A 2D Compact ultrasound computerized tomography (UCT) system is developed. Fully automatic post-processing tools involving signal and image processing are developed as well. Square of the amplitude values are used in transmission mode with natural 1.5 MHz frequency and rise time 10.4 ns and fall time 8.4 ns and duty cycle of 4.32%. The highest peak to corresponding trough values are considered as transmitting wave between transducers in direct line talk. Sensitivity analysis of methods to extract peak to the corresponding trough per transducer are discussed in this paper. Total five methods are tested. These methods are taken from broad categories: (a) Conventional and (b) Artificial Intelligence (AI) based methods. Conventional methods, namely: (a) simple gradient based peak detection, (b) Fourier based, (c) wavelet transform, are compared with AI based methods: (a) support vector machine (SVM), (b) artificial neural network (ANN). The classification step is performed as well to discard the signal which does not has a contribution to the transmission wave. It is found that AI methods have equally good as compared to conventional methods. Reconstruction error, KT 1error estimates, accuracy, F-Score, recall, precision, specificity and MCC are used. ANN and FFT methods are processing the UCT signal with the best recovery.

开发了二维紧凑型超声计算机断层扫描 (UCT) 系统。还开发了涉及信号和图像处理的全自动后处理工具。振幅值的平方用于传输模式，自然频率为 1.5 MHz，上升时间为 10.4 ns，下降时间为 8.4 ns，占空比为 4.32%。对应波谷值的最高峰值被认为是直线通话中换能器之间的传输波。本文讨论了提取每个换能器对应波谷的峰值的方法的灵敏度分析。总共测试了五种方法。这些方法来自广泛的类别：(a) 传统和 (b) 基于人工智能 (AI) 的方法。常规方法，即：（a）基于简单梯度的峰值检测，（b）基于傅立叶的，（c）小波变换，与基于 AI 的方法进行比较：（a）支持向量机（SVM），（b）人工神经网络（ANN）。还执行分类步骤以丢弃对传输波没有贡献的信号。研究发现，与传统方法相比，人工智能方法具有同样的优势。使用了重建误差、KT 1error 估计、准确度、F-Score、召回率、精确度、特异性和 MCC。ANN 和 FFT 方法正在以最佳恢复处理 UCT 信号。使用召回、精确度、特异性和 MCC。ANN 和 FFT 方法正在以最佳恢复处理 UCT 信号。使用召回、精确度、特异性和 MCC。ANN 和 FFT 方法正在以最佳恢复处理 UCT 信号。