A deep learning pipeline for identification of motor units in musculoskeletal ultrasound
(2020) In IEEE Access 8. p.170595-170608- Abstract
Skeletal muscles are functionally regulated by populations of so-called motor units (MUs). An MU comprises a bundle of muscle fibers controlled by a neuron from the spinal cord. Current methods to diagnose neuromuscular diseases and monitor rehabilitation, and study sports sciences rely on recording and analyzing the bio-electric activity of the MUs. However, these methods provide information from a limited part of a muscle. Ultrasound imaging provides information from a large part of the muscle. It has recently been shown that ultrafast ultrasound imaging can be used to record and analyze the mechanical response of individual MUs using blind source separation. In this work, we present an alternative method - a deep learning pipeline -... (More)
Skeletal muscles are functionally regulated by populations of so-called motor units (MUs). An MU comprises a bundle of muscle fibers controlled by a neuron from the spinal cord. Current methods to diagnose neuromuscular diseases and monitor rehabilitation, and study sports sciences rely on recording and analyzing the bio-electric activity of the MUs. However, these methods provide information from a limited part of a muscle. Ultrasound imaging provides information from a large part of the muscle. It has recently been shown that ultrafast ultrasound imaging can be used to record and analyze the mechanical response of individual MUs using blind source separation. In this work, we present an alternative method - a deep learning pipeline - to identify active MUs in ultrasound image sequences, including segmentation of their territories and signal estimation of their mechanical responses (twitch train). We train and evaluate the model using simulated data mimicking the complex activation pattern of tens of activated MUs with overlapping territories and partially synchronized activation patterns. Using a slow fusion approach (based on 3D CNNs), we transform the spatiotemporal image sequence data to 2D representations and apply a deep neural network architecture for segmentation. Next, we employ a second deep neural network architecture for signal estimation. The results show that the proposed pipeline can effectively identify individual MUs, estimate their territories, and estimate their twitch train signal at low contraction forces. The framework can retain spatio-temporal consistencies and information of the mechanical response of MU activity even when the ultrasound image sequences are transformed into a 2D representation for compatibility with more traditional computer vision and image processing techniques. The proposed pipeline is potentially useful to identify simultaneously active MUs in whole muscles in ultrasound image sequences of voluntary skeletal muscle contractions at low force levels.
(Less)
- author
- Ali, Hazrat ; Umander, Johannes ; Rohlén, Robin LU and Grönlund, Christer
- publishing date
- 2020
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Decomposition, Deep learning, Mechanical response, Medical imaging, Motor unit, Neural networks, Recurrent neural networks, Ultrafast ultrasound
- in
- IEEE Access
- volume
- 8
- pages
- 14 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85102796911
- ISSN
- 2169-3536
- DOI
- 10.1109/ACCESS.2020.3023495
- language
- English
- LU publication?
- no
- additional info
- Funding Information: This work was supported in part by the Swedish Research Council under Grant dnr 2015-04461, and in part by the Kempe Foundations under Grant dnr JCK-1115 and Grant SMK-1868. Publisher Copyright: © 2020 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.
- id
- cc1593b4-d175-438e-98c3-67073c074c67
- date added to LUP
- 2023-05-16 00:03:10
- date last changed
- 2023-06-13 11:21:05
@article{cc1593b4-d175-438e-98c3-67073c074c67, abstract = {{<p>Skeletal muscles are functionally regulated by populations of so-called motor units (MUs). An MU comprises a bundle of muscle fibers controlled by a neuron from the spinal cord. Current methods to diagnose neuromuscular diseases and monitor rehabilitation, and study sports sciences rely on recording and analyzing the bio-electric activity of the MUs. However, these methods provide information from a limited part of a muscle. Ultrasound imaging provides information from a large part of the muscle. It has recently been shown that ultrafast ultrasound imaging can be used to record and analyze the mechanical response of individual MUs using blind source separation. In this work, we present an alternative method - a deep learning pipeline - to identify active MUs in ultrasound image sequences, including segmentation of their territories and signal estimation of their mechanical responses (twitch train). We train and evaluate the model using simulated data mimicking the complex activation pattern of tens of activated MUs with overlapping territories and partially synchronized activation patterns. Using a slow fusion approach (based on 3D CNNs), we transform the spatiotemporal image sequence data to 2D representations and apply a deep neural network architecture for segmentation. Next, we employ a second deep neural network architecture for signal estimation. The results show that the proposed pipeline can effectively identify individual MUs, estimate their territories, and estimate their twitch train signal at low contraction forces. The framework can retain spatio-temporal consistencies and information of the mechanical response of MU activity even when the ultrasound image sequences are transformed into a 2D representation for compatibility with more traditional computer vision and image processing techniques. The proposed pipeline is potentially useful to identify simultaneously active MUs in whole muscles in ultrasound image sequences of voluntary skeletal muscle contractions at low force levels.</p>}}, author = {{Ali, Hazrat and Umander, Johannes and Rohlén, Robin and Grönlund, Christer}}, issn = {{2169-3536}}, keywords = {{Decomposition; Deep learning; Mechanical response; Medical imaging; Motor unit; Neural networks; Recurrent neural networks; Ultrafast ultrasound}}, language = {{eng}}, pages = {{170595--170608}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Access}}, title = {{A deep learning pipeline for identification of motor units in musculoskeletal ultrasound}}, url = {{http://dx.doi.org/10.1109/ACCESS.2020.3023495}}, doi = {{10.1109/ACCESS.2020.3023495}}, volume = {{8}}, year = {{2020}}, }