Full Waveform Inversion-Based Ultrasound Computed Tomography Acceleration Using Two-Dimensional Convolutional Neural Networks
Full Waveform Inversion-Based Ultrasound Computed Tomography Acceleration Using Two-Dimensional Convolutional Neural Networks
复制标题
使用二维卷积神经网络的基于全波形反演的超声计算机断层扫描加速
DOI：
10.1115/1.4062092
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
He, Jiaze
中科院分区：
文献类型：
--
作者：
Kleman, Christopher;Anwar, Shoaib;Liu, Zhengchun;Gong, Jiaqi;Zhu, Xishi;Yunker, Austin;Kettimuthu, Rajkumar;He, Jiaze
超声计算机断层成像(USCT)因其能够快速扫描和收集感兴趣区域的数据而在无损评估和医学成像方面显示出巨大的前景。然而，现有的方法是在预测的准确性和分析数据的速度之间进行权衡，并且将收集的数据处理成有意义的图像需要时间和计算资源。我们建议开发卷积神经网络(CNN)来加速和增强反演结果，以揭示可能位于感兴趣区域内的潜在结构或异常。为了进行训练，首先使用全波形反转(FWI)技术对超声信号进行单次迭代处理；得到的图像和对应的真实模型分别作为输入和输出。所提出的机器学习方法是基于实现二维CNN来寻找基于偏微分方程组的模型重构反问题的近似解。为了缓解训练数据生成过程中耗时和计算量大的问题，开发了一种基于计算的高性能框架来并行生成训练数据。在推理阶段，首先对采集到的信号进行FWI单次迭代处理；然后由预先训练好的CNN对得到的图像进行处理，瞬时生成最终的输出图像。结果表明，一旦训练完成，CNN可以快速生成预测的波速分布，速度和精度都有显著提高。
Ultrasound computed tomography (USCT) shows great promise in nondestructive evaluation and medical imaging due to its ability to quickly scan and collect data from a region of interest. However, existing approaches are a tradeoff between the accuracy of the prediction and the speed at which the data can be analyzed, and processing the collected data into a meaningful image requires both time and computational resources. We propose to develop convolutional neural networks (CNNs) to accelerate and enhance the inversion results to reveal underlying structures or abnormalities that may be located within the region of interest. For training, the ultrasonic signals were first processed using the full waveform inversion (FWI) technique for only a single iteration; the resulting image and the corresponding true model were used as the input and output, respectively. The proposed machine learning approach is based on implementing two-dimensional CNNs to find an approximate solution to the inverse problem of a partial differential equation-based model reconstruction. To alleviate the time-consuming and computationally intensive data generation process, a high-performance computing-based framework has been developed to generate the training data in parallel. At the inference stage, the acquired signals will be first processed by FWI for a single iteration; then the resulting image will be processed by a pre-trained CNN to instantaneously generate the final output image. The results showed that once trained, the CNNs can quickly generate the predicted wave speed distributions with significantly enhanced speed and accuracy.