Neuron recognition by parallel Potts segmentation

Identifying neurons and their spatial coordinates in images of the cerebral cortex is a necessary step in the quantitative analysis of spatial organization in the brain. This is especially important in the study of Alzheimer's disease (AD), in which spatial neuronal organization and relationships are highly disrupted because of neuronal loss. To automate neuron recognition by using high-resolution confocal microscope images from human brain tissue, we propose a recognition method based on statistical physics that consists of image preprocessing, parallel image segmentation, and cluster selection on the basis of shape, optical density, and size. We segment a preprocessed digital image into clusters by applying Monte Carlo simulations of a q-state inhomogeneous Potts model. We then select the range of Potts segmentation parameters to yield an ideal recognition of simplified objects in the test image. We apply our parallel segmentation method to control individuals and to AD patients and achieve recognition of 98% (for a control) and 93% (for an AD patient), with at most 3% false clusters.

[1]  Chayes,et al.  Invaded cluster algorithm for equilibrium critical points. , 1995, Physical review letters.

[2]  Wang,et al.  Nonuniversal critical dynamics in Monte Carlo simulations. , 1987, Physical review letters.

[3]  H. Stanley,et al.  Description of microcolumnar ensembles in association cortex and their disruption in Alzheimer and Lewy body dementias. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[4]  E. G. Jones,et al.  Microcolumns in the cerebral cortex. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[5]  F. Y. Wu The Potts model , 1982 .

[6]  Jon Machta,et al.  GRAPHICAL REPRESENTATIONS AND CLUSTER ALGORITHMS FOR CRITICAL POINTS WITH FIELDS , 1998 .

[7]  Kandel,et al.  General cluster Monte Carlo dynamics. , 1991, Physical review. B, Condensed matter.

[8]  Y Okabe,et al.  Probability-changing cluster algorithm for Potts models. , 2001, Physical review letters.

[9]  Eytan Domany,et al.  Superparamagnetic Clustering of Data , 1996 .

[10]  Antonio Coniglio,et al.  Clusters and Ising critical droplets: a renormalisation group approach , 1980 .

[11]  E. Glaser,et al.  Stereology, morphometry, and mapping: the whole is greater than the sum of its parts , 2000, Journal of Chemical Neuroanatomy.

[12]  A. Sokal,et al.  Generalization of the Fortuin-Kasteleyn-Swendsen-Wang representation and Monte Carlo algorithm. , 1988, Physical review. D, Particles and fields.

[13]  G. Godefroy,et al.  Voronoi tessellation to study the numerical density and the spatial distribution of neurones , 2000, Journal of Chemical Neuroanatomy.

[14]  G. M. Halliday,et al.  Practical considerations for the use of the optical disector in estimating neuronal number , 1994, Journal of Neuroscience Methods.

[15]  J. D. Clements,et al.  Automated image analysis for counting unstained cultured neurones , 1991, Journal of Neuroscience Methods.

[16]  F. Wörgötter,et al.  Cluster update algorithm and recognition , 2000 .

[17]  Patrick R Hof,et al.  Altered spatial arrangement of layer V pyramidal cells in the mouse brain following prenatal low-dose X-irradiation. A stereological study using a novel three-dimensional analysis method to estimate the nearest neighbor distance distributions of cells in thick sections. , 2002, Cerebral cortex.

[18]  F. Niedermayer,et al.  General cluster updating method for Monte Carlo simulations. , 1988, Physical review letters.

[19]  Wolff,et al.  Collective Monte Carlo updating for spin systems. , 1989, Physical review letters.

[20]  G. Godefroy,et al.  Evaluation of neuronal numerical density by Dirichlet tessellation , 1994, Journal of Neuroscience Methods.

[21]  H. E. Stanley,et al.  Neurotoxic effects of thioflavin S-positive amyloid deposits in transgenic mice and Alzheimer's disease , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[22]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[23]  R. Swendsen,et al.  Cluster Monte Carlo algorithms , 1990 .

[24]  A Fast and Robust Cluster Update Algorithm for Image Segmentation in Spin-Lattice Models Without AnnealingVisual Latencies Revisited , 1998, Neural Computation.

[25]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[26]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[27]  H. Gundersen,et al.  Unbiased stereological estimation of the number of neurons in the human hippocampus , 1990, The Journal of comparative neurology.

[28]  C. Fortuin,et al.  On the random-cluster model: I. Introduction and relation to other models , 1972 .