Zhang Ling, Chen Siping, Chin Chien Ting, Wang Tianfu, Li Shengli
Department of Biomedical Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China.
Med Phys. 2012 Aug;39(8):5015-27. doi: 10.1118/1.4736415.
To assist radiologists and decrease interobserver variability when using 2D ultrasonography (US) to locate the standardized plane of early gestational sac (SPGS) and to perform gestational sac (GS) biometric measurements.
In this paper, the authors report the design of the first automatic solution, called "intelligent scanning" (IS), for selecting SPGS and performing biometric measurements using real-time 2D US. First, the GS is efficiently and precisely located in each ultrasound frame by exploiting a coarse to fine detection scheme based on the training of two cascade AdaBoost classifiers. Next, the SPGS are automatically selected by eliminating false positives. This is accomplished using local context information based on the relative position of anatomies in the image sequence. Finally, a database-guided multiscale normalized cuts algorithm is proposed to generate the initial contour of the GS, based on which the GS is automatically segmented for measurement by a modified snake model.
This system was validated on 31 ultrasound videos involving 31 pregnant volunteers. The differences between system performance and radiologist performance with respect to SPGS selection and length and depth (diameter) measurements are 7.5% ± 5.0%, 5.5% ± 5.2%, and 6.5% ± 4.6%, respectively. Additional validations prove that the IS precision is in the range of interobserver variability. Our system can display the SPGS along with biometric measurements in approximately three seconds after the video ends, when using a 1.9 GHz dual-core computer.
IS of the GS from 2D real-time US is a practical, reproducible, and reliable approach.
在使用二维超声（US）定位早期妊娠囊标准化平面（SPGS）并进行妊娠囊（GS）生物测量时，辅助放射科医生并减少观察者间的变异性。
在本文中，作者报告了首个自动解决方案“智能扫描”（IS）的设计，该方案用于使用实时二维超声选择SPGS并进行生物测量。首先，通过基于两个级联AdaBoost分类器训练的从粗到细的检测方案，在每个超声帧中高效且精确地定位GS。接下来，通过消除误报自动选择SPGS。这是利用基于图像序列中解剖结构相对位置的局部上下文信息来完成的。最后，提出了一种基于数据库引导的多尺度归一化割算法来生成GS的初始轮廓，在此基础上通过改进的蛇形模型对GS进行自动分割以进行测量。
该系统在涉及31名怀孕志愿者的31个超声视频上得到验证。在SPGS选择以及长度和深度（直径）测量方面，系统性能与放射科医生性能之间的差异分别为7.5%±5.0%、5.5%±5.2%和6.5%±4.6%。额外的验证证明IS精度在观察者间变异性范围内。当使用1.9 GHz双核计算机时，我们的系统在视频结束后大约三秒内可以显示SPGS以及生物测量结果。
二维实时超声的GS智能扫描是一种实用、可重复且可靠的方法。
