Unknown

Dataset Information

0

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


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.

SUBMITTER: Weber KA 

PROVIDER: S-EPMC6538618 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

altmetric image

Publications

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

Weber Kenneth A KA   Smith Andrew C AC   Wasielewski Marie M   Eghtesad Kamran K   Upadhyayula Pranav A PA   Wintermark Max M   Hastie Trevor J TJ   Parrish Todd B TB   Mackey Sean S   Elliott James M JM  

Scientific reports 20190528 1


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 wh  ...[more]

Similar Datasets

| S-EPMC7660886 | biostudies-literature
| S-EPMC8309686 | biostudies-literature
| S-EPMC6775245 | biostudies-literature
| S-EPMC7652331 | biostudies-literature
| S-EPMC8170407 | biostudies-literature
| S-EPMC8267174 | biostudies-literature
| S-EPMC7697270 | biostudies-literature
| S-EPMC6010233 | biostudies-other
| S-EPMC5773911 | biostudies-literature
| S-EPMC7266316 | biostudies-literature