmid:26579733

    CrossRefPubMed