Abstract
Due to dozens of colorized neuron fibers spreading densely in a very intricate structure, it is difficult to trace them by using existing algorithms designed for monochrome single-neuron images and also time-consuming to label them manually. We propose a neuron segmentation system on Drosophila Brainbow image stack. The idea follows the steps of manually, that is, the system is designed to imitate the way biological experts identify different neurons. Besides, because the “color information” of Brainbow imagery is a composite signal coming from those captured by different band-pass filters, it is straightforward to consider each channel independently. On the other hand, according to the considerable morphological differences between cell bodies and neuron fibers, some three-dimensional morphological processing methods could also be applied. Based on the location and the fluorescence intensity of each cell body, we can trace and segment each neuron by considering the similarities among adjacent voxels. The proposed system can provide segmentation results semi-automatically, and thus it would be useful for biologists in identifying the neural-circuits.