Material parameters (such as elastic coefficient, bone thickness and so on) are important indicators of long cortical bone health. To overcome the limitations of the ultrasonic parameter extraction method for long cortical bone in the dispersive domain (for example high-precision extraction of dispersive curve is difficult, and multi-parameter optimization solution is complex), Intelligent Medical Ultrasound Lab proposed a deep learning based method to extract the material parameters of long cortical bone. The finite-difference time-domain (FDTD) method was performed to obtain the array signals of the simulated ultrasonic guided waves (UGWs) for training the multichannel crossed convolutional neural network (MCC-CNN), which can directly extract the long cortical bone material parameters from the experimental UGW data. The MCC-CNN avoided the dispersive trajectory extraction and the complicated process of the optimization solution for multiple parameters. The method provided a new data-driven scheme for multi-parameter extraction of long cortical bone, which can provide comprehensive assessment for the elasticity and thickness of long cortical bone.

The relevant research was published inIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Controlin April, 2021, with the title of“Deep Learning Analysis of Ultrasonic Guided Waves for Cortical Bone Characterization”. Doctor Yifang Li is the first author, and the Young Researcher Kailiang Xu and Professor Dean Ta are the corresponding authors. This work was supported in part by the National Natural Science Foundation of China under Grant 11974081, Grant 11827808, and Grant 11804056; in part by the National Science Fund for Distinguished Young Scholars of China under Grant 11525416; in part by the Program of Shanghai Academic Research Leader under Grant 19XD1400500; in part by the Natural Science Foundation of Shanghai under Grant 19ZR1402700; in part by the Shanghai Municipal Science and Technology Major Project under Grant 2017SHZDZX01; in part by the State Key Laboratory of ASIC and System Project under Grant 2018MS004; and in part by the Shanghai Rising Star Program under Grant 20QC1400200.(Yifang Li, Kailiang Xu*, Ying Li, Feng Xu, Dean Ta*, and Weiqi Wang, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2021, 68(4), 935-951)