Deep Learning Convolutional Neural Networks for the Automatic Quantification of Muscle Fat Infiltration Following Whiplash Injury

Muscle fat infiltration (MFI) of the deep cervical spine extensors has been observed in cervical spine conditions using time-consuming and rater-dependent manual techniques. Deep learning convolutional neural network (CNN) models have demonstrated state-of-the-art performance in segmentation tasks. Here, we train and test a CNN for muscle segmentation and automatic MFI calculation using high-resolution fat-water images from 39 participants (26 female, average = 31.7 ± 9.3 years) 3 months post whiplash injury. First, we demonstrate high test reliability and accuracy of the CNN compared to manual segmentation. Then we explore the relationships between CNN muscle volume, CNN MFI, and clinical measures of pain and neck-related disability. Across all participants, we demonstrate that CNN muscle volume was negatively correlated to pain (R = −0.415, p = 0.006) and disability (R = −0.286, p = 0.045), while CNN MFI tended to be positively correlated to disability (R = 0.214, p = 0.105). Additionally, CNN MFI was higher in participants with persisting pain and disability (p = 0.049). Overall, CNN’s may improve the efficiency and objectivity of muscle measures allowing for the quantitative monitoring of muscle properties in disorders of and beyond the cervical spine.

[1]  Örjan Smedby,et al.  An Investigation of Fat Infiltration of the Multifidus Muscle in Patients With Severe Neck Symptoms Associated With Chronic Whiplash-Associated Disorder. , 2016, The Journal of orthopaedic and sports physical therapy.

[2]  I. Pulido-Valdeolivas,et al.  Muscle imaging in laminopathies: Synthesis study identifies meaningful muscles for follow‐up , 2018, Muscle & nerve.

[3]  S. O'Leary,et al.  Morphological changes in the cervical muscles of women with chronic whiplash can be modified with exercise—A pilot study , 2015, Muscle & nerve.

[4]  T. Parrish,et al.  Fatty infiltration of the cervical multifidus musculature and their clinical correlates in spondylotic myelopathy , 2018, Journal of Clinical Neuroscience.

[5]  W. Spitzer,et al.  Scientific monograph of the Quebec Task Force on Whiplash-Associated Disorders: redefining "whiplash" and its management. , 1995, Spine.

[6]  M. Battié,et al.  Association between paraspinal muscle morphology, clinical symptoms and functional status in patients with lumbar spinal stenosis , 2017, European Spine Journal.

[7]  R. Crawford,et al.  Towards defining muscular regions of interest from axial magnetic resonance imaging with anatomical cross-reference: part II - cervical spine musculature , 2018, BMC Musculoskeletal Disorders.

[8]  Pedagógia,et al.  Cross Sectional Study , 2019 .

[9]  Sébastien Ourselin,et al.  Automatic Brain Tumor Segmentation Using Cascaded Anisotropic Convolutional Neural Networks , 2017, BrainLes@MICCAI.

[10]  Alfred Rademaker,et al.  The Rapid and Progressive Degeneration of the Cervical Multifidus in Whiplash: An MRI Study of Fatty Infiltration , 2015, Spine.

[11]  Alan D. Lopez,et al.  Dissonant health transition in the states of Mexico, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2016, The Lancet.

[12]  Hassan Rivaz,et al.  Evaluation of an automated thresholding algorithm for the quantification of paraspinal muscle composition from MRI images , 2017, Biomedical engineering online.

[13]  S. Mior,et al.  The Neck Disability Index: a study of reliability and validity. , 1991, Journal of manipulative and physiological therapeutics.

[14]  J. Kenardy,et al.  The Temporal Development of Fatty Infiltrates in the Neck Muscles Following Whiplash Injury: An Association with Pain and Posttraumatic Stress , 2011, PloS one.

[15]  Bernadette A. Thomas,et al.  Global, regional, and national age–sex specific all-cause and cause-specific mortality for 240 causes of death, 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013 , 2015, The Lancet.

[16]  Statement and Editorial Board , 1995 .

[17]  M. Sterling,et al.  The geography of fatty infiltrates within the cervical multifidus and semispinalis cervicis in individuals with chronic whiplash-associated disorders. , 2015, The Journal of orthopaedic and sports physical therapy.

[18]  Christian S. Perone,et al.  Spinal cord gray matter segmentation using deep dilated convolutions , 2017, Scientific Reports.

[19]  J. Elliott,et al.  Multifidi Muscle Characteristics and Physical Function Among Older Adults With and Without Chronic Low Back Pain. , 2017, Archives of physical medicine and rehabilitation.

[20]  M. Fortin,et al.  Relationship between cervical muscle morphology evaluated by MRI, cervical muscle strength and functional outcomes in patients with degenerative cervical myelopathy. , 2018, Musculoskeletal science & practice.

[21]  J. Elliott,et al.  A reconceptualization of the pain numeric rating scale: Anchors and clinically important differences. , 2018, Journal of hand therapy : official journal of the American Society of Hand Therapists.

[22]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[23]  J. Vissing,et al.  Fat Replacement of Paraspinal Muscles with Aging in Healthy Adults , 2017, Medicine and science in sports and exercise.

[24]  Julien Cohen-Adad,et al.  Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks , 2018, NeuroImage.

[25]  T. Parrish,et al.  Ambulatory function in motor incomplete spinal cord injury: A magnetic resonance imaging study of spinal cord edema and lower extremity muscle morphometry , 2017, Spinal Cord.

[26]  J. Elliott,et al.  Advancements in Imaging Technology: Do They (or Will They) Equate to Advancements in Our Knowledge of Recovery in Whiplash? , 2016, The Journal of orthopaedic and sports physical therapy.

[27]  G. Galloway,et al.  Fatty infiltrate in the cervical extensor muscles is not a feature of chronic, insidious-onset neck pain. , 2008, Clinical radiology.

[28]  James M. Elliott,et al.  Differential Changes in Muscle Composition Exist in Traumatic and Nontraumatic Neck Pain , 2014, Spine.

[29]  W. Dong,et al.  Lasting Effects of a Community-Based Self-Management Intervention for Patients With Type 2 Diabetes in China: Outcomes at 2-Year Follow-up of a Randomized Trial , 2020, Asia-Pacific journal of public health.

[30]  Martin Underwood,et al.  Prevention and treatment of low back pain: evidence, challenges, and promising directions , 2018, The Lancet.

[31]  J. Elliott The Rapid and Progressive Degeneration of Neck Muscles in Whiplash: An MRI Study of Fatty Infiltration , 2015 .

[32]  H. Birnbaum,et al.  Real-world practice patterns, health-care utilization, and costs in patients with low back pain: the long road to guideline-concordant care. , 2011, The spine journal : official journal of the North American Spine Society.

[33]  A. Espeland,et al.  Fat in the lumbar multifidus muscles - predictive value and change following disc prosthesis surgery and multidisciplinary rehabilitation in patients with chronic low back pain and degenerative disc: 2-year follow-up of a randomized trial , 2017, BMC Musculoskeletal Disorders.

[34]  Andrew C. Smith,et al.  Advancing imaging technologies for patients with spinal pain: with a focus on whiplash injury. , 2017, The spine journal : official journal of the North American Spine Society.

[35]  T. Hornby,et al.  Potential associations between chronic whiplash and incomplete spinal cord injury , 2015, Spinal Cord Series and Cases.

[36]  Tine Willems,et al.  Lumbar muscle structure and function in chronic versus recurrent low back pain: a cross-sectional study. , 2017, The spine journal : official journal of the North American Spine Society.

[37]  Parashkev Nachev,et al.  Computer Methods and Programs in Biomedicine NiftyNet: a deep-learning platform for medical imaging , 2022 .

[38]  W. T. Dixon Simple proton spectroscopic imaging. , 1984, Radiology.

[39]  Shaun O'leary Pt,et al.  Morphological changes in the cervical muscles of women with chronic whiplash can be modified with exercise—A pilot study , 2015 .

[40]  Terence Verla,et al.  Back Muscle Morphometry: Effects on Outcomes of Spine Surgery. , 2017, World neurosurgery.

[41]  Julien Cohen-Adad,et al.  Spinal cord grey matter segmentation challenge , 2017, NeuroImage.

[42]  J. West,et al.  The qualitative grading of muscle fat infiltration in whiplash using fat and water magnetic resonance imaging. , 2017, The spine journal : official journal of the North American Spine Society.