An Automatic Method for Nucleus Boundary Segmentation Based on a Closed Cubic Spline

The recognition of brain nuclei is the basis for localizing brain functions. Traditional histological research, represented by atlas illustration, achieves the goal of nucleus boundary recognition by manual delineation, but it has become increasingly difficult to extend this handmade method to delineating brain regions and nuclei from large datasets acquired by the recently developed single-cell-resolution imaging techniques for the whole brain. Here, we propose a method based on a closed cubic spline (CCS), which can automatically segment the boundaries of nuclei that differ to a relatively high degree in cell density from the surrounding areas and has been validated on model images and Nissl-stained microimages of mouse brain. It may even be extended to the segmentation of target outlines on MRI or CT images. The proposed method for the automatic extraction of nucleus boundaries would greatly accelerate the illustration of high-resolution brain atlases.

[1]  William H. Press,et al.  Numerical Recipes 3rd Edition: The Art of Scientific Computing , 2007 .

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Daniel P. Huttenlocher,et al.  Comparing Images Using the Hausdorff Distance , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  D. Kershaw,et al.  The Orders of Approximation of the First Derivative of Cubic Splines at the Knots , 1972 .

[5]  M. Gahr.  How should brain nuclei be delineated? Consequences for developmental mechanisms and for correlations ofarea size, neuron numbers and functions of brain nuclei , 1997, Trends in Neurosciences.

[6]  Alan C. Evans,et al.  BigBrain: An Ultrahigh-Resolution 3D Human Brain Model , 2013, Science.

[7]  A. McDonald,et al.  Cytoarchitecture of the central amygdaloid nucleus of the rat , 1982, The Journal of comparative neurology.

[8]  K. Andres,et al.  Morphologic and cytochemical criteria for the identification and delineation of individual subnuclei within the lateral habenular complex of the rat , 2003, The Journal of comparative neurology.

[9]  Mario Giacobini,et al.  Automatic segmentation of hippocampus in histological images of mouse brains using deformable models and random forest , 2012, 2012 25th IEEE International Symposium on Computer-Based Medical Systems (CBMS).

[10]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[11]  Kurt R Illig,et al.  Differences in chemo‐ and cytoarchitectural features within pars principalis of the rat anterior olfactory nucleus suggest functional specialization , 2006, The Journal of comparative neurology.

[12]  Peter C. Brunjes,et al.  A field guide to the anterior olfactory nucleus (cortex) , 2005, Brain Research Reviews.

[13]  Theodore Raphan,et al.  Texture-based approaches for identifying neuro-anatomical structures and electrode tracks , 2004, Comput. Methods Programs Biomed..

[14]  Hong Wei Dong,et al.  Allen reference atlas : a digital color brain atlas of the C57Black/6J male mouse , 2008 .

[15]  Stefano Cagnoni,et al.  Segmentation of histological images using a metaheuristic-based level set approach , 2013, GECCO.

[16]  George Paxinos,et al.  The Mouse Brain in Stereotaxic Coordinates , 2001 .

[17]  Wiro J. Niessen,et al.  Hippocampus segmentation in MR images using atlas registration, voxel classification, and graph cuts , 2008, NeuroImage.

[18]  J. Price.  :Allen Reference Atlas: A Digital Color Brain Atlas of the C57BL/6J Male Mouse , 2008 .

[19]  David S Tuch,et al.  Automatic segmentation of thalamic nuclei from diffusion tensor magnetic resonance imaging , 2003, NeuroImage.

[20]  Abdul Rahman Ramli,et al.  Review of brain MRI image segmentation methods , 2010, Artificial Intelligence Review.

[21]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.