Semi-automatic tumor segmentation based on modified sparse field method

Active contour methods for image segmentation allow a contour to deform iteratively to partition an image into various regions. Active contours are often implemented with level set methods because of their power and versatility. The primary drawback of level set methods is that, they are slow to compute. In this paper, we discussed the sparse field method (SFM) proposed by Whitaker that allows one to implement level set active contours efficiently. In active contour, stopping term depends on gradient of image only. In practice, the discrete gradients are bounded and then the stopping function is never zero on the edges, and the curve may pass through the object boundary. In this paper, we proposed the new method of edge detection for active contours based on local adaptive threshold technique via variational energy minimization. As an application, our method has been used for tumor segmentation from magnetic resonance images and experimental results show desirable performances of our method.