Segmentation of Inter-Neurons in Three Dimensional Brain Imagery

Abstract. Segmentation of neural cells in three dimensional fluorescence mi-croscopy images is a challenging image processing problem. In addition to be-ing important to neurobiologists, accurate segmentation is a vital component of an automated image processing system. Due to the complexity of the data, par-ticularly the extreme irregularity in neural cell shape, generic segmentation techniques do not perform well. This paper presents a novel segmentation tech-nique for segmenting neural cells in three dimensional images. Accuracy rates of over 90 % are reported on a data set of 100 images containing over 130 neural cells and subsequently validated using a novel data set of 64 neurons.