Analysis of combined clinical and diffusion basis spectrum imaging metrics to predict the outcome of chronic cervical spondylotic myelopathy following cervical decompression surgery

Dinal JayasekeraDepartment of Biomedical Engineering, Washington University in St. Louis McKelvey School of Engineering, St. Louis;

Search for other papers by Dinal Jayasekera in
jns
Google Scholar
PubMed
Close
 MS
,
Justin K. ZhangDepartment of Neurosurgery, Washington University School of Medicine, St. Louis;

Search for other papers by Justin K. Zhang in
jns
Google Scholar
PubMed
Close
 BS
,
Jacob BlumDepartment of Radiology, Washington University School of Medicine, St. Louis, Missouri;

Search for other papers by Jacob Blum in
jns
Google Scholar
PubMed
Close
 BA
,
Rachel JakesDepartment of Biomedical Engineering, Case School of Engineering, Cleveland, Ohio; and

Search for other papers by Rachel Jakes in
jns
Google Scholar
PubMed
Close
 BS
,
Peng SunDepartment of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas

Search for other papers by Peng Sun in
jns
Google Scholar
PubMed
Close
 PhD
,
Saad JaveedDepartment of Neurosurgery, Washington University School of Medicine, St. Louis;

Search for other papers by Saad Javeed in
jns
Google Scholar
PubMed
Close
 MD
,
Jacob K. GreenbergDepartment of Neurosurgery, Washington University School of Medicine, St. Louis;

Search for other papers by Jacob K. Greenberg in
jns
Google Scholar
PubMed
Close
 MD, MSCI
,
Sheng-Kwei SongDepartment of Radiology, Washington University School of Medicine, St. Louis, Missouri;

Search for other papers by Sheng-Kwei Song in
jns
Google Scholar
PubMed
Close
 PhD
, and
Wilson Z. RayDepartment of Biomedical Engineering, Washington University in St. Louis McKelvey School of Engineering, St. Louis;
Department of Neurosurgery, Washington University School of Medicine, St. Louis;

Search for other papers by Wilson Z. Ray in
jns
Google Scholar
PubMed
Close
 MD
Restricted access

Purchase Now

USD  $45.00

Spine - 1 year subscription bundle (Individuals Only)

USD  $376.00

JNS + Pediatrics + Spine - 1 year subscription bundle (Individuals Only)

USD  $612.00
USD  $45.00
USD  $376.00
USD  $612.00
Print or Print + Online Sign in

OBJECTIVE

Cervical spondylotic myelopathy (CSM) is the most common cause of chronic spinal cord injury, a significant public health problem. Diffusion tensor imaging (DTI) is a neuroimaging technique widely used to assess CNS tissue pathology and is increasingly used in CSM. However, DTI lacks the needed accuracy, precision, and recall to image pathologies of spinal cord injury as the disease progresses. Thus, the authors used diffusion basis spectrum imaging (DBSI) to delineate white matter injury more accurately in the setting of spinal cord compression. It was hypothesized that the profiles of multiple DBSI metrics can serve as imaging outcome predictors to accurately predict a patient’s response to therapy and his or her long-term prognosis. This hypothesis was tested by using DBSI metrics as input features in a support vector machine (SVM) algorithm.

METHODS

Fifty patients with CSM and 20 healthy controls were recruited to receive diffusion-weighted MRI examinations. All spinal cord white matter was identified as the region of interest (ROI). DBSI and DTI metrics were extracted from all voxels in the ROI and the median value of each patient was used in analyses. An SVM with optimized hyperparameters was trained using clinical and imaging metrics separately and collectively to predict patient outcomes. Patient outcomes were determined by calculating changes between pre- and postoperative modified Japanese Orthopaedic Association (mJOA) scale scores.

RESULTS

Accuracy, precision, recall, and F1 score were reported for each SVM iteration. The highest performance was observed when a combination of clinical and DBSI metrics was used to train an SVM. When assessing patient outcomes using mJOA scale scores, the SVM trained with clinical and DBSI metrics achieved accuracy and an area under the curve of 88.1% and 0.95, compared with 66.7% and 0.65, respectively, when clinical and DTI metrics were used together.

CONCLUSIONS

The accuracy and efficacy of the SVM incorporating clinical and DBSI metrics show promise for clinical applications in predicting patient outcomes. These results suggest that DBSI metrics, along with the clinical presentation, could serve as a surrogate in prognosticating outcomes of patients with CSM.

ABBREVIATIONS

ACDF = anterior cervical decompression and fusion; ADC = apparent diffusion coefficient; AUC = area under the curve; CI = confidence interval; CSM = cervical spondylotic myelopathy; DASH = Disabilities of the Arm, Shoulder, and Hand; DBSI = diffusion basis spectrum imaging; DTI = diffusion tensor imaging; DWI = diffusion-weighted imaging; FN = false negative; FOV = field of view; FP = false positive; HC = healthy control; MCS = mental component summary; MDI = Myelopathy Disability Index; MEDIC = multi-echo data image combination; mJOA = modified Japanese Orthopaedic Association; NDI = Neck Disability Index; OR = odds ratio; PCDF = posterior cervical decompression and fusion; PCS = physical component summary; PRC = precision-recall curve; ROC = receiver operating characteristic; ROI = region of interest; SF-36 = 36-item Short-Form Health Survey; SVM = support vector machine; TN = true negative; TP = true positive.
  • Collapse
  • Expand

Images from de Andrada Pereira et al. (pp 525–534).

  • 1

    Boogaarts HD, Bartels RHMA. Prevalence of cervical spondylotic myelopathy. Eur Spine J. 2015;24(Suppl 2):139141.

  • 2

    Kadaňka Z, Bednarík J, Vohánka S, et al. Conservative treatment versus surgery in spondylotic cervical myelopathy: a prospective randomised study. Eur Spine J. 2000;9(6):538544.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 3

    Lebl DR, Hughes A, Cammisa FP Jr, O’Leary PF. Cervical spondylotic myelopathy: pathophysiology, clinical presentation, and treatment. HSS J. 2011;7(2):170178.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 4

    Nouri A, Tetreault L, Singh A, Karadimas SK, Fehlings MG. Degenerative cervical myelopathy: epidemiology, genetics, and pathogenesis. Spine (Phila Pa 1976). 2015;40(12):E675E693.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 5

    Last AR, Hulbert K. Chronic low back pain: evaluation and management. Am Fam Physician. 2009;79(12):10671074.

  • 6

    Inglese M, Makani S, Johnson G, et al. Diffuse axonal injury in mild traumatic brain injury: a diffusion tensor imaging study. J Neurosurg. 2005;103(2):298303.

  • 7

    Niogi SN, Mukherjee P. Diffusion tensor imaging of mild traumatic brain injury. J Head Trauma Rehabil. 2010;25(4):241255.

  • 8

    Shanmuganathan K, Gullapalli RP, Zhuo J, Mirvis SE. Diffusion tensor MR imaging in cervical spine trauma. AJNR Am J Neuroradiol. 2008;29(4):655659.

  • 9

    Xu J, Shimony JS, Klawiter EC, et al. Improved in vivo diffusion tensor imaging of human cervical spinal cord. Neuroimage. 2013;67:6476.

  • 10

    Wang K, Chen Z, Zhang F, et al. Evaluation of DTI parameter ratios and diffusion tensor tractography grading in the diagnosis and prognosis prediction of cervical spondylotic myelopathy. Spine (Phila Pa 1976). 2017;42(4):E202E210.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 11

    Murphy RKJ, Sun P, Xu J, et al. Magnetic resonance imaging biomarker of axon loss reflects cervical spondylotic myelopathy severity. Spine (Phila Pa 1976). 2016;41(9):751756.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 12

    Song SK, Sun SW, Ramsbottom MJ, Chang C, Russell J, Cross AH. Dysmyelination revealed through MRI as increased radial (but unchanged axial) diffusion of water. Neuroimage. 2002;17(3):14291436.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 13

    Song SK, Sun SW, Ju WK, Lin SJ, Cross AH, Neufeld AH. Diffusion tensor imaging detects and differentiates axon and myelin degeneration in mouse optic nerve after retinal ischemia. Neuroimage. 2003;20(3):17141722.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 14

    Song SK, Yoshino J, Le TQ, et al. Demyelination increases radial diffusivity in corpus callosum of mouse brain. Neuroimage. 2005;26(1):132140.

  • 15

    Cross AH, Song SK. A new imaging modality to non-invasively assess multiple sclerosis pathology. J Neuroimmunol. 2017;304:8185.

  • 16

    Wang Y, Wang Q, Haldar JP, et al. Quantification of increased cellularity during inflammatory demyelination. Brain. 2011;134(Pt 12):35903601.

  • 17

    Murphy RKJ, Sun P, Han RH, et al. Fractional anisotropy to quantify cervical spondylotic myelopathy severity. J Neurosurg Sci. 2018;62(4):406412.

  • 18

    Kalsi-Ryan S, Singh A, Massicotte EM, et al. Ancillary outcome measures for assessment of individuals with cervical spondylotic myelopathy. Spine (Phila Pa 1976). 2013;38(22 Suppl 1):S111S122.

    • Search Google Scholar
    • Export Citation
  • 19

    Bzdok D, Altman N, Krzywinski M. Statistics versus machine learning. Nat Methods. 2018;15(4):233234.

  • 20

    Lötsch J, Ultsch A. Machine learning in pain research. Pain. 2018;159(4):623630.

  • 21

    Kopjar B, Tetreault L, Kalsi-Ryan S, Fehlings M. Psychometric properties of the modified Japanese Orthopaedic Association scale in patients with cervical spondylotic myelopathy. Spine (Phila Pa 1976). 2015;40(1):E23E28.

    • Search Google Scholar
    • Export Citation
  • 22

    Tetreault L, Kopjar B, Nouri A, et al. The modified Japanese Orthopaedic Association scale: establishing criteria for mild, moderate and severe impairment in patients with degenerative cervical myelopathy. Eur Spine J. 2017;26(1):7884.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 23

    Fehlings MG, Tetreault LA, Riew KD, et al. A clinical practice guideline for the management of patients with degenerative cervical myelopathy: recommendations for patients with mild, moderate, and severe disease and nonmyelopathic patients with evidence of cord compression. Global Spine J. 2017;7(3 Suppl):70S83S.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 24

    Tetreault L, Wilson JR, Kotter MRN, et al. Predicting the minimum clinically important difference in patients undergoing surgery for the treatment of degenerative cervical myelopathy. Neurosurg Focus. 2016;40(6):E14.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 25

    Soroceanu A, Smith JS, Lau D, et al. Establishing the minimum clinically important difference in Neck Disability Index and modified Japanese Orthopaedic Association scores for adult cervical deformity. J Neurosurg Spine. 2020;33(4):441445.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 26

    Wang X, Cusick MF, Wang Y, et al. Diffusion basis spectrum imaging detects and distinguishes coexisting subclinical inflammation, demyelination and axonal injury in experimental autoimmune encephalomyelitis mice. NMR Biomed. 2014;27(7):843852.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 27

    Chiang CW, Wang Y, Sun P, et al. Quantifying white matter tract diffusion parameters in the presence of increased extra-fiber cellularity and vasogenic edema. Neuroimage. 2014;101:310319.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 28

    De Leener B, Lévy S, Dupont SM, et al. SCT: Spinal Cord Toolbox, an open-source software for processing spinal cord MRI data. Neuroimage. 2017;145(Pt A):2443.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 29

    Avants BB, Tustison NJ, Song G, Cook PA, Klein A, Gee JC. A reproducible evaluation of ANTs similarity metric performance in brain image registration. Neuroimage. 2011;54(3):20332044.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 30

    Arslan AK, Colak C, Sarihan ME. Different medical data mining approaches based prediction of ischemic stroke. Comput Methods Programs Biomed. 2016;130:8792.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 31

    Abraham A, Pedregosa F, Eickenberg M, et al. Machine learning for neuroimaging with scikit-learn. Front Neuroinform. 2014;8:14.

  • 32

    Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:28252830.

  • 33

    Ozenne B, Subtil F, Maucort-Boulch D. The precision–recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J Clin Epidemiol. 2015;68(8):855859.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 34

    Karpova A, Arun R, Davis AM, et al. Predictors of surgical outcome in cervical spondylotic myelopathy. Spine (Phila Pa 1976). 2013;38(5):392400.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 35

    Demir A, Ries M, Moonen CTW, et al. Diffusion-weighted MR imaging with apparent diffusion coefficient and apparent diffusion tensor maps in cervical spondylotic myelopathy. Radiology. 2003;229(1):3743.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 36

    Shabani S, Kaushal M, Budde MD, Wang MC, Kurpad SN. Diffusion tensor imaging in cervical spondylotic myelopathy: a review. J Neurosurg Spine. 2020;33(1):6572.

    • Search Google Scholar
    • Export Citation
  • 37

    Jones JGA, Cen SY, Lebel RM, Hsieh PC, Law M. Diffusion tensor imaging correlates with the clinical assessment of disease severity in cervical spondylotic myelopathy and predicts outcome following surgery. AJNR Am J Neuroradiol. 2013;34(2):471478.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 38

    Rao A, Soliman H, Kaushal M, et al. Diffusion tensor imaging in a large longitudinal series of patients with cervical spondylotic myelopathy correlated with long-term functional outcome. Neurosurgery. 2018;83(4):753760.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 39

    Khan O, Badhiwala JH, Akbar MA, Fehlings MG. Prediction of worse functional status after surgery for degenerative cervical myelopathy: a machine learning approach. Neurosurgery. 2021;88(3):584591.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 40

    Fehlings MG, Ibrahim A, Tetreault L, et al. A global perspective on the outcomes of surgical decompression in patients with cervical spondylotic myelopathy: results from the prospective multicenter AOSpine international study on 479 patients. Spine (Phila Pa 1976). 2015;40(17):1322-1328.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 41

    Fehlings MG, Barry S, Kopjar B, et al. Anterior versus posterior surgical approaches to treat cervical spondylotic myelopathy: outcomes of the prospective multicenter AOSpine North America CSM study in 264 patients. Spine (Phila Pa 1976). 2013;38(26):22472252.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 42

    Ghogawala Z, Terrin N, Dunbar MR, et al. Effect of ventral vs dorsal spinal surgery on patient-reported physical functioning in patients with cervical spondylotic myelopathy: a randomized clinical trial. JAMA. 2021;325(10):942951.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 43

    Merali ZG, Witiw CD, Badhiwala JH, Wilson JR, Fehlings MG. Using a machine learning approach to predict outcome after surgery for degenerative cervical myelopathy. PLoS One. 2019;14(4):e0215133.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation
  • 44

    Shabani S, Kaushal M, Budde M, Schmit B, Wang MC, Kurpad S. Comparison between quantitative measurements of diffusion tensor imaging and T2 signal intensity in a large series of cervical spondylotic myelopathy patients for assessment of disease severity and prognostication of recovery. J Neurosurg Spine. 2019;31(4):473479.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • 45

    Tetreault LA, Côté P, Kopjar B, Arnold P, Fehlings MG. A clinical prediction model to assess surgical outcome in patients with cervical spondylotic myelopathy: internal and external validations using the prospective multicenter AOSpine North American and international datasets of 743 patients. Spine J. 2015;15(3):388397.

    • Crossref
    • PubMed
    • Search Google Scholar
    • Export Citation

Metrics

All Time Past Year Past 30 Days
Abstract Views 1260 1260 40
Full Text Views 303 303 9
PDF Downloads 282 282 11
EPUB Downloads 0 0 0