SIRC-UNet: Improving Bone Tracking Precision of A-mode Ultrasound by Decoding Hierarchical Resolution Features

A-mode ultrasound has not been widely used in medical applications compared to B-mode ultrasound. The primary reason is that the data representation, being 1-D, is less intuitive for users and harder to interpret. However, A-mode ultrasound has several advantageous features, such as faster data acquisition for real-time sensing, direct distance measurement from raw RF data, and a smaller size. Traditionally, A-mode ultrasound has been used to measure biometric distance. However, current distance measurement algorithms are crude, mostly relying on conventional signal processing for peak detection. When the tracking task is under dynamic conditions, it becomes challenging to maintain high accuracy and robustness. In this study, we introduced a deep-learning framework to enhance A-mode ultrasound's bone tracking reliability and accuracy under dynamic conditions. The proposed sampling-based increased resolution cascaded UNet (SIRC-UNet) was designed to enhance the perceptual resolution of 1-D signal, allowing for accurate analysis of A-mode's RF data and leading to more precise peak detection. The method was evaluated by analyzing bias between peak locations from the prediction and the ground truth and analyzing the capability of distinguishing bone peaks from other irrelevant peaks. The results demonstrated that our method could perform real-time high-precision (submillimeter accuracy) bone measurements in one cadaver experiment. It showcased the potential to provide accurate dynamic bone tracking and bone position detection, with the possibility to extend applications to surgical robots and rehabilitation exoskeletons, where real-time bone tracking is crucial.