Generally, thesegmentation of a medical image is difficult, because the medical image is often corruptedby norrupted by noise, and the anatomical shape in the medical image is complicated. Inthis paper presents a new geometric active contour scheme for medical image segmentation.First, we regularize the attraction force field in the geometric active contour model toextend the capture range of the object boundaries, and improve the ability of convergenceto the concavities. Then, using a multi-scale scheme improve the boundary detectionaccuracy. In addition, combining the regularization and the multi-scale method, theproposed scheme can effectively suppress and eliminate the noise and the spurious edges inthe medical images. Furthermore, the topology of the deforming curve can naturally changewithout and special topolygy handing procedures added to the scheme. This permitssynchronously extracting several anatomical structures. The experiments on some medicalimages obtained from different medical imaging methods demonstrate that the proposedapproach is competent for medical image segmentation.