It is of positive significance to extract the contour of ultrasound images for medical diagnosis. The paper proposes a method which combines with multi-scale wavelet transform modulus maxima and GVF snake algorithm to extract the contour of cervical lymph node. Firstly, the proposed method obtains the initial contour of the ultrasound image with using an algorithm of edge detection called wavelet transform modulus maxima, and then using GVF snake model can extract the accurate contour of the image. Experiments show that the method overcomes the disadvantages of the wavelet analysis getting the discontinuous edge; it is better in noise immunity and anti-artifact interference compared with the traditional GVF snake model. In addition, the initial contour is close to the real edge of the given image, thus it reduces the iteration number of gradient vector flow (GVF) field and improves the convergence speed of the contour.Index Terms-Lymph node ultrasound images, multi-scale analysis, wavelet transform, the gradient vector flow, active contour model, contour extraction.