Automatic Estimation of Gestational Age in Ultrasound Images Based on Direct Least‐Squares Fitting of Ellipse

Measurement of the fetal head biparietal diameter (BPD) and head circumference (HC) is crucial for estimation of fetal age. Due to the noisy nature of ultrasound images and variation in image acquisition and measurement techniques, manual measurements of these parameters are subject to inter- and intraobserver variability. In this study, we present an approach for estimation of gestational age in ultrasound images, based on direct least-squares fitting of an ellipse. The process goes through three steps: image preprocessing, object extraction, and fitting an ellipse to the resultant shape and measuring its parameters. The proposed technique was tested and evaluated on 20 ultrasound images of fetal head. The images had a combination of noise and low contrast. Excellent linear correlation between manual and automatic measurement was obtained, which verifies the reliability of the proposed automatic approach.

[1]  C.W. Hanna,et al.  Automated measurements in obstetric ultrasound images , 1997, Proceedings of International Conference on Image Processing.

[2]  W. Gander.  Least squares with a quadratic constraint , 1980 .

[3]  R A Peters,et al.  Automatic segmentation of ultrasound images using morphological operators. , 1991, IEEE transactions on medical imaging.

[4]  Quan Pan,et al.  Fast algorithm and application of Hough transform in iris segmentation , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[5]  Andrew W. Fitzgibbon,et al.  Direct Least Square Fitting of Ellipses , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Mário A. T. Figueiredo,et al.  Automatic contour estimation in fetal ultrasound images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[7]  V Chalana,et al.  Automatic fetal head measurements from sonographic images. , 1996, Academic radiology.

[8]  Jinglu Tan,et al.  Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform. , 2005, Ultrasound in medicine & biology.

[9]  A. Khashman,et al.  Automatic edge detection of foetal head and abdominal circumferences using neural network arbitration , 1997, ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics.

[10]  Nicholas Ayache,et al.  Medical Image Analysis: Progress over Two Decades and the Challenges Ahead , 2000, IEEE Trans. Pattern Anal. Mach. Intell..