» Articles » PMID: 19756243

Segmentation of Brain Immunohistochemistry Images Using Clustering of Linear Centroids and Regional Shapes

Overview
Date 2009 Sep 17
PMID 19756243
Citations 3
Authors
Affiliations
Soon will be listed here.
Abstract

A generalized clustering algorithm utilizing the geometrical shapes of clusters for segmentation of colored brain immunohistological images is presented. To simplify the computation, the dimension of vectors composed from the pixel RGB components is reduced from three to two by applying a de-correlation mapping with the orthogonal bases of the eigenvectors of the auto-covariance matrix. Since the brain immunohistochemical images have stretched clusters that appear long and narrow in geometrical shape, we use centroids of straight lines instead of single points to approximate the clusters. An iterative algorithm is developed to optimize the linear centroids by minimizing the approximation mean-squared error. The partitioning of the two-dimensional vector domain into three portions classifies each image pixel into one of the three classes: The microglial cell cytoplasm, the combined hematoxylin stained cell nuclei and the neuropil, and the pale background. Regions of the combined hematoxylin stained cell nuclei and the neuropil are to be separated based on the differences in their regional shapes. The segmentation results of real immunohistochemical images of brain microglia are provided and discussed.

Citing Articles

Impact of opiate addiction on neuroinflammation in HIV.

Byrd D, Murray J, Safdieh G, Morgello S J Neurovirol. 2012; 18(5):364-73.

PMID: 22797933 PMC: 3573366. DOI: 10.1007/s13365-012-0118-x.


Significant effects of antiretroviral therapy on global gene expression in brain tissues of patients with HIV-1-associated neurocognitive disorders.

Borjabad A, Morgello S, Chao W, Kim S, Brooks A, Murray J PLoS Pathog. 2011; 7(9):e1002213.

PMID: 21909266 PMC: 3164642. DOI: 10.1371/journal.ppat.1002213.


Restoration of distorted colour microscopic images from transverse chromatic aberration of imperfect lenses.

Wu H, Murray J, Morgello S, Fiel M, Schiano T, Kalir T J Microsc. 2011; 241(2):125-31.

PMID: 21902693 PMC: 3807600. DOI: 10.1111/j.1365-2818.2010.03443.x.

References
1.
Mausset-Bonnefont A, de Seze R, Privat A . Immunohistochemistry as a tool for topographical semi-quantification of neurotransmitters in the brain. Brain Res Brain Res Protoc. 2003; 10(3):148-55. DOI: 10.1016/s1385-299x(02)00206-4. View

2.
Chen X, Zhou X, Wong S . Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy. IEEE Trans Biomed Eng. 2006; 53(4):762-6. DOI: 10.1109/TBME.2006.870201. View

3.
Deligdisch L, de Resende Miranda C, Wu H, Gil J . Human papillomavirus-related cervical lesions in adolescents: a histologic and morphometric study. Gynecol Oncol. 2003; 89(1):52-9. DOI: 10.1016/s0090-8258(03)00003-9. View

4.
Mattfeldt T, Gottfried H, Schmidt V, Kestler H . Classification of spatial textures in benign and cancerous glandular tissues by stereology and stochastic geometry using artificial neural networks. J Microsc. 2000; 198(Pt 2):143-58. DOI: 10.1046/j.1365-2818.2000.00689.x. View

5.
Biertho L, Kim C, Wu H, Unger P, Inabnet W . Relationship between sestamibi uptake, parathyroid hormone assay, and nuclear morphology in primary hyperparathyroidism. J Am Coll Surg. 2004; 199(2):229-33. DOI: 10.1016/j.jamcollsurg.2004.04.013. View