Automatic Estimation of Fetal Abdominal Circumference From Ultrasound Images

Abstract

Ultrasound diagnosis is routinely used in obstetrics and gynecology for fetal biometry, and owing to its time-consuming process, there has been a great demand for automatic estimation. However, the automated analysis of ultrasound images is complicated because they are patient specific, operator dependent, and machine specific. Among various types of fetal biometry, the accurate estimation of abdominal circumference (AC) is especially difficult to perform automatically because the abdomen has low contrast against surroundings, nonuniform contrast, and irregular shape compared to other parameters. We propose a method for the automatic estimation of the fetal AC from two-dimensional ultrasound data through a specially designed convolutional neural network (CNN), which takes account of doctors' decision process, anatomical structure, and the characteristics of the ultrasound image. The proposed method uses CNN to classify ultrasound images (stomach bubble, amniotic fluid, and umbilical vein) and Hough transformation for measuring AC. We test the proposed method using clinical ultrasound data acquired from 56 pregnant women. Experimental results show that, with relatively small training samples, the proposed CNN provides sufficient classification results for AC estimation through the Hough transformation. The proposed method automatically estimates AC from ultrasound images. The method is quantitatively evaluated and shows stable performance in most cases and even for ultrasound images deteriorated by shadowing artifacts. As a result of experiments for our acceptance check, the accuracies are 0.809 and 0.771 with expert 1 and expert 2, respectively, whereas the accuracy between the two experts is 0.905. However, for cases of oversized fetus, when the amniotic fluid is not observed or the abdominal area is distorted, it could not correctly estimate AC.

Complementary Network for Accurate Amniotic Fluid Segmentation From Ultrasound Images

“…More precisely, h (3) is obtained by concatenation of h (2) and ReLU (η 1 (I) 4 W (3) ). Similarly, h (6) and h (9) are produced by using η 2 (I) and η 3 (I) that are the average pooling of I by a factor of four and eight, respectively. This multi-scale side-input layer achieves multiple levels of receptive field size in the encoding path of AF-net, therefore it helps deal with unpredictable shapes and large size variations of AF pockets.…”

“…Therefore, the fully automatic segmentation of the AF pocket has been in substantial demand. Unfortunately, this task is highly challenging, unlike other ultrasound-based automatic fetal biometric measurements [6]- [9]. The difficulty arises due to amorphous features (i.e., an unspecified variety of shapes and sizes) of the AF pocket and various factors, such as reverberation, the AF mimicking region, floating matter, and incomplete or missing boundary, which lead to limited accuracy of AF pocket segmentation [3], [10].…”

Defending Against Child Death: Deep learning‐based diagnosis method for abnormal identification of fetus ultrasound Images

“…This section describes the proposed Defending Against Child Death (DACD) method where it involves CNN in deep learning 25,26 for ultrasound image classification with improved accuracy.…”

Deteksi Otomatis Bidang Kepala Janin dari Citra Ultrasonografi 2 Dimensi

“…Pada penelitian ini, diusulkan sebuah sistem yang dapat melakukan proses deteksi otomatis bidang kepala janin menggunakan CNN. Pemilihan metode CNN digunakan karena CNN dapat menjadi classifier yang robust untuk citra USG janin [1], [6], [7]. CNN digunakan untuk melakukan segmentasi semantik terhadap tiga kelas yaitu bidang elips, maternal tissue, dan background.…”