Segmentation of breast ultrasound image using graph cuts and level set

Image segmentation plays a crucial role in breast ultrasound (BUS) for breast cancer detection. However, due to the heavy speckle noise, low contrast and shadowing effects of BUS images, it's a challenging task to develop an accurate and robust segmentation algorithm. In this paper, we present a novel algorithm for breast ultrasound image segmentation which is based on hybrid of level set and graph cuts. Firstly, speckle reducing anisotropic diffusion. Subsequently, the initial contour is achieved by graph cut. To smooth the boundaries, a boundary item is added into the energy function of level set. At last, the final contour converges to the objective boundary quickly and accurately after finite steps of iteration of level set. Comparing with the traditional level set method, the requirement of the costly re-initialization procedure is completely eliminated and the local minima are effectively avoided in our method. The experiment results show that the processing time for level set based method to BUS image can be substantially reduced while getting promising segmentation results.