Level Set Segmentation of the Fetal Heart
Segmentation of the fetal heart can facilitate the 3D assessment of the cardiac function and structure. Ultrasound acquisition typically results in drop-out artifacts of the chamber walls. This paper presents a level set deformable model to simultaneously segment all four cardiac chambers using region based information. The segmented boundaries are automatically penalized from intersecting at walls with signal dropout. Root mean square errors of the perpendicular distances between the algorithm’s delineation and manual tracings are within 7 pixels (<2mm) in 2D and under 3 voxels (<4.5mm) in 3D. The ejection fraction was determined from the 3D dataset. Future work will include further testing on additional datasets and validation on a phantom.
KeywordsFetal Heart Deformable Model Active Contour Model Gradient Vector Flow Signal Dropout
Unable to display preview. Download preview PDF.
- 1.Mitchell, S.C., Korones, S.B., Berendes, H.W.: Congenital heart disease in 56,109 births. Incidence and natural history. Circulation 43, 323–332 (1971)Google Scholar
- 2.Copel, J.A., Gianluigi, P., Green, J., Hobbins, J.C., Kleinman, C.S.: Fetal echocardiographic screening for congenital heart disease: The importance of the four-chamber view. British Journal of Obstetrics and Gynaecology 157, 648–655 (1987)Google Scholar
- 4.Deng, J.: Terminology of three-dimensional and four-dimensional ultrasound imaging of the fetal heart and other moving parts. Ultrasound in Obstetrics & Gynecology 22, 336–334 (2003)Google Scholar
- 5.Piccoli, L., Dahmer, A., Scharcanski, J., Navaux, P.O.A.: Fetal echocardiographic image segmentation using neural networks. In: Seventh International Conference on Image Processing and its Applications 1999 (1999)Google Scholar
- 8.Dindoyal, I., Lambrou, T., Deng, J., Ruff, C.F., Linney, A.D., Todd-Pokropek, A.: An active contour model to segment foetal cardiac ultrasound data. In: Medical Image Understanding and Analysis, University of Sheffield, UK, July 10 (2003)Google Scholar
- 12.Gibou, F., Fedkiw, R.: A fast hybrid k-means level set algorithm for segmentation. Stanford Technical Report (2002)Google Scholar