Ultrasound Sensor Data Enhancement via Hybrid Deep Learning Approaches

This paper proposes a new approach to improve acoustic imaging. This involves the use of a Convolutional Neural Network (CNN) approach applied to ultrasound data. This method is then compared with an approach using only the inverse Discrete Cosine Transform (iDCT), by modifying the number of sources and the Signal-to-Noise Ratio (SNR) and estimating the performances in terms of detection of the sources. The results show an interest of this Machine Learning approach to improve detection and visibility in acoustic imaging.