DocumentCode :
617505
Title :
Improved automatic centerline tracing for dendritic structures
Author :
Jimenez, Daniel ; Papadakis, Mike ; Labate, Demetrio ; Kakadiaris, Ioannis A.
Author_Institution :
Dept. of Math., Univ. of Houston, Houston, TX, USA
fYear :
2013
fDate :
7-11 April 2013
Firstpage :
1050
Lastpage :
1053
Abstract :
Centerline tracing of dendritic structures in confocal images of neurons is an essential tool for the construction of a geometric representation of a neuronal network. In this paper, we propose a novel algorithm (ORION 2) for centerline extraction that is both highly accurate and computationally efficient. The main novelty of the proposed method is the use of a small set of Multiscale Isotropic Laplacian filters for a fast and efficient binarization of the dendritic structure.The performance of this algorithm, which is validated using datasets from DIADEM is shown to be very competitive against other state-of-the-art algorithms.
Keywords :
biological techniques; biology computing; digital filters; feature extraction; image processing; image segmentation; neural nets; neurophysiology; optical microscopy; DIADEM datasets; ORION 2 algorithm; automatic centerline tracing; computationally efficient centerline extraction algorithm; dendritic structure binarization; dendritic structures; high accuracy centerline extraction algorithm; multiscale isotropic Laplacian filters; neuron confocal images; neuronal network geometric representation; Biomedical imaging; Laplace equations; Measurement; Microscopy; Neurons; Solids; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on
Conference_Location :
San Francisco, CA
ISSN :
1945-7928
Print_ISBN :
978-1-4673-6456-0
Type :
conf
DOI :
10.1109/ISBI.2013.6556658
Filename :
6556658
Link To Document :
بازگشت