Abstract
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.
Highlights
Muscular degeneration may have clinical implications for management and rates of recovery from persistent spinal disorders that currently feature high as the world’s most disabling diseases: low back pain and neck pain[18]
convolutional neural network (CNN) segmentation performance was similar at the C3–C4 and C5–C6 vertebral levels where the deep cervical extensor muscle composition and morphometry differs
We demonstrate the feasibility of training a previous CNN model for a novel segmentation task
Summary
Muscular degeneration (as the larger magnitude of MFI might indicate) may have clinical implications for management and rates of recovery from persistent spinal disorders that currently feature high as the world’s most disabling diseases: low back pain (first) and neck pain (fourth)[18]. Manual segmentation methods for MFI do not permit for time-efficient monitoring of these muscles in clinical practice. CNN’s may permit time-efficient quantification of the characteristic MFI observed in disorders of the spine (e.g., DCM, SCI, whiplash, and low back pain) and other musculoskeletal/neuromuscular conditions (e.g., rotator cuff pathology, osteoarthritis, diabetes, and laminopathies)[25]. We trained and tested a CNN for segmentation of the deep cervical spine extensor muscles using high-resolution fat-water Dixon images from participants with whiplash following an MVC. We assessed the association of the automated CNN measures to clinical measures of pain and neck-related disability
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
