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

Krupenevich, Rebecca L.; Funk, Callum J.; Franz, Jason R.

doi:10.1016/j.cmpb.2021.106120

Cited by 11 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared our model to recent MTJ tracking algorithms by computing RMSE for each method based on our test-set. We considered the semi-supervised computer vision algorithm from Cenni et al [16] and deep-learning approaches from Leitner et al [17] and Krupenevich et al [18]. For the algorithm of Cenni et al MTJ positions in the first frame of each video are needed to start predictions.…”

Section: Comparison With Other Mtj Trackersmentioning

confidence: 99%

“…Therefore, we used the reference labels P S x1,i,y1,i of the first video frame, from the i th video file in the test-set, to mark starting positions for optical flow calculations. MTJ trackers from Leitner et al [17] and Krupenevich et al [18] are based on CNN architectures. We used their provided trained models for predictions on our test-set.…”

Section: Comparison With Other Mtj Trackersmentioning

confidence: 99%

“…To investigate tissue behaviour in lower limbs (e.g., the triceps surae muscle tendon unit) and to distinguish between individual contributions of muscles and tendons, their junctions are usually visualized using ultrasound (US) imaging (Fig. 1) while their displacements are tracked with various methods [14]- [18]. The triceps surae (Fig.…”

Section: Introductionmentioning

confidence: 99%

“…They found that an inclusion of healthy and impaired patients into the training dataset improved overall performance of their model. 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).…”

Section: Introductionmentioning

confidence: 99%

“…using data from machines of different vendors) often cause significant performance impairments. In case of the proposed MTJ tracker by Leitner et al [17] and Krupenevich et al [18], evaluation and training dataset come from the same US instrument. Therefore, these networks might fail to provide similar performance on datasets obtained from other US machine types.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Leitner,

Jarolim,

Englmair

et al. 2022

Preprint

View full text Add to dashboard Cite

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/.

show abstract

Section: Comparison With Other Mtj Trackersmentioning

confidence: 99%

Section: Comparison With Other Mtj Trackersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Leitner,

Jarolim,

Englmair

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

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

Drazan

Phillips

Seethapathi

et al. 2021

Journal of Biomechanics

View full text Add to dashboard Cite

A Hybrid Method for Ultrasound-Based Tracking of Skeletal Muscle Architecture

Verheul

Yeo

2022

Preprint

View full text Add to dashboard Cite

Tracking skeletal muscle architecture using B-mode ultra-sound is a widely used method in the field of human movement science and biomechanics. Sequential methods based on optical flow algorithms allow for smooth and coherent muscle tracking but are known to drift over time. Non-sequential feature detection methods on the other hand, do not suffer from drift, but are limited to tracking only lower-dimensional features. They are also known to be sensitive to image noise, and therefore often result in highly irregular tracking patterns. Building on the complimentary nature of both approaches, we present a novel fully automated hybrid muscle tracking approach that combines a sequential feature-point tracking method and a non-sequential method based on Hough transform. Tibialis anterior fascicle pennation angle and length, and central aponeurosis displacement, were measured in five healthy individuals during isometric contractions at five different ankle angles. Our hybrid method was demonstrated to significantly (p < 0.001) reduce drift compared to two sequential methods, and curve irregularity was significantly (p < 0.001) decreased compared to a non-sequential method. These findings suggest that the proposed hybrid approach can uniquely mitigate drift and irregularity limitation of individual methods used for tracking skeletal muscle architecture. Fully automated muscle tracking allows for convenient analysis of large datasets, whereas automatic drift correction opens the door for tracking muscle architecture in long ultrasound recordings during common movements, such as walking, running, and jumping without the need for manual intervention.

show abstract

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

Cited by 11 publications

References 20 publications

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

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

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

A Hybrid Method for Ultrasound-Based Tracking of Skeletal Muscle Architecture

Contact Info

Product

Resources

About