Segmentation of Nerve Fibers by Introducing Intensity Priority in Level Set

The segmentation of the optic nerve fibers is important for the morphometry study of optic nerve. However, such studies are hampered by the thousands of fibers involved when manual segmentation has to be used. We have developed an automatic segmentation method which is principally based on improved Chan-Vese level set model which integrating myelin sheath intensity priority. Next, identify the axon candidates by labeling closed region based on marker. Our results indicate that this approach for segmenting nerve fiber images is efficient, and advisable compared to manual segmentation.