Chen Xijie, He Miao, Dan Tingting, Wang Nan, Lin Meifang, Zhang Lihe, Xian Jianbo, Cai Hongmin, Xie Hongning
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
Front Neurol. 2020 Jul 17;11:526. doi: 10.3389/fneur.2020.00526. eCollection 2020.
Measurement of the width of fetal lateral ventricles (LVs) in prenatal ultrasound (US) images is essential for antenatal neuronographic assessment. However, the manual measurement of LV width is highly subjective and relies on the clinical experience of scanners. To deal with this challenge, we propose a computer-aided detection framework for automatic measurement of fetal LVs in two-dimensional US images. First, we train a deep convolutional network on 2,400 images of LVs to perform pixel-wise segmentation. Then, the number of pixels per centimeter (PPC), a vital parameter for quantifying the caliper in US images, is obtained via morphological operations guided by prior knowledge. The estimated PPC, upon conversion to a physical length, is used to determine the diameter of the LV by employing the minimum enclosing rectangle method. Extensive experiments on a self-collected dataset demonstrate that the proposed method achieves superior performance over manual measurement, with a mean absolute measurement error of 1.8 mm. The proposed method is fully automatic and is shown to be capable of reducing measurement bias caused by improper US scanning.
产前超声（US）图像中胎儿侧脑室（LVs）宽度的测量对于产前神经影像学评估至关重要。然而，手动测量LV宽度具有高度主观性，且依赖于超声检查人员的临床经验。为应对这一挑战，我们提出了一种计算机辅助检测框架，用于在二维US图像中自动测量胎儿LVs。首先，我们在2400张LVs图像上训练一个深度卷积网络，以进行逐像素分割。然后，通过先验知识引导的形态学操作，获得每厘米像素数（PPC），这是量化US图像中卡尺的一个重要参数。将估计的PPC转换为物理长度后，采用最小外接矩形法来确定LV的直径。在一个自收集数据集上进行的大量实验表明，所提出的方法比手动测量具有更优的性能，平均绝对测量误差为1.8毫米所提出的方法是完全自动的，并且能够减少因US扫描不当引起的测量偏差。
