In this paper, a close-form B-snake model is presented for contour extraction in medical images. Based on our previous research work [lo], the Principal Component Analysis (PCA) has been applied to our B-snake model, in order to use available statistical information about the desired object shape. This approach allows the deformation of B-snake to synthesize the shape similar to those in the training set. Experimental results show the robustness and accurateness of proposed model in object contour extraction in medical images.