Objective Children’s heart valves by DS CT images were enhanced and segmented in order to reconstruct 3D construction of heart valves and do motion analysis according to this model. Methods Adaptive seed-filling algorithm is proposed in this paper to segment region of interest of heart based on DS CT images. Contourlet transform is used to enhance and segment heart valve based on the part-segmented image. Results With these methods, DS CT images were successfully processed and segmented in Matlab7.0 and clear images of mitral valves were got. Conclusion The adaptive seed-filling algorithm proposed in this paper and Contourlet transform are very useful for segmentation in different situation. The conclusion in this paper provides useful reference for doctors to do research on the motion of mitral valves and plan on surgical operation of mitral valves.
MA Li-dan, YANG Xin, SONG Wei, QIU Jun-wei, SUN Kun. Segmentation of heart valves in DS CT image based on Contourlet transform[J]. Journal of medical biomechanics,2009,24(6):408-413Copy