Fetal ultrasound image segmentation system and its use in fetal weight estimation

Abstract

A semi-automated fetal ultrasound image segmentation system is developed to improve the estimation of fetal weight (EFW). Four standardized fetal parameters are measured by the proposed segmentation system: biparietal diameter, head circumference, abdominal circumference and femur length. Computerized measurements of 215 fetuses are compared with manual measurements in term of fitness analysis and difference analysis. Among 215 cases, computerized measurements of 103 fetuses within 3 days of delivery are utilized in the fetal weight estimation. The EFW based on computerized measurements and manual measurements are compared by using regression analysis, artificial neural network and support vector regression. By using different estimation methods, the computerized measurements decrease the EFW errors about 40-70 g. The lowest mean absolute percentage error of EFW decrease from 6.71% for manual measurements to 4.66% for computerized measurements. The proposed fetal ultrasound image segmentation system can provide more accurate EFW in antepartum examination.

A Knowledge-Based Approach for Carpal Tunnel Segmentation from Magnetic Resonance Images

“…Seifert et al [25] presented a segmentation method for the soft tissues of the cervical spine based on spine anatomy. This issue was also addressed by Yu et al [26] for fetal ultrasound image segmentation. These methods combined anatomical knowledge with segmentation protocols in order to initialize the model closely to the target and increase the accuracy of the segmentation.…”

Biomedical Image Segmentation Based on Multiple Image Features

“…Fetal abdominal circumference (AC), an indicator of fetal growth, is one of the standardized measurements in antepartum ultrasound monitoring. In the first application, a method that makes effective use of the intensity and edge information is provided to outline and measure the fetal abdominal circumference from ultrasound images (Yu et al, 2008a;Yu et al, 2008b). Fig.…”

Difference of Gaussians revolved along elliptical paths for ultrasound fetal head segmentation

“…These methods have mostly been based on the segmentation of the ultrasound images [22]. Approaches for the fetal skull segmentation have been based on deformable spline [12] and contour models [4,20], supervised learning [2], and ellipse fitting through (randomized) Hough transform [10,17,27]. The deformable contour or spline model [4,20,12] based approaches rely on the user to indicate a point close to the center of head and construct an initial contour model based on this information.…”

“…The ellipse fitting approaches first segment pre-processed ultrasound images through clustering or histogram analysis [10,17] or perform edge detection [27], in either case producing a binary image of the fetal skull. The Hough transform [10] or the randomized Hough transform (RHT) [17,27] is then utilized to fit the ellipse model to the binary image.…”

“…The Hough transform [10] or the randomized Hough transform (RHT) [17,27] is then utilized to fit the ellipse model to the binary image. As Hough transform and RHT are very sensitive to image artifacts, these methods require the user to define an initial region of interest (ROI) [27] or their application is limited to images where head contour is complete and is not overlapped by other structures [10].…”