Steerable Features for Statistical 3D Dendrite Detection
G. González, F. Aguet, F. Fleuret, M. Unser, P. Fua
Proceedings of the Twelfth International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI'09), London, United Kingdom, September 20-24, 2009, [Lecture Notes in Computer Science, vol. 5762, part 2, Springer, 2009], pp. 625–632.
Most state-of-the-art algorithms for filament detection in 3-D image-stacks rely on computing the Hessian matrix around individual pixels and labeling these pixels according to its eigenvalues. This approach, while very effective for clean data in which linear structures are nearly cylindrical, loses its effectiveness in the presence of noisy data and irregular structures.
In this paper, we show that using steerable filters to create rotationally invariant features that include higher-order derivatives and training a classifier based on these features lets us handle such irregular structures. This can be done reliably and at acceptable computational cost and yields better results than state-of-the-art methods.
@INPROCEEDINGS(http://bigwww.epfl.ch/publications/gonzalez0901.html,
AUTHOR="Gonz{\'{a}}lez, G. and Aguet, F. and Fleuret, F. and Unser, M.
and Fua, P.",
TITLE="Steerable Features for Statistical {3D} Dendrite Detection",
BOOKTITLE="Proceedings of the Twelfth International Conference on
Medical Image Computing and Computer Assisted Intervention
({MICCAI'09})",
YEAR="2009",
editor="",
volume="5762",
series="Lecture Notes in Computer Science",
pages="625--632",
address="London, United Kingdom",
month="September 20-24,",
organization="",
publisher="Springer",
note="Part {II}")