The detection of left ventricular boundary is an interesting and challenging task in the cardiac analysis. In this paper, a self-learning contour finding model derived based on the snake model is designed to detect the echocardiac boundaries. The proposed model utilizes the genetic algorithms as a training kernel to acquire the weights for the driving forces in the snake deformation. Thus, the weights can be treated as a priori knowledge of contour definition before the contour finding process is proceeded. Both the synthetic and real image experiments are carried out to verify the performance of the proposed method.
|頁（從 - 到）||971-981|
|期刊||Proceedings of SPIE - The International Society for Optical Engineering|
|出版狀態||Published - 1998 十二月 1|
|事件||Medical Imaging 1998: Image Processing - San Diego, CA, United States|
持續時間: 1998 二月 23 → 1998 二月 23
All Science Journal Classification (ASJC) codes