Literature DB >> 33991901

Automated analysis of medial gastrocnemius muscle-tendon junction displacements in heathy young adults during isolated contractions and walking using deep neural networks.

Rebecca L Krupenevich1, Callum J Funk2, Jason R Franz2.   

Abstract

BACKGROUND AND
OBJECTIVE: Direct measurement of muscle-tendon junction (MTJ) position is important for understanding dynamic tendon behavior and muscle-tendon interaction in healthy and pathological populations. Traditionally, obtaining MTJ position during functional activities is accomplished by manually tracking the position of the MTJ in cine B-mode ultrasound images - a laborious and time-consuming process. Recent advances in deep learning have facilitated the availability of user-friendly open-source software packages for automated tracking. However, these software packages were originally intended for animal pose estimation and have not been widely tested on ultrasound images. Therefore, the purpose of this paper was to evaluate the efficacy of deep neural networks to accurately track medial gastrocnemius MTJ positions in cine B-mode ultrasound images across tasks spanning controlled loading during isolated contractions to physiological loading during treadmill walking.
METHODS: Cine B-mode ultrasound images of the medial gastrocnemius MTJ were collected from 15 subjects (6M/9F, 23 yr, 71.9 kg, 1.8 m) during treadmill walking at 1.25 m/s and during maximal voluntary isometric plantarflexor contractions (MVICs). Five deep neural networks were trained using 480 manually-labeled images collected during walking, defined as the ground truth, and were then used to predict MTJ position in images from novel subjects: 1) during walking (novel-subject) and 2) during MVICs (novel-condition).
RESULTS: We found an average mean absolute error of 1.26±1.30 mm and 2.61±3.31 mm between the ground truth and predicted MTJ positions in the novel-subject and novel-condition evaluations, respectively.
CONCLUSIONS: Our results provide support for the use of open-source software for creating deep neural networks to reliably track MTJ positions in B-mode ultrasound images. We believe this approach to MTJ position tracking is an accessible and time-saving solution, with broad applications for many fields, such as rehabilitation or clinical diagnostics.
Copyright © 2021. Published by Elsevier B.V.

Entities:  

Keywords:  Ankle; Deep learning; Gait; Plantarflexor; Ultrasound

Mesh:

Year:  2021        PMID: 33991901      PMCID: PMC8223120          DOI: 10.1016/j.cmpb.2021.106120

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   7.027


  21 in total

1.  Deficits in heel-rise height and achilles tendon elongation occur in patients recovering from an Achilles tendon rupture.

Authors:  Karin Grävare Silbernagel; Robert Steele; Kurt Manal
Journal:  Am J Sports Med       Date:  2012-05-16       Impact factor: 6.202

2.  An algorithm for automated analysis of ultrasound images to measure tendon excursion in vivo.

Authors:  Sabrina S M Lee; Gregory S Lewis; Stephen J Piazza
Journal:  J Appl Biomech       Date:  2008-02       Impact factor: 1.833

3.  Medial gastrocnemius and soleus muscle-tendon unit, fascicle, and tendon interaction during walking in children with cerebral palsy.

Authors:  Lee Barber; Chris Carty; Luca Modenese; John Walsh; Roslyn Boyd; Glen Lichtwark
Journal:  Dev Med Child Neurol       Date:  2017-04-01       Impact factor: 5.449

Review 4.  A unified perspective on ankle push-off in human walking.

Authors:  Karl E Zelik; Peter G Adamczyk
Journal:  J Exp Biol       Date:  2016-12-01       Impact factor: 3.312

5.  The Acute Effects of Static and Cyclic Stretching on Muscle Stiffness and Hardness of Medial Gastrocnemius Muscle.

Authors:  Noriaki Maeda; Yukio Urabe; Shogo Tsutsumi; Shogo Sakai; Hironori Fujishita; Toshiki Kobayashi; Makoto Asaeda; Kazuhiko Hirata; Yukio Mikami; Hiroaki Kimura
Journal:  J Sports Sci Med       Date:  2017-12-01       Impact factor: 2.988

6.  Ultrasound characterization of medial gastrocnemius tissue composition in children with spastic cerebral palsy.

Authors:  Christian A Pitcher; Catherine M Elliott; Fausto A Panizzolo; Jane P Valentine; Katherine Stannage; Siobhán L Reid
Journal:  Muscle Nerve       Date:  2015-06-18       Impact factor: 3.217

7.  DeepLabCut: markerless pose estimation of user-defined body parts with deep learning.

Authors:  Alexander Mathis; Pranav Mamidanna; Kevin M Cury; Taiga Abe; Venkatesh N Murthy; Mackenzie Weygandt Mathis; Matthias Bethge
Journal:  Nat Neurosci       Date:  2018-08-20       Impact factor: 24.884

8.  The mechanism for efficacy of eccentric loading in Achilles tendon injury; an in vivo study in humans.

Authors:  J D Rees; G A Lichtwark; R L Wolman; A M Wilson
Journal:  Rheumatology (Oxford)       Date:  2008-07-22       Impact factor: 7.580

9.  An automatic fascicle tracking algorithm quantifying gastrocnemius architecture during maximal effort contractions.

Authors:  John F Drazan; Todd J Hullfish; Josh R Baxter
Journal:  PeerJ       Date:  2019-07-02       Impact factor: 2.984

10.  Simple Muscle Architecture Analysis (SMA): An ImageJ macro tool to automate measurements in B-mode ultrasound scans.

Authors:  Olivier R Seynnes; Neil J Cronin
Journal:  PLoS One       Date:  2020-02-12       Impact factor: 3.240

View more
  2 in total

1.  Moving outside the lab: Markerless motion capture accurately quantifies sagittal plane kinematics during the vertical jump.

Authors:  John F Drazan; William T Phillips; Nidhi Seethapathi; Todd J Hullfish; Josh R Baxter
Journal:  J Biomech       Date:  2021-06-13       Impact factor: 2.789

2.  Manual and semi-automatic determination of elbow angle-independent parameters for a model of the biceps brachii distal tendon based on ultrasonic imaging.

Authors:  Malte Mechtenberg; Nils Grimmelsmann; Hanno Gerd Meyer; Axel Schneider
Journal:  PLoS One       Date:  2022-10-06       Impact factor: 3.752

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.