Abstract
Biomechanical and clinical gait research observes muscles and tendons in limbs to study their functions and behaviour. Therefore, movements of distinct anatomical landmarks, such as muscle-tendon junctions, are frequently measured. We propose a reliable and time efficient machine-learning approach to track these junctions in ultrasound videos and support clinical biomechanists in gait analysis. In order to facilitate this process, a method based on deep-learning was introduced. We gathered an extensive dataset, covering 3 functional movements, 2 muscles, collected on 123 healthy and 38 impaired subjects with 3 different ultrasound systems, and providing a total of 66864 annotated ultrasound images in our network training. Furthermore, we used data collected across independent laboratories and curated by researchers with varying levels of experience. For the evaluation of our method a diverse test-set was selected that is independently verified by four specialists. We show that our model achieves similar performance scores to the four human specialists in identifying the muscle-tendon junction position. Our method provides time-efficient tracking of muscle-tendon junctions, with prediction times of up to 0.078 seconds per frame (approx. 100 times faster than manual labeling). All our codes, trained models and test-set were made publicly available and our model is provided as a free-to-use online service on https://deepmtj.org/.
Highlights
Biomechanical and clinical gait research observes muscles and tendons in limbs to study their functions and behaviour
We found that the training was performed with a pixelwise loss, the neural network provided similar probability maps to the ground-truth labels
To account for label noise introduced by our algorithm, as well as by inter-observer variability, we identified three errorcase scenarios
Summary
D URING human locomotion, muscle-tendon complexes of lower limbs are under cyclic concentric and eccentric stress [7]. Krupenevich et al [18] focused their work on the trackability of MTJs across several isometric movements and complex functional tasks such as walking They trained a MobileNetV2 [34] architecture on 1200 manually annotated ground truth labels, collected from 15 subjects that were walking, with a Telemed US system (Telemed UAB, Vilnius, Lithuania). These newly emerging machine-learning applications for MTJ tracking show that deep neural networks provide strong performance in identifying the exact MTJ positions in US images, even for small training datasets, and independent of subjects and movements.
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.
