IEEE Trans Ultrason Ferroelectr Freq Control. 2020 Nov;67(11):2218-2229. doi: 10.1109/TUFFC.2020.3016092. Epub 2020 Aug 12.
In this article, we present a novel method for line artifacts quantification in lung ultrasound (LUS) images of COVID-19 patients. We formulate this as a nonconvex regularization problem involving a sparsity-enforcing, Cauchy-based penalty function, and the inverse Radon transform. We employ a simple local maxima detection technique in the Radon transform domain, associated with known clinical definitions of line artifacts. Despite being nonconvex, the proposed technique is guaranteed to convergence through our proposed Cauchy proximal splitting (CPS) method, and accurately identifies both horizontal and vertical line artifacts in LUS images. To reduce the number of false and missed detection, our method includes a two-stage validation mechanism, which is performed in both Radon and image domains. We evaluate the performance of the proposed method in comparison to the current state-of-the-art B-line identification method, and show a considerable performance gain with 87% correctly detected B-lines in LUS images of nine COVID-19 patients.
在本文中，我们提出了一种新的方法，用于量化 COVID-19 患者肺部超声（LUS）图像中的线伪影。我们将其表述为一个涉及稀疏约束、基于柯西的惩罚函数以及逆 Radon 变换的非凸正则化问题。我们在 Radon 变换域中使用了一种简单的局部极大值检测技术，并结合了已知的线伪影临床定义。尽管是非凸的，但通过我们提出的柯西近端分裂（CPS）方法，所提出的技术保证能够收敛，并在 LUS 图像中准确识别水平和垂直的线伪影。为了减少误报和漏报，我们的方法包括一个在 Radon 和图像域中执行的两阶段验证机制。我们将所提出的方法与当前最先进的 B 线识别方法进行了性能评估，并在 9 名 COVID-19 患者的 LUS 图像中显示了 87%的 B 线正确检测，性能有了显著提高。
