Soft computing algorithms applied to the segmentation of nerve cell images

Microscopic images of stained nerve cells are routinely analyzed during neuropathological research. Manual analysis relies heavily on operator knowledge, and therefore can be highly subjective. The process is also time consuming. This paper investigates the use of fuzzy C-means to automate the analysis of nerve cell images. Using fuzzy C-means clustering, nerve cells are detected in an image. The nerve cells are then classified into degrees of health based upon their physical characteristics. A fuzzy approach is taken in order to account for vagueness in the data. This ambiguity stems from both the nature of digital images and the nature of biological systems.