1
|
Liu K, Liu Y, Ji S, Gao C, Fu J. Estimation of Muscle Forces of Lower Limbs Based on CNN-LSTM Neural Network and Wearable Sensor System. SENSORS (BASEL, SWITZERLAND) 2024; 24:1032. [PMID: 38339749 PMCID: PMC10857390 DOI: 10.3390/s24031032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Revised: 01/26/2024] [Accepted: 01/26/2024] [Indexed: 02/12/2024]
Abstract
Estimation of vivo muscle forces during human motion is important for understanding human motion control mechanisms and joint mechanics. This paper combined the advantages of the convolutional neural network (CNN) and long-short-term memory (LSTM) and proposed a novel muscle force estimation method based on CNN-LSTM. A wearable sensor system was also developed to collect the angles and angular velocities of the hip, knee, and ankle joints in the sagittal plane during walking, and the collected kinematic data were used as the input for the neural network model. In this paper, the muscle forces calculated using OpenSim based on the Static Optimization (SO) method were used as the standard value to train the neural network model. Four lower limb muscles of the left leg, including gluteus maximus (GM), rectus femoris (RF), gastrocnemius (GAST), and soleus (SOL), were selected as the studying objects in this paper. The experiment results showed that compared to the standard CNN and the standard LSTM, the CNN-LSTM performed better in muscle forces estimation under slow (1.2 m/s), medium (1.5 m/s), and fast walking speeds (1.8 m/s). The average correlation coefficients between true and estimated values of four muscle forces under slow, medium, and fast walking speeds were 0.9801, 0.9829, and 0.9809, respectively. The average correlation coefficients had smaller fluctuations under different walking speeds, which indicated that the model had good robustness. The external testing experiment showed that the CNN-LSTM also had good generalization. The model performed well when the estimated object was not included in the training sample. This article proposed a convenient method for estimating muscle forces, which could provide theoretical assistance for the quantitative analysis of human motion and muscle injury. The method has established the relationship between joint kinematic signals and muscle forces during walking based on a neural network model; compared to the SO method to calculate muscle forces in OpenSim, it is more convenient and efficient in clinical analysis or engineering applications.
Collapse
Affiliation(s)
- Kun Liu
- School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130000, China; (Y.L.); (S.J.); (C.G.); (J.F.)
| | | | | | | | | |
Collapse
|
2
|
Gaffney BMM, Vandenberg NW, Davis-Wilson HC, Christiansen CL, Roda GF, Schneider G, Johnson T, Stoneback JW. Biomechanical compensations during a stand-to-sit maneuver using transfemoral osseointegrated prostheses: A case series. Clin Biomech (Bristol, Avon) 2022; 98:105715. [PMID: 35839740 DOI: 10.1016/j.clinbiomech.2022.105715] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/20/2021] [Revised: 04/24/2022] [Accepted: 07/05/2022] [Indexed: 02/07/2023]
Abstract
BACKGROUND Patients with transfemoral amputation and socket prostheses are at a heightened risk of developing musculoskeletal overuse injuries, commonly due to altered joint biomechanics. Osseointegrated prostheses, which involve direct anchorage of the prosthesis to the residual limb through a bone anchored prosthesis, are a novel alternative to sockets yet their biomechanical effect is largely unknown. METHODS Four patients scheduled to undergo unilateral transfemoral prosthesis osseointegration completed two data collections (baseline with socket prosthesis and 12-months after prosthesis osseointegration) in which whole-body kinematics and ground reaction forces were collected during stand-to-sit tasks. Trunk, pelvis, and hip kinematics, and the surrounding muscle forces, were calculated using subject-specific musculoskeletal models developed in OpenSim. Peak joint angles and muscle forces were compared between timepoints using Cohen's d effect sizes. FINDINGS Compared to baseline with socket prostheses, patients with osseointegrated prostheses demonstrated reduced lateral trunk bending (d = 1.46), pelvic obliquity (d = 1.09), and rotation (d = 1.77) toward the amputated limb during the stand to sit task. This was accompanied by increased amputated limb hip flexor, abductor, and rotator muscle forces (d> > 0.8). INTERPRETATION Improved lumbopelvic movement patterns and stabilizing muscle forces when using an osseointegrated prosthesis indicate that this novel prosthesis type likely reduces the risk of the development and/or progression of overuse injuries, such as low back pain and osteoarthritis. We attribute the increased muscle hip muscle forces to the increased load transmission between the osseointegrated prosthesis and residual limb, which allows a greater eccentric ability of the amputated limb to control lowering during the stand-to-sit task.
Collapse
Affiliation(s)
- Brecca M M Gaffney
- Department of Mechanical Engineering, University of Colorado Denver, Denver, CO, United States of America; Center for Bioengineering, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America.
| | - Nicholas W Vandenberg
- Department of Mechanical Engineering, University of Colorado Denver, Denver, CO, United States of America
| | - Hope C Davis-Wilson
- Physical Therapy Program, Department of Physical Medicine and Rehabilitation, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America; VA Eastern Colorado Healthcare System, Aurora, CO, United States of America
| | - Cory L Christiansen
- Physical Therapy Program, Department of Physical Medicine and Rehabilitation, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America; VA Eastern Colorado Healthcare System, Aurora, CO, United States of America
| | - Galen F Roda
- Department of Mechanical Engineering, University of Colorado Denver, Denver, CO, United States of America
| | - Gary Schneider
- University of Colorado Hospital, Aurora, CO, United States of America
| | - Tony Johnson
- University of Colorado Hospital, Aurora, CO, United States of America
| | - Jason W Stoneback
- Department of Orthopedics, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America
| |
Collapse
|
3
|
Fougeron N, Bonnet X, Panhelleux B, Rose JL, Rohan PY, Pillet H. Prediction of muscle forces in residual limb during walking: comparison of transfemoral and Gritti–Stokes amputations. Comput Methods Biomech Biomed Engin 2020. [DOI: 10.1080/10255842.2020.1812857] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
Affiliation(s)
- N. Fougeron
- Institut de Biomécanique Humaine Georges Charpak, Arts et Métiers Paristech, Paris, France
- Proteor, Recherche et développement, Dijon, France
| | - X. Bonnet
- Institut de Biomécanique Humaine Georges Charpak, Arts et Métiers Paristech, Paris, France
| | - B. Panhelleux
- Institut de Biomécanique Humaine Georges Charpak, Arts et Métiers Paristech, Paris, France
- Department of Surgery and Cancer, Imperial College London, London, UK
| | - J.-L. Rose
- Proteor, Recherche et développement, Dijon, France
| | - P.-Y. Rohan
- Institut de Biomécanique Humaine Georges Charpak, Arts et Métiers Paristech, Paris, France
| | - H. Pillet
- Institut de Biomécanique Humaine Georges Charpak, Arts et Métiers Paristech, Paris, France
| |
Collapse
|
4
|
Moissenet F, Bélaise C, Piche E, Michaud B, Begon M. An Optimization Method Tracking EMG, Ground Reactions Forces, and Marker Trajectories for Musculo-Tendon Forces Estimation in Equinus Gait. Front Neurorobot 2019; 13:48. [PMID: 31379547 PMCID: PMC6646662 DOI: 10.3389/fnbot.2019.00048] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2019] [Accepted: 06/24/2019] [Indexed: 11/22/2022] Open
Abstract
In the context of neuro-orthopedic pathologies affecting walking and thus patients' quality of life, understanding the mechanisms of gait deviations and identifying the causal motor impairments is of primary importance. Beside other approaches, neuromusculoskeletal simulations may be used to provide insight into this matter. To the best of our knowledge, no computational framework exists in the literature that allows for predictive simulations featuring muscle co-contractions, and the introduction of various types of perturbations during both healthy and pathological gait types. The aim of this preliminary study was to adapt a recently proposed EMG-marker tracking optimization process to a lower limb musculoskeletal model during equinus gait, a multiphase problem with contact forces. The resulting optimization method tracking EMG, ground reactions forces, and marker trajectories allowed an accurate reproduction of joint kinematics (average error of 5.4 ± 3.3 mm for pelvis translations, and 1.9 ± 1.3° for pelvis rotation and joint angles) and ensured good temporal agreement in muscle activity (the concordance between estimated and measured excitations was 76.8 ± 5.3 %) in a relatively fast process (3.88 ± 1.04 h). We have also highlighted that the tracking of ground reaction forces was possible and accurate (average error of 17.3 ± 5.5 N), even without the use of a complex foot-ground contact model.
Collapse
Affiliation(s)
- Florent Moissenet
- Centre National de Rééducation Fonctionnelle et de Réadaptation-Rehazenter, Luxembourg, Luxembourg
| | - Colombe Bélaise
- Laboratory of Simulation and Movement Modeling, School of Kinesiology and Exercise Sciences, Université de Montréal, Montreal, QC, Canada
| | - Elodie Piche
- Laboratory of Simulation and Movement Modeling, School of Kinesiology and Exercise Sciences, Université de Montréal, Montreal, QC, Canada
| | - Benjamin Michaud
- Laboratory of Simulation and Movement Modeling, School of Kinesiology and Exercise Sciences, Université de Montréal, Montreal, QC, Canada.,Sainte-Justine Hospital Research Center, Montreal, QC, Canada
| | - Mickaël Begon
- Laboratory of Simulation and Movement Modeling, School of Kinesiology and Exercise Sciences, Université de Montréal, Montreal, QC, Canada.,Sainte-Justine Hospital Research Center, Montreal, QC, Canada
| |
Collapse
|
5
|
Bélaise C, Michaud B, Dal Maso F, Mombaur K, Begon M. Which data should be tracked in forward-dynamic optimisation to best predict muscle forces in a pathological co-contraction case? J Biomech 2018; 68:99-106. [DOI: 10.1016/j.jbiomech.2017.12.028] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2017] [Revised: 09/25/2017] [Accepted: 12/28/2017] [Indexed: 11/15/2022]
|
6
|
MacIntosh AR, Keir PJ. An open-source model and solution method to predict co-contraction in the finger. Comput Methods Biomech Biomed Engin 2017; 20:1373-1381. [DOI: 10.1080/10255842.2017.1364732] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Affiliation(s)
| | - Peter J. Keir
- Department of Kinesiology, McMaster University, Hamilton, Canada
| |
Collapse
|
7
|
Krašna S, Đorđević S, Hribernik M, Trajkovski A. A Novel Approach to Measuring Muscle Mechanics in Vehicle Collision Conditions. SENSORS (BASEL, SWITZERLAND) 2017; 17:s17061389. [PMID: 28613265 PMCID: PMC5492481 DOI: 10.3390/s17061389] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/20/2017] [Revised: 06/08/2017] [Accepted: 06/09/2017] [Indexed: 06/07/2023]
Abstract
The aim of the study was to evaluate a novel approach to measuring neck muscle load and activity in vehicle collision conditions. A series of sled tests were performed on 10 healthy volunteers at three severity levels to simulate low-severity frontal impacts. Electrical activity-electromyography (EMG)-and muscle mechanical tension was measured bilaterally on the upper trapezius. A novel mechanical contraction (MC) sensor was used to measure the tension on the muscle surface. The neck extensor loads were estimated based on the inverse dynamics approach. The results showed strong linear correlation (Pearson's coefficient = 0.821) between the estimated neck muscle load and the muscle tension measured with the MC sensor. The peak of the estimated neck muscle force delayed 0.2 ± 30.6 ms on average vs. the peak MC sensor signal compared to the average delay of 61.8 ± 37.4 ms vs. the peak EMG signal. The observed differences in EMG and MC sensor collected signals indicate that the MC sensor offers an additional insight into the analysis of the neck muscle load and activity in impact conditions. This approach enables a more detailed assessment of the muscle-tendon complex load of a vehicle occupant in pre-impact and impact conditions.
Collapse
Affiliation(s)
- Simon Krašna
- Faculty of Mechanical Engineering, University of Ljubljana, Aškerčeva cesta 6, 1000 Ljubljana, Slovenia.
| | - Srđan Đorđević
- TMG-BMC d.o.o., Štihova ulica 24, 1000 Ljubljana, Slovenia.
| | - Marija Hribernik
- Faculty of Medicine, University of Ljubljana, Korytkova ulica 2, 1000 Ljubljana, Slovenia.
| | - Ana Trajkovski
- Faculty of Mechanical Engineering, University of Ljubljana, Aškerčeva cesta 6, 1000 Ljubljana, Slovenia.
| |
Collapse
|