Format

Send to

Choose Destination
Sci Rep. 2019 May 28;9(1):7973. doi: 10.1038/s41598-019-44416-8.

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

Author information

1
Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, USA. kenweber@stanford.edu.
2
School of Physical Therapy, Regis University, Denver, CO, USA.
3
Department of Physical Therapy and Human Movement Sciences, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA.
4
Systems Neuroscience and Pain Lab, Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Palo Alto, CA, USA.
5
Department of Radiology, Neuroradiology Section, Stanford University, Palo Alto, CA, USA.
6
Statistics Department, Stanford University, Palo Alto, CA, USA.
7
Department of Radiology, Northwestern University, Chicago, IL, USA.
8
Honorary Senior Fellow, School of Health and Rehabilitation Sciences, The University of Queensland, Queensland, Australia.
9
Northern Sydney Local Health District, The Kolling Research Institute and The Faculty of Health Sciences, The University of Sydney, St. Leonards, NSW, Australia.

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.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center