Region of interest (ROI) plays an important role in medical image analysis. In this paper, a new approach to ROI extraction based on the curve evolution is proposed. Different from the existent method, the proposed approach is efficient both in segmentation results and computational cost. The deforming curve is modeled as a monotonically marching front under a positive speed field, where a region speed function is derived by minimizing the new defined ROI energy, and integrated with the edge-based speed function. The curve evolution model integrating the ROI information has a large propagation range and could even drive the front in low-contrast and narrow thin areas. Moreover, a multi-initial fast marching algorithm, which permits the user to plant several seed curves as the initial front and evolves them simultaneously, is developed to fast implement the numerical solution. Selective planting seed curves could help the local growth and thus may further improve the segmentation results and reduce the computational cost. Experiments by our approach are presented and compared with that of the other methods, which show that the proposed approach could fast extract low-contrast and narrow thin ROI precisely.