DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning
B-mode ultrasound is commonly used to image musculoskeletal tissues, but one major bottleneck is data analysis. Manual analysis is commonly deployed for assessment of muscle thickness, pennation angle and fascicle length in muscle ultrasonography images. However, manual analysis is somewhat subject...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bern Open Publishing
2023-02-01
|
| Series: | Current Issues in Sport Science |
| Subjects: | |
| Online Access: | https://ciss-journal.org/article/view/9385 |
| _version_ | 1797905376558972928 |
|---|---|
| author | Paul Ritsche Oliver Faude Martino Franchi Taija Finni Olivier Seynnes Neil Cronin |
| author_facet | Paul Ritsche Oliver Faude Martino Franchi Taija Finni Olivier Seynnes Neil Cronin |
| author_sort | Paul Ritsche |
| collection | DOAJ |
| description |
B-mode ultrasound is commonly used to image musculoskeletal tissues, but one major bottleneck is data analysis. Manual analysis is commonly deployed for assessment of muscle thickness, pennation angle and fascicle length in muscle ultrasonography images. However, manual analysis is somewhat subjective, laborious and requires thorough experience. We provide an openly available algorithm (DL_Track) to automatically analyze muscle architectural parameters in ultrasonography images or videos of human lower limb muscles.
We trained two different neural networks (classic U-net [Ronneberger et al., 2021] and U-net with VGG16 [Simonyan & Zisserman, 2015] pretrained encoder) one to detect muscle fascicles and another to detect muscle aponeuroses using a set of labelled musculoskeletal ultrasound images. We included images from four different devices of the vastus lateralis, gastrocnemius medialis, tibilias anterior and soleus. In total, we included 310 images for the fascicle model and 570 images for the aponeuroses model, which we augmented to about 1,700 images per set. Each dataset was randomly split into a training and test set for model training, using a common 80/20 train/test split. We determined the best performing model based on intersection-over-union and loss metrics calculated during model training. We compared neural network predictions on an unseen test set consisting of 35 images to those obtained via manual analysis and two existing semi/automated analysis approaches (SMA and Ultratrack).
Across the set of 35 unseen images, the mean differences between DL_Track and manual analysis were for fascicle length -2.4 mm (95% compatibility interval (CI) = -3.7 to -1.2), for pennation angle 0.6° (-0.2 to 1.4), and for muscle thickness -0.6 mm (-1.2 to 0.002). The corresponding values comparing DL_Track with SMA were for fascicle length 5.2 mm (1.3 to 9.0), for pennation angle -1.4° (-2.6 to -0.4) and for muscle thickness -0.9 mm (-1.5 to -0.3) respectively. ICC values between DL_Track and Ultratrack were 0.19 (0.00 to 0.35) for medial gastrocnemius passive contraction, 0.79 (0.77 to 0.81) for medial gastrocnemius maximal voluntary contraction, 0.88 (0.87 to 0.89) for calf raise, 0.67 (0.07 to 0.86) for medial gastrocnemius during walking, 0.80 (0.79 to 0.82) for tibialis passive plantar and dorsiflexion, and 0.85 (0.83 to 0.86) for tibialis anterior maximum voluntary contraction.
Our method is fully automated and can estimate fascicle length, pennation angle and muscle thickness from single images or videos in multiple superficial muscles. For single images, the method gave results that are in agreement with those produced by SMA or manual analysis. Similarly, for videos, there was overlap between the results produced with Ultratrack and our method. In contrast to Ultratrack, DL_Track analyzes each frame independently of the previous frames, which might explain the observerd variability.
References
Ronneberger, O., Fischer, P., & Brox, T. (2021). U-Net: Convolutional networks for biomedical image segmentation. arXiv. https://doi.org/10.48550/arXiv.1505.04597
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv. https://doi.org/10.48550/arXiv.1409.1556
|
| first_indexed | 2024-04-10T10:04:15Z |
| format | Article |
| id | doaj.art-27451c357ba4450db16993578cd14c75 |
| institution | Directory Open Access Journal |
| issn | 2414-6641 |
| language | English |
| last_indexed | 2024-04-10T10:04:15Z |
| publishDate | 2023-02-01 |
| publisher | Bern Open Publishing |
| record_format | Article |
| series | Current Issues in Sport Science |
| spelling | doaj.art-27451c357ba4450db16993578cd14c752023-02-16T03:15:14ZengBern Open PublishingCurrent Issues in Sport Science2414-66412023-02-018210.36950/2023.2ciss088DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learningPaul Ritsche0Oliver Faude1Martino Franchi2Taija Finni3Olivier Seynnes4Neil Cronin5Department of Sport, Exercise and Health, University of Basel, SwitzerlandDepartment of Sport, Exercise and Health, University of Basel, SwitzerlandDepartment of Biomedical Sciences, University of Padova, Italy Faculty of Sport and Health Sciences, University of Jyväskylä, FinlandDepartment for Physical Performance, Norwegian School of Sport Sciences, NorwayFaculty of Sport and Health Sciences, University of Jyväskylä, Finland & School of Sport & Exercise, University of Gloucestershire, United Kingdom B-mode ultrasound is commonly used to image musculoskeletal tissues, but one major bottleneck is data analysis. Manual analysis is commonly deployed for assessment of muscle thickness, pennation angle and fascicle length in muscle ultrasonography images. However, manual analysis is somewhat subjective, laborious and requires thorough experience. We provide an openly available algorithm (DL_Track) to automatically analyze muscle architectural parameters in ultrasonography images or videos of human lower limb muscles. We trained two different neural networks (classic U-net [Ronneberger et al., 2021] and U-net with VGG16 [Simonyan & Zisserman, 2015] pretrained encoder) one to detect muscle fascicles and another to detect muscle aponeuroses using a set of labelled musculoskeletal ultrasound images. We included images from four different devices of the vastus lateralis, gastrocnemius medialis, tibilias anterior and soleus. In total, we included 310 images for the fascicle model and 570 images for the aponeuroses model, which we augmented to about 1,700 images per set. Each dataset was randomly split into a training and test set for model training, using a common 80/20 train/test split. We determined the best performing model based on intersection-over-union and loss metrics calculated during model training. We compared neural network predictions on an unseen test set consisting of 35 images to those obtained via manual analysis and two existing semi/automated analysis approaches (SMA and Ultratrack). Across the set of 35 unseen images, the mean differences between DL_Track and manual analysis were for fascicle length -2.4 mm (95% compatibility interval (CI) = -3.7 to -1.2), for pennation angle 0.6° (-0.2 to 1.4), and for muscle thickness -0.6 mm (-1.2 to 0.002). The corresponding values comparing DL_Track with SMA were for fascicle length 5.2 mm (1.3 to 9.0), for pennation angle -1.4° (-2.6 to -0.4) and for muscle thickness -0.9 mm (-1.5 to -0.3) respectively. ICC values between DL_Track and Ultratrack were 0.19 (0.00 to 0.35) for medial gastrocnemius passive contraction, 0.79 (0.77 to 0.81) for medial gastrocnemius maximal voluntary contraction, 0.88 (0.87 to 0.89) for calf raise, 0.67 (0.07 to 0.86) for medial gastrocnemius during walking, 0.80 (0.79 to 0.82) for tibialis passive plantar and dorsiflexion, and 0.85 (0.83 to 0.86) for tibialis anterior maximum voluntary contraction. Our method is fully automated and can estimate fascicle length, pennation angle and muscle thickness from single images or videos in multiple superficial muscles. For single images, the method gave results that are in agreement with those produced by SMA or manual analysis. Similarly, for videos, there was overlap between the results produced with Ultratrack and our method. In contrast to Ultratrack, DL_Track analyzes each frame independently of the previous frames, which might explain the observerd variability. References Ronneberger, O., Fischer, P., & Brox, T. (2021). U-Net: Convolutional networks for biomedical image segmentation. arXiv. https://doi.org/10.48550/arXiv.1505.04597 Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv. https://doi.org/10.48550/arXiv.1409.1556 https://ciss-journal.org/article/view/9385ultrasoundU-netconvolutional neural networkmuscle architecture |
| spellingShingle | Paul Ritsche Oliver Faude Martino Franchi Taija Finni Olivier Seynnes Neil Cronin DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning Current Issues in Sport Science ultrasound U-net convolutional neural network muscle architecture |
| title | DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning |
| title_full | DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning |
| title_fullStr | DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning |
| title_full_unstemmed | DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning |
| title_short | DL_Track - Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning |
| title_sort | dl track automated analysis of muscle architecture from b mode ultrasonography images using deep learning |
| topic | ultrasound U-net convolutional neural network muscle architecture |
| url | https://ciss-journal.org/article/view/9385 |
| work_keys_str_mv | AT paulritsche dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning AT oliverfaude dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning AT martinofranchi dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning AT taijafinni dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning AT olivierseynnes dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning AT neilcronin dltrackautomatedanalysisofmusclearchitecturefrombmodeultrasonographyimagesusingdeeplearning |