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

Abstract

Background 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.

A deep learning method to predict ankle joint moment during walking at different speeds with ultrasound imaging: A framework for assistive devices control

“…However, the significance of the current investigation lies in the potential application to estimate/predict other joints’ mechanical functions, as well as to estimate/predict states generally from individual muscles, given the fact that the information is well encoded in skeletal muscles’ collagen structure and are observable by using US imaging (Cunningham and Loram, 2020). Recent research studies have also applied US imaging + deep (machine) learning to estimate skeletal muscles’ activation levels (Cunningham et al, 2017b; Cunningham and Loram, 2020; Feigin et al, 2020), fascicle length (Rosa et al, 2021), fascicle orientation (Cunningham et al, 2017a), and muscle segmentation (Carneiro and Nascimento, 2013; Zhou et al, 2020).…”

Closing the loop between wearable technology and human biology: A new paradigm for steering neuromuscular form and function

“…Recently, USG was employed to study how bi-lateral ankle exoskeletons influence muscle mechanics during human locomotion, establishing a path toward closed-loop control of wearable robotics based on measured muscle dynamics [29,30]. Automated image processing of B-mode images [31][32][33] is also accelerating toward the possibility for real-time tracking of muscle length and shape changes in vivo [34,35]. Developments in machine learning have enabled automated measurements of muscle architectural properties as well as fascicle length and pennation angle during dynamic contractions [36][37][38].…”

AW-Net

“…Rosa et al [14] proposed a direct prediction approach that estimates the fascicle length from ultrasound images. In this study, the muscle fascicle lengths are first annotated in the images by using UltraTrack [8], a semi-automated software to track muscle fascicles.…”

“…Hence, the annotation process is speeded up but still requires manual initialization and correction. Rosa et al [14] model is then trained using these annotations and images to directly predict the average fascicle length of the visible part of the muscle. However, this model does not give access to other mechanical properties such as the pennation angle and fascicle length distribution.…”