DocumentCode
1674264
Title
Estimating Fetal Nuchal Translucency Parameters from its Ultrasound Image
Author
Deng, Yin-Hui ; Wang, Yuan-Yuan ; Chen, Ping
Author_Institution
Dept. of Electron. Eng., Fudan Univ., Shanghai
fYear
2008
Firstpage
2643
Lastpage
2646
Abstract
Parameters of the fetal nuchal translucency (NT) are very important for the diagnosis and evaluation of fetuses. Currently these parameters are manually measured from the fetal ultrasound image, which may introduce problems of the variability and reproducibility. Here an automatic scheme is proposed to estimate fetal NT parameters. With a morphologic filtering, this scheme firstly establishes the edge map and extracts a preliminary contour by the gradient vector flow (GVF) snake. Then an algorithm based on the dynamic programming is proposed to compound the edge map and the preliminary contour to obtain the NT contour. Finally, parameters of the NT such as the NT thickness and the NT area are calculated. From the application, it is seen that this scheme simultaneously overcomes problems of discontinuousness and concavities in the contour extraction and parameters of the fetal NT can be automatically calculated.
Keywords
biomedical ultrasonics; dynamic programming; edge detection; feature extraction; filtering theory; medical image processing; obstetrics; automatic method; contour extraction; dynamic programming; edge map; fetal nuchal translucency parameter estimation; fetuses diagnosis; fetuses evaluation; gradient vector flow snake; morphologic filtering; ultrasound image; Current measurement; Data mining; Dynamic programming; Filters; Parameter estimation; Reproducibility of results; Speckle; Thickness measurement; Ultrasonic imaging; Ultrasonic variables measurement;
fLanguage
English
Publisher
ieee
Conference_Titel
Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on
Conference_Location
Shanghai
Print_ISBN
978-1-4244-1747-6
Electronic_ISBN
978-1-4244-1748-3
Type
conf
DOI
10.1109/ICBBE.2008.994
Filename
4535874
Link To Document