Active contour based on transformation of grayscale fluctuations for medical image segmentation

Currently, medical images cannot be segmented well due to the inhomogeneous intensity distribution. This problem exists in X-ray (digital radiographs/tomography), MRI and ultrasound. In order to address this problem, this paper proposed a novel active contour model based on grayscale fluctuations. In this model, grayscale fluctuations are introduced to obtain the grayscale curve in the horizontal direction, and then they are used to get the normalization of grayscale image by the monotone interval judgment. Based on these results, our new active contour model is proposed by redefining the energy function. This paper also introduced related experiments, which are performed on synthetic images and real medical images, with the purpose to verify the proposed model. The experiment results show that the model is able to achieve high accurate segmentation of the image with inhomogeneous intensity distribution.