Study of Pulse Excitation Modes on UCT Reconstruction

The parametric optimization for the ultrasound computed tomography (UCT) system is introduced. It is hypothesized that the pulse characteristic directly affects the information present in the reconstructed profile. The ultrasound excitation modes based on pulsewidth modifications are studied to estimate the effect on reconstruction quality. Studies show that the pulsewidth affects the response of the transducer, and thus, the reconstruction. The ultrasound scanning parameters, mainly pulsewidth, are assessed and optimally set by an artificial intelligence (AI)-driven process, according to the object without the requirement of a priori information. The optimization study uses a novel intelligent object placement (IOP) procedure to ensure repeatability of the same region of interest (ROI), a key requirement to minimize the error. Kanpur theorem-1 (KT1) is further implemented to evaluate the quality of the acquired projection data and discard inferior-quality data. Scanning results corresponding to homogeneous and heterogeneous phantoms are presented. The image processing step involves a deep-learning model evaluating the dice coefficient for estimating the reconstruction quality if prior information about the inner profile is known or about a classical error estimate otherwise. The model’s segmentation accuracy is 95.72%, and the intersection over union (IoU) score is 0.8842 on the validation dataset. The article also provides valuable insights into the development and low-level control of the system.