A mobile ultrasound system for majority detection

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.