Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities

This paper presents a modified region-scalable fitting (RSF) model in [1] and a more efficient narrow band algorithm to perform level set evolution. A distance regularization term is used to maintain the regularity of the level set function, which is necessary for maintaining stable level set evolution and ensuring accurate numerical computation. The computational efficiency of our algorithm is further improved by using 1D directional convolutions to approximate the 2D convolutions in the computation of the two fitting functions in the RSF model. Our algorithm has been tested on synthetic and real medical images with promising results.