Abstract
A new texture analysis approach is applied to the problem of classification of pathological states from electron microscopy images of mouse liver cell nuclei. For each pixel in the image, a region of consistent connected neighbouring pixels is extracted, forming a local texel of pixels belonging to the same gray level population. The geometric properties of each texel is described by invariant moment-based features. A recently developed method for fast and exact computation of Cartesian geometric moments is utilized. Each cell nucleus is characterized by a feature vector, giving the average feature values of both the bright and the dark structures. A leave-one-out classification is performed, using 4 different classes of cells (normal, proliferating, precancer and cancer).
The results demonstrate that using gray level connected neighbour structures as texels gives us important information about the chromatin texture of the cell nuclei and thus the pathological state of the cell. Several pairs of radiometric and geometric moment features of the texels gave a 90% correct classification.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
S. O. Belkasim, M. Shridhar, and M. Ahmadi, Pattern recognition with moment invariants: a comparative study and new results, Pattern Recognition 24(12), 1117–1138 (1991).
J. Bigun, and J. M. H. du Buf, Geometric image primitives by complex moments in Gabor space and the application to texture segmentation, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 648–650 (1992).
H. E. Danielsen, G. E. Farrants and A. Reith, Characterization of chromatin structure by image analysis — A method for assessment of changes in cromatin organization, Scanning Microscopy Suppl., 3, 297–302 (1988).
N. Glick, Additive estimators for probabilities of correct classification, Pattern Recognition, 10, 211–222 (1978).
M.-K. Hu, Visual pattern recognition by moment invariants, IRE Trans. Information Theory 8, 179–187 (1962).
A. K. Jain and F. Farrokhnia, Unsupervised texture segmentation using Gabor filters, Pattern Recognition, 24, 1167–1186 (1991).
K. Knutsson, and G. H. Granlund, Texture analysis using two-dimensional quadrature filters, IEEE CAPAIDM Workshop, Pasadena, Cal., Oct. 12–14, 206–213 (1983).
B.-C. Li, and J. Shen, Fast computation of moment invariants, Pattern Recognition 24(8), 807–813 (1991).
T. Lønnestad, Connected filters for noise removal, Proc. 9thICPR, 848–850, Rome (1988).
R. J. Prokop, and A. P. Reeves, A survey of moment-based techniques for unoccluded object representation and recognition, CVGPR: Graphical Models and Image Processing 54(5), 438–460 (1992).
H. Schulerud and J.M. Carstensen, Multiresolution Texture Analysis of four classes of Mice Liver cells using different cell cluster representations, Proceedings, 9th Scandinavian Conference on Image Analysis, Uppsala, Sweden, 121–129 (1995).
M. Tuceryan, Moment based texture segmentation, Pattern Recognition Letters 15, 659–668 (1994).
L. Yang, and F. Albregtsen, Fast computation of invariant geometric moments: A new method giving correct results, Proc. 12thICPR, Vol. A, 201–204, (1994).
L. Yang, and F. Albregtsen, Fast and exact computation of cartesian geometric moments using discrete Green's theorem, Pattern Recognition (In Press).
K. Yogesan, F. Albregtsen, A. Reith, and H. E. Danielsen, Cooccurrence and run length-based texture analysis of experimental liver carcinogenesis in mice, Proc. 8th Scandinavian Conference on Image Analysis, Tromsø, Norway, 227–234 (1993).
K. Yogesan, F. Albregtsen, J.M. Nesland, and H.E. Danielsen, Chromatin texture analysis of normal, regenerating, premalignant and malignant liver cells, Ultrastructural Pathology (In Press).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Albregtsen, F., Schulerud, H., Yang, L. (1995). Texture classification of mouse liver cell nuclei using invariant moments of consistent regions. In: Hlaváč, V., Šára, R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60268-2_334
Download citation
DOI: https://doi.org/10.1007/3-540-60268-2_334
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60268-2
Online ISBN: 978-3-540-44781-8
eBook Packages: Springer Book Archive