A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images

• Published in: IEEE transactions on biomedical engineering Vol. 69; no. 6; pp. 1920 - 1930
• Main Authors: Leitner, Christoph, Jarolim, Robert, Englmair, Bernhard, Kruse, Annika, Hernandez, Karen Andrea Lara, Konrad, Andreas, Su, Eric Yung-Sheng, Schrottner, Jorg, Kelly, Luke A., Lichtwark, Glen A., Tilp, Markus, Baumgartner, Christian
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: anatomical landmark detection; Attention mechanism; Biomechanics; convolutional neural network; Deep learning; domain generalization; feature extraction; Gait; Instruments; Junctions; label noise; Learning algorithms; locomotion; Machine learning; Muscles; myotendinous junction; probability map; segmentation; sequential learning; soft labeling; Tendons; Test sets; Tracking; Training; U-net; Ultrasonic imaging; Ultrasound; Videos
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2021.3130548

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/ .