Qiu Wu, Yuan Jing, Ukwatta Eranga, Fenster Aaron
Imaging Research Laboratories, Robarts Research Institute, The University of Western Ontario, London, Ontario N64 5K8, Canada.
Department of Biomedical Engineering, Johns Hopkins University, Baltimore, Maryland 21205.
Med Phys. 2015 Feb;42(2):877-91. doi: 10.1118/1.4906129.
Efficient and accurate segmentations of 3D end-firing transrectal ultrasound (TRUS) images play an important role in planning of 3D TRUS guided prostate biopsy. However, poor image quality of the input 3D TRUS images, such as strong imaging artifacts and speckles, often makes it a challenging task to extract the prostate boundaries accurately and efficiently.
In this paper, the authors propose a novel convex optimization-based approach to delineate the prostate surface from a given 3D TRUS image, which reduces the original 3D segmentation problem to a sequence of simple 2D segmentation subproblems over the rotational reslices of the 3D TRUS volume. Essentially, the authors introduce a novel convex relaxation-based contour evolution approach to each 2D slicewise image segmentation with the joint optimization of shape information, where the learned 2D nonlinear statistical shape prior is incorporated to segment the initial slice, its result is propagated as a shape constraint to the segmentation of the following slices. In practice, the proposed segmentation algorithm is implemented on a GPU to achieve the high computational performance.
Experimental results using 30 patient 3D TRUS images show that the proposed method can achieve a mean Dice similarity coefficient of 93.4% ± 2.2% in 20 s for one 3D image, outperforming the existing local-optimization-based methods, e.g., level-set and active-contour, in terms of accuracy and efficiency. In addition, inter- and intraobserver variability experiments show its good reproducibility.
A semiautomatic segmentation approach is proposed and evaluated to extract the prostate boundary from 3D TRUS images acquired by a 3D end-firing TRUS guided prostate biopsy system. Experimental results suggest that it may be suitable for the clinical use involving the image guided prostate biopsy procedures.
高效且准确地分割三维端射式经直肠超声（TRUS）图像在三维TRUS引导下的前列腺活检规划中起着重要作用。然而，输入的三维TRUS图像质量较差，如强烈的成像伪影和斑点，常常使得准确且高效地提取前列腺边界成为一项具有挑战性的任务。
在本文中，作者提出了一种基于凸优化的新颖方法来从给定的三维TRUS图像中描绘前列腺表面，该方法将原始的三维分割问题简化为在三维TRUS体积的旋转重切片上的一系列简单二维分割子问题。本质上，作者为每个二维逐切片图像分割引入了一种基于凸松弛的轮廓演化方法，并联合优化形状信息，其中将学习到的二维非线性统计形状先验纳入初始切片的分割，其结果作为形状约束传播到后续切片的分割。在实践中，所提出的分割算法在图形处理器（GPU）上实现以实现高计算性能。
使用30例患者的三维TRUS图像进行的实验结果表明，所提出的方法对于一幅三维图像在20秒内可实现平均骰子相似系数为93.4%±2.2%，在准确性和效率方面优于现有的基于局部优化的方法，如水平集和活动轮廓法。此外，观察者间和观察者内变异性实验表明了其良好的可重复性。
提出并评估了一种半自动分割方法，以从三维端射式TRUS引导的前列腺活检系统获取的三维TRUS图像中提取前列腺边界。实验结果表明，它可能适用于涉及图像引导前列腺活检程序的临床应用。
