Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Rosa LG

PROVIDER: S-EPMC8153491 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundFunctional magnetic resonance imaging (fMRI) provides critical information about the neurophysiology of the central nervous systems (CNS), posing clinical significance for the understanding of neuropathologies and advancement of rehabilitation. Typical fMRI study designs include subjects performing designed motor tasks within specific time frames, in which fMRI data are then analyzed by assuming that observed functional brain activations correspond to the designed tasks. Therefore, developing MRI-compatible sensors that enable real-time monitoring of subjects' task performances would allow for highly accurate fMRI studies. While several MRI-compatible sensors have been developed, none have demonstrated the ability to measure individual muscle fascicle length during fMRI, which could help uncover the complexities of the peripheral and central nervous systems. Furthermore, previous MRI-compatible sensors have been focused on biologically intact populations, limiting accessibility to populations such as those who have undergone amputation.MethodsWe propose a lightweight, low-cost, skin impedance-insensitive pressure-based muscular motion sensor (pMMS) that provides reliable estimates of muscle fascicle length and joint angle. The muscular motions are captured through measured pressure changes in an air pocket wrapped around the muscle of interest, corresponding to its muscular motion. The muscle fascicle length and joint angle are then estimated from the measured pressure changes based on the proposed muscle-skin-sensor interaction dynamics. Furthermore, we explore an integration method of multiple pMMS systems to expand the sensor capacity of estimating muscle fascicle length and joint angle. Ultrasound imaging paired with joint encoder measurements are utilized to assess pMMS estimation accuracy of muscle fascicle length in the tibialis anterior (TA) and ankle joint angle, respectively, of five biologically intact subjects.ResultsWe found that a single pMMS sufficiently provides robust and accurate estimations of TA muscle fascicle length and ankle joint angle during dorsiflexion at various speeds and amplitudes. Further, differential pressure readings from two pMMSs, in which each pMMS were proximally and distally placed, were able to mitigate errors due to perturbations, expanding pMMS capacity for muscle fascicle length and ankle joint angle estimation during the full range of plantar flexion and dorsiflexion.ConclusionsOur results from this study demonstrate the feasibility of the pMMS system to further be incorporated in fMRI settings for real-time monitoring of subjects' task performances, allowing sophisticated fMRI study designs.