The reliable assessment of muscle states, such as contracted muscles vs. non-contracted muscles or relaxed muscles vs. fatigue muscles, is crucial in many sports and rehabilitation scenarios, such as the assessment of therapeutic measures. The goal of this work was to deploy machine learning (ML) models based on one-dimensional (1-D) sonomyography (SMG) signals to facilitate low-cost and wearable ultrasound devices. One-dimensional SMG is a non-invasive technique using 1-D ultrasound radio-frequency signals to measure muscle states and has the advantage of being able to acquire information from deep soft tissue layers. To mimic real-life scenarios, we did not emphasize the acquisition of particularly distinct signals. The ML models exploited muscle contraction signals of eight volunteers and muscle fatigue signals of 21 volunteers. We evaluated them with different schemes on a variety of data types, such as unprocessed or processed raw signals and found that comparatively simple ML models, such as Support Vector Machines or Logistic Regression, yielded the best performance w.r.t. accuracy and evaluation time. We conclude that our framework for muscle contraction and muscle fatigue classifications is very well-suited to facilitate low-cost and wearable devices based on ML models using 1-D SMG.

X-ray imaging, based on ionizing radiation, can be used to determine bone age by examining distal growth plate fusion in the ulna and radius bones. Legal age determination approaches based on ultrasound signals exist but are unsuitable to reliably determine bone age. We present a low-cost, mobile system that uses one-dimensional ultrasound radio frequency signals to obtain a robust binary classifier enabling the determination of bone age from data of girls and women aged 9 to 24 years. These data were acquired as part of a clinical study conducted with 148 subjects. Our system detects the presence or absence of the epiphyseal plate by moving ultrasound array transducers along the forearm, measuring reflection and transmission signals. Even though classical digital signal processing methods did not achieve a robust classifier, we achieved an ${\mathrm{F}}_1$ score of approximately 87% for binary classification of completed bone growth with machine learning approaches, such as the gradient boosting machine method CatBoost. We demonstrate that our ultrasound system can classify the fusion of the distal growth plate of the radius bone and the completion of bone growth with high accuracy. We propose a non-ionizing alternative to established X-ray imaging methods for this purpose.

Being able to distinguish non-invasively between different muscle states is crucial for rehabilitation and sports athletes alike. The analysis of muscle activities is often performed using optical systems, kinetic approaches or surface electromyography. However, these methods can only obtain information from the body surface. In this work, raw ultrasound radio frequency data is used for muscle state classifications as this method provides information from deeper muscle layers. A setup to classify muscle contractions with artificial neural networks and traditional time series analysis algorithms is presented. Experiments with the pulser-receiver Olympus 5800PR and Panametrics transducers were performed to obtain A-scans from the calves of healthy volunteers. Dimensionality reduction techniques, such as (Kernel-) Principal Component Analysis and t-Distributed Stochastic Neighbor Embedding were applied, which provide information about the distribution of A-scans belonging to relaxed and contracted muscle states. A comparison of different ML methods is presented with average F1 scores of up to 89 % after appropriate post-processing for muscle contraction classifications and average F1 scores of up to 76 % for muscle fatigue state classifications. We conclude that low-cost ultrasound measurements can be used for reliable muscle activity tracking. More data is expected to result in even more robust future solutions.

Human trafficking for the purpose of sexual exploitation is a problem worldwide and the proportion of underage victims is significant. To identify the minority of a person, the measurement of bone age using X-ray imaging is the gold-standard procedure. Beside several technical and judicial problems like radiation, this technique still requires medical diagnosis and limits the acceptance and practicability. Existing ultrasound systems for bone age determination evaluate changes of speed of sound through bone showing unreliable results for majority determining. In this work a mobile ultrasound system for the purpose of fast and reliable majority determination is developed and clinically evaluated using machine learning for classification without the need of a physician trained for age determination. In women, the complete fusion of the distal growth plate in ulna and radius bones correlates with reaching the age of 18. The existence of this growth plate is measured using the developed mobile multichannel ultrasound system. Its main parts are a low cost and low power FPGA, a fully integrated 8 channel transceiver and a WIFI module for data transfer to a mobile device. A pair of ultrasound array transducers (4 elements with 11x11 mm aperture each, 1 MHz center frequency) is positioned and moved up to 15 mm for reflection and transmission measurements through the forearm resulting in measurements of multiple paths through an existing growth plate leading to more robust results. The detection of growth plate existence was done using machine learning approaches. Different types of artificial neural nets were used. The system has been evaluated successfully in a clinical study with 149 women at Saarland University Medical Center. Classical signal processing analyzing the change of ultrasound signals during transducer movement over the growth plate showed that a difference between underage and legal age women is contained in the data, but classification had to be done using machine learning methods. The best performance for binary majority classification was achieved using a ResNet with an F1 score of approximately 84 % showing the capabilities of the setup. Currently, a multi-center study started to increase the number of data used for training the artificial neural nets, improving these results further while adapting the technology even to male subject groups.

Being aware of the correct execution of certain fitness exercises (e.g. squats) is important for rehabilitation and sports athletes alike. Thus, being able to noninvasively distinguish between contracted and relaxed muscle states is crucial. Measurements using optical systems (movement tracking) or kinetic approaches (muscle circumference) only provide information from the body surface with varying accuracy.