Department of Computational Science and Engineering, Yonsei University, Seoul 03722, Republic of Korea.
Physiol Meas. 2018 Oct 22;39(10):105007. doi: 10.1088/1361-6579/aae255.
Obstetricians mainly use ultrasound imaging for fetal biometric measurements. However, such measurements are cumbersome. Hence, there is urgent need for automatic biometric estimation. Automated analysis of ultrasound images is complicated owing to the patient-specific, operator-dependent, and machine-specific characteristics of such images.
This paper proposes a method for the automatic fetal biometry estimation from 2D ultrasound data through several processes consisting of a specially designed convolutional neural network (CNN) and U-Net for each process. These machine learning techniques take clinicians' decisions, anatomical structures, and the characteristics of ultrasound images into account. The proposed method is divided into three steps: initial abdominal circumference (AC) estimation, AC measurement, and plane acceptance checking.
A CNN is used to classify ultrasound images (stomach bubble, amniotic fluid, and umbilical vein), and a Hough transform is used to obtain an initial estimate of the AC. These data are applied to other CNNs to estimate the spine position and bone regions. Then, the obtained information is used to determine the final AC. After determining the AC, a U-Net and a classification CNN are used to check whether the image is suitable for AC measurement. Finally, the efficacy of the proposed method is validated by clinical data.
Our method achieved a Dice similarity metric of [Formula: see text] for AC measurement and an accuracy of 87.10% for our acceptance check of the fetal abdominal standard plane.
妇产科医生主要使用超声成像进行胎儿生物测量。然而，这些测量方法繁琐。因此，迫切需要自动生物测量估计。由于这些图像具有患者特异性、操作人员依赖性和机器特异性，因此自动分析超声图像很复杂。
本文提出了一种通过几个过程从二维超声数据中自动进行胎儿生物测量估计的方法，这些过程包括一个专门设计的卷积神经网络（CNN）和每个过程的 U-Net。这些机器学习技术考虑了临床医生的决策、解剖结构以及超声图像的特征。所提出的方法分为三个步骤：初始腹围（AC）估计、AC 测量和平面接受检查。
使用 CNN 对超声图像（胃泡、羊水和脐静脉）进行分类，并使用霍夫变换获得 AC 的初始估计。将这些数据应用于其他 CNN 以估计脊柱位置和骨骼区域。然后，使用获得的信息确定最终的 AC。确定 AC 后，使用 U-Net 和分类 CNN 检查图像是否适合 AC 测量。最后，通过临床数据验证了所提出方法的功效。
我们的方法在 AC 测量方面达到了[公式：见文本]的 Dice 相似性度量，在胎儿腹部标准平面的接受检查方面达到了 87.10%的准确性。
