scholarly journals Information from dynamic length changes improves reliability of static ultrasound fascicle length measurements

PeerJ ◽  
2017 ◽  
Vol 5 ◽  
pp. e4164 ◽  
Author(s):  
Jeroen Aeles ◽  
Glen A. Lichtwark ◽  
Sietske Lenchant ◽  
Liesbeth Vanlommel ◽  
Tijs Delabastita ◽  
...  
Keyword(s):  
Length Change ◽  
Medial Gastrocnemius ◽  
Ultrasound Images ◽  
Initial Image ◽  
Fascicle Length ◽  
Mean Squared Errors ◽  
Length Measurements ◽  
Length Changes ◽  
Dynamic Length ◽  
Effectiveness Studies

PurposeVarious strategies for improving reliability of fascicle identification on ultrasound images are used in practice, yet these strategies are untested for effectiveness. Studies suggest that the largest part of differences between fascicle lengths on one image are attributed to the error on the initial image. In this study, we compared reliability results between different strategies.MethodsStatic single-image recordings and image sequence recordings during passive ankle rotations of the medial gastrocnemius were collected. Images were tracked by three different raters. We compared results from uninformed fascicle identification (UFI) and results with information from dynamic length changes, or data-informed tracking (DIT). A second test compared tracking of image sequences of either fascicle shortening (initial-long condition) or fascicle lengthening (initial-short condition).ResultsIntra-class correlations (ICC) were higher for the DIT compared to the UFI, yet yielded similar standard error of measurement (SEM) values. Between the initial-long and initial-short conditions, similar ICC values, coefficients of multiple determination, mean squared errors, offset-corrected mean squared errors and fascicle length change values were found for the DIT, yet with higher SEM values and greater absolute fascicle length differences between raters on the first image in the initial-long condition and on the final image in the initial-short condition.ConclusionsDIT improves reliability of fascicle length measurements, without lower SEM values. Fascicle length on the initial image has no effect on subsequent tracking results. Fascicles on ultrasound images should be identified by a single rater and care should be taken when comparing absolute fascicle lengths between studies.

Gastrocnemius Fascicle Length Changes with Two-Joint Passive Movements

2008 ◽  
Vol 24 (3) ◽  
pp. 252-261 ◽  
Author(s):  
Timothy J. Brindle ◽  
Jeri L. Miller ◽  
Maria K. Lebiedowska ◽  
Steven J. Stanhope
Keyword(s):  
Kinematic Model ◽  
Medial Gastrocnemius ◽  
Ultrasound Images ◽  
Fascicle Length ◽  
Knee Motion ◽  
Lateral Gastrocnemius ◽  
Ankle Motion ◽  
Muscle Fascicle ◽  
Length Changes ◽  
Passive Movements

Predicting muscle fascicle length changes during passive movements may lead to a better understanding of muscle function. The purpose of this study was to experimentally compare fascicle length changes in the gastrocnemius during two-joint passive movements with a previously derived kinematic model based on anatomical measures from a cadaver. The ratio of passive ankle to knee motion was manipulated to generate medial gastrocnemius fascicle elongation and lateral gastrocnemius fascicle shortening. Ultrasound images from both heads of the gastrocnemius fascicles were acquired at 10° knee flexion increments and compared with this kinematic model. Our results suggest that the two-joint kinematic model from which we originally based our knee and ankle movements did not adequately reflect fascicle length changes during any of the movement conditions in this study. From our data, we propose that for every degree of ankle motion the medial and lateral gastrocnemius changes 0.42 mm and 0.96 mm, respectively, whereas changes of 0.14 mm and 0.22 mm are observed for the medial and lateral gastrocnemius, respectively, during knee movements.

scholarly journals Machine Learning to Extract Muscle Fascicle Length Changes from Dynamic Ultrasound Images in Real-Time

2021 ◽  
Author(s):  
Luis G. Rosa ◽  
Jonathan S. Zia ◽  
Omer T. Inan ◽  
Gregory S. Sawicki
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Muscle Length ◽  
Ground Truth ◽  
Length Change ◽  
Fascicle Length ◽  
Automated Tracking ◽  
Direct Training ◽  
Muscle Fascicle ◽  
Length Changes

AbstractBackground and objectiveDynamic muscle fascicle length measurements through B-mode ultrasound have become popular for the non-invasive physiological insights they provide regarding musculoskeletal structure-function. However, current practices typically require time consuming post-processing to track muscle length changes from B-mode images. A real-time measurement tool would not only save processing time but would also help pave the way toward closed-loop applications based on feedback signals driven by in vivo muscle length change patterns. In this paper, we benchmark an approach that combines traditional machine learning (ML) models with B-mode ultrasound recordings to obtain muscle fascicle length changes in real-time. To gauge the utility of this framework for ‘in-the-loop’ applications, we evaluate accuracy of the extracted muscle length change signals against time-series’ derived from a standard, post-hoc automated tracking algorithm.MethodsWe collected B-mode ultrasound data from the soleus muscle of six participants performing five defined ankle motion tasks: (a) seated, constrained ankle plantarflexion, (b) seated, free ankle dorsi/plantarflexion, (c) weight-bearing, calf raises (d) walking, and then a (e) mix. We trained machine learning (ML) models by pairing muscle fascicle lengths obtained from standardized automated tracking software (UltraTrack) with the respective B-mode ultrasound image input to the tracker, frame-by-frame. Then we conducted hyperparameter optimizations for five different ML models using a grid search to find the best performing parameters for a combination of high correlation and low RMSE between ML and UltraTrack processed muscle fascicle length trajectories. Finally, using the global best model/hyperparameter settings, we comprehensively evaluated training-testing outcomes within subject (i.e., train and test on same subject), cross subject (i.e., train on one subject, test on another) and within/direct cross task (i.e., train and test on same subject, but different task).ResultsSupport vector machine (SVM) was the best performing model with an average r = 0.70 ±0.34 and average RMSE = 2.86 ±2.55 mm across all direct training conditions and average r = 0.65 ±0.35 and average RMSE = 3.28 ±2.64 mm when optimized for all cross-participant conditions. Comparisons between ML vs. UltraTrack (i.e., ground truth) tracked muscle fascicle length versus time data indicated that ML tracked images reliably capture the salient qualitative features in ground truth length change data, even when correlation values are on the lower end. Furthermore, in the direct training, calf raises condition, which is most comparable to previous studies validating automated tracking performance during isolated contractions on a dynamometer, our ML approach yielded 0.90 average correlation, in line with other accepted tracking methods in the field.ConclusionsBy combining B-mode ultrasound and classical ML models, we demonstrate it is possible to achieve real-time tracking of human soleus muscle fascicles across a number of functionally relevant contractile conditions. This novel sensing modality paves the way for muscle physiology in-the-loop applications that could be used to modify gait via biofeedback or unlock novel wearable device control techniques that could enable restored or augmented locomotion performance.

scholarly journals Machine learning to extract muscle fascicle length changes from dynamic ultrasound images in real-time

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0246611
Author(s):  
Luis G. Rosa ◽  
Jonathan S. Zia ◽  
Omer T. Inan ◽  
Gregory S. Sawicki
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
Muscle Length ◽  
Ground Truth ◽  
Length Change ◽  
Fascicle Length ◽  
Automated Tracking ◽  
Direct Training ◽  
Muscle Fascicle ◽  
Length Changes

Background and objective Dynamic muscle fascicle length measurements through B-mode ultrasound have become popular for the non-invasive physiological insights they provide regarding musculoskeletal structure-function. However, current practices typically require time consuming post-processing to track muscle length changes from B-mode images. A real-time measurement tool would not only save processing time but would also help pave the way toward closed-loop applications based on feedback signals driven by in vivo muscle length change patterns. In this paper, we benchmark an approach that combines traditional machine learning (ML) models with B-mode ultrasound recordings to obtain muscle fascicle length changes in real-time. To gauge the utility of this framework for ‘in-the-loop’ applications, we evaluate accuracy of the extracted muscle length change signals against time-series’ derived from a standard, post-hoc automated tracking algorithm. Methods We collected B-mode ultrasound data from the soleus muscle of six participants performing five defined ankle motion tasks: (a) seated, constrained ankle plantarflexion, (b) seated, free ankle dorsi/plantarflexion, (c) weight-bearing, calf raises (d) walking, and then a (e) mix. We trained machine learning (ML) models by pairing muscle fascicle lengths obtained from standardized automated tracking software (UltraTrack) with the respective B-mode ultrasound image input to the tracker, frame-by-frame. Then we conducted hyperparameter optimizations for five different ML models using a grid search to find the best performing parameters for a combination of high correlation and low RMSE between ML and UltraTrack processed muscle fascicle length trajectories. Finally, using the global best model/hyperparameter settings, we comprehensively evaluated training-testing outcomes within subject (i.e., train and test on same subject), cross subject (i.e., train on one subject, test on another) and within/direct cross task (i.e., train and test on same subject, but different task). Results Support vector machine (SVM) was the best performing model with an average r = 0.70 ±0.34 and average RMSE = 2.86 ±2.55 mm across all direct training conditions and average r = 0.65 ±0.35 and average RMSE = 3.28 ±2.64 mm when optimized for all cross-participant conditions. Comparisons between ML vs. UltraTrack (i.e., ground truth) tracked muscle fascicle length versus time data indicated that ML tracked images reliably capture the salient qualitative features in ground truth length change data, even when correlation values are on the lower end. Furthermore, in the direct training, calf raises condition, which is most comparable to previous studies validating automated tracking performance during isolated contractions on a dynamometer, our ML approach yielded 0.90 average correlation, in line with other accepted tracking methods in the field. Conclusions By combining B-mode ultrasound and classical ML models, we demonstrate it is possible to achieve real-time tracking of human soleus muscle fascicles across a number of functionally relevant contractile conditions. This novel sensing modality paves the way for muscle physiology in-the-loop applications that could be used to modify gait via biofeedback or unlock novel wearable device control techniques that could enable restored or augmented locomotion performance.

scholarly journals Automatic tracking of medial gastrocnemius fascicle length during human locomotion

2011 ◽  
Vol 111 (5) ◽  
pp. 1491-1496 ◽  
Author(s):  
Neil J. Cronin ◽  
Christopher P. Carty ◽  
Rod S. Barrett ◽  
Glen Lichtwark
Keyword(s):  
Human Error ◽  
Human Locomotion ◽  
Medial Gastrocnemius ◽  
Fascicle Length ◽  
Tracking Method ◽  
Automated Method ◽  
Lower Extremity Muscle ◽  
Muscle Fascicle ◽  
Length Changes ◽  
Level Of Agreement

During human locomotion lower extremity muscle-tendon units undergo cyclic length changes that were previously assumed to be representative of muscle fascicle length changes. Measurements in cats and humans have since revealed that muscle fascicle length changes can be uncoupled from those of the muscle-tendon unit. Ultrasonography is frequently used to estimate fascicle length changes during human locomotion. Fascicle length analysis requires time consuming manual methods that are prone to human error and experimenter bias. To bypass these limitations, we have developed an automatic fascicle tracking method based on the Lucas-Kanade optical flow algorithm with an affine optic flow extension. The aims of this study were to compare gastrocnemius fascicle length changes during locomotion using the automated and manual approaches and to determine the repeatability of the automated approach. Ultrasound was used to examine gastrocnemius fascicle lengths in eight participants walking at 4, 5, 6, and 7 km/h and jogging at 7 km/h on a treadmill. Ground reaction forces and three dimensional kinematics were recorded simultaneously. The level of agreement between methods and the repeatability of the automated method were quantified using the coefficient of multiple correlation (CMC). Regardless of speed, the level of agreement between methods was high, with overall CMC values of 0.90 ± 0.09 (95% CI: 0.86–0.95). Repeatability of the algorithm was also high, with an overall CMC of 0.88 ± 0.08 (95% CI: 0.79–0.96). The automated fascicle tracking method presented here is a robust, reliable, and time-efficient alternative to the manual analysis of muscle fascicle length during gait.

Sign in / Sign up

Export Citation Format

Share Document