Kim Hee Chang, Genovesio Auguste
Universite Rene Descartes Paris 5, 75006 Paris.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:1020-3. doi: 10.1109/IEMBS.2009.5334083.
The morphological studies of neuron structures are of great interests for biologists. However, manually detecting dendrites structures is very labor intensive, therefore unfeasible in studies that involve a large number of images. In this paper, we propose an automated neuron detection and description method. The proposed method uses ratios of probability maps from random walk sessions to detect initial seed-points and minimal cost path integrals with Delaunay triangulations.
