Three Dimensional Segmentation Of Intravascular Ultrasound Image Sequence Based On Fast Marching

Intravascular Ultrasound (IVUS) is one of interventional imaging modalities for diagnosing vascular diseases, especially coronary artery diseases. Segmentation of IVUS image sequence to extract inner and outer contours of vessel wall from each cross-sectional slice is of importance for quantitative analysis and 3-D reconstruction of IVUS sequence.In this dissertation, a 3-D method based on fast marching is proposed to implement parallel segmentation of IVUS sequences. First, IVUS longitudinal cut is obtained after preprocessing procedures including denoising and suppression of ring-down artifact. Then, vessel wall contours detected from IVUS longitudinal cut are mapped into each cross-sectional slice to obtain initial vessel wall contours in each IVUS frame. Finally, with the fast marching algorithm, initial contours begin to deform until stops at the actual contours.The research work in this dissertation was supported by National Nature Science Foundation of China (Grant No.30500129 and 60973087).