Oguz Ipek, Yushkevich Natalie, Pouch Alison, Oguz Baris U, Wang Jiancong, Parameshwaran Shobhana, Gee James, Yushkevich Paul A, Schwartz Nadav
Vanderbilt University, Department of Electrical Engineering and Computer Science, Nashville, Tennessee, United States.
University of Pennsylvania, Penn Image Computing and Science Laboratory, Department of Radiology, Philadelphia, Pennsylvania, United States.
J Med Imaging (Bellingham). 2020 Jan;7(1):014004. doi: 10.1117/1.JMI.7.1.014004. Epub 2020 Feb 22.
: Placental size in early pregnancy has been associated with important clinical outcomes, including fetal growth. However, extraction of placental size from three-dimensional ultrasound (3DUS) requires time-consuming interactive segmentation methods and is prone to user variability. We propose a semiautomated segmentation technique that requires minimal user input to robustly measure placental volume from 3DUS images. : For semiautomated segmentation, a single, central 2D slice was manually annotated to initialize an automated multi-atlas label fusion (MALF) algorithm. The dataset consisted of 47 3DUS volumes obtained at 11 to 14 weeks in singleton pregnancies (28 anterior and 19 posterior). Twenty-six of these subjects were imaged twice within the same session. Dice overlap and surface distance were used to quantify the automated segmentation accuracy compared to expert manual segmentations. The mean placental volume measurements obtained by our method and VOCAL (virtual organ computer-aided analysis), a leading commercial semiautomated method, were compared to the manual reference set. The test-retest reliability was also assessed. : The overlap between our automated segmentation and manual (mean Dice: , median: 0.831) was within the range reported by other methods requiring extensive manual input. The average surface distance was . The correlation coefficient between test-retest volumes was , and the intraclass correlation was . : MALF is a promising method that can allow accurate and reliable segmentation of the placenta with minimal user interaction. Further refinement of this technique may allow for placental biometry to be incorporated into clinical pregnancy surveillance.
孕早期胎盘大小与包括胎儿生长在内的重要临床结局相关。然而，从三维超声（3DUS）中提取胎盘大小需要耗时的交互式分割方法，并且容易受到用户差异的影响。我们提出了一种半自动分割技术，该技术只需最少的用户输入就能从3DUS图像中稳健地测量胎盘体积。
对于半自动分割，手动标注单个中央二维切片以初始化自动多图谱标签融合（MALF）算法。数据集由47例单胎妊娠在11至14周时获得的3DUS容积组成（28例前位胎盘和19例后位胎盘）。其中26名受试者在同一检查期间进行了两次成像。与专家手动分割相比，使用骰子重叠率和表面距离来量化自动分割的准确性。将我们的方法和领先的商业半自动方法VOCAL（虚拟器官计算机辅助分析）获得的平均胎盘体积测量值与手动参考集进行比较。还评估了重测可靠性。
我们的自动分割与手动分割之间的重叠率（平均骰子重叠率： ，中位数：0.831）在其他需要大量手动输入的方法所报告的范围内。平均表面距离为 。重测体积之间的相关系数为 ，组内相关系数为 。
MALF是一种很有前景的方法，只需最少的用户交互就能实现胎盘的准确可靠分割。该技术的进一步完善可能会使胎盘生物测量纳入临床妊娠监测。
