B-mode ultrasound (US) is often used to noninvasively measure skeletal muscle architecture, which contains human intent information. Extracted features from B-mode images can help improve closed-loop human–robotic interaction control when using rehabilitation/assistive devices. The traditional manual approach to inferring the muscle structural features from US images is laborious, time-consuming, and subjective among different investigators. This paper proposes a clustering-based detection method that can mimic a well-trained human expert in identifying fascicle and aponeurosis and, therefore, compute the pennation angle. The clustering-based architecture assumes that muscle fibers have tubular characteristics. It is robust for low-frequency image streams. We compared the proposed algorithm to two mature benchmark techniques: UltraTrack and ImageJ. The performance of the proposed approach showed higher accuracy in our dataset (frame frequency is 20 Hz), that is, similar to the human expert. The proposed method shows promising potential in automatic muscle fascicle orientation detection to facilitate implementations in biomechanics modeling, rehabilitation robot control design, and neuromuscular disease diagnosis with low-frequency data stream.

Electrical muscle stimulation (EMS) is widely used in rehabilitation and athletic training to generate involuntary muscle contractions. However, EMS leads to rapid muscle fatigue, limiting the force a muscle can produce during prolonged use. Currently available methods to monitor localized muscle fatigue and recovery are generally not compatible with EMS. The purpose of this study was to examine whether Doppler ultrasound imaging can assess changes in stimulated muscle twitches that are related to muscle fatigue from electrical stimulation. We stimulated five isometric muscle twitches in the medial and lateral gastrocnemius of 13 healthy subjects before and after a fatiguing EMS protocol. Tissue Doppler imaging of the medial gastrocnemius recorded muscle tissue velocities during each twitch. Features of the average muscle tissue velocity waveforms changed immediately after the fatiguing stimulation protocol (peak velocity: -38%, p = .022; time-to-zero velocity: +8%, p = .050). As the fatigued muscle recovered, the features of the average tissue velocity waveforms showed a return towards their baseline values similar to that of the normalized ankle torque. We also found that features of the average tissue velocity waveform could significantly predict the ankle twitch torque for each participant (R2 = 0.255–0.849, p < .001). Our results provide evidence that Doppler ultrasound imaging can detect changes in muscle tissue during isometric muscle twitch that are related to muscle fatigue, fatigue recovery, and the generated joint torque. Tissue Doppler imaging may be a feasible method to monitor localized muscle fatigue during EMS in a wearable device.

Robotic assistive or rehabilitative devices are promising aids for people with neurological disorders as they help regain normative functions for both upper and lower limbs. However, it remains challenging to accurately estimate human intent or residual efforts non-invasively when using these robotic devices. In this article, we propose a deep learning approach that uses a brightness mode, that is, B-mode, of ultrasound (US) imaging from skeletal muscles to predict the ankle joint net plantarflexion moment while walking. The designed structure of customized deep convolutional neural networks (CNNs) guarantees the convergence and robustness of the deep learning approach. We investigated the influence of the US imaging’s region of interest (ROI) on the net plantarflexion moment prediction performance. We also compared the CNN-based moment prediction performance utilizing B-mode US and sEMG spectrum imaging with the same ROI size. Experimental results from eight young participants walking on a treadmill at multiple speeds verified an improved accuracy by using the proposed US imaging + deep learning approach for net joint moment prediction. With the same CNN structure, compared to the prediction performance by using sEMG spectrum imaging, US imaging significantly reduced the normalized prediction root mean square error by 37.55% ($ p $ < .001) and increased the prediction coefficient of determination by 20.13% ($ p $ < .001). The findings show that the US imaging + deep learning approach personalizes the assessment of human joint voluntary effort, which can be incorporated with assistive or rehabilitative devices to improve clinical performance based on the assist-as-needed control strategy.