Share Email Print
cover

Proceedings Paper

Quantization and similarity measure selection for discrimination of lymphoma subtypes under k-nearest neighbor classification
Author(s): Cristian Mircean; Ioan Tabus; Jaakko Astola; Tohru Kobayashi; Hiroshi Shiku; Motoko Yamaguchi; Ilya Shmulevich; Wei Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Molecular classification of tumors holds great potential for cancer research, diagnosis, and treatment. In this study, we apply a novel classification technique to cDNA microarray data for discriminating between three subtypes of malignant lymphoma: CD5+ diffuse large B-cell lymphoma, CD5- diffuse large B-cell lymphoma, and mantle cell lymphoma. The proposed technique combines the k-Nearest Neighbor (k-NN) algorithm with optimized data quantization. The feature genes on which the classification is based are selected by ranking them according to their separability criteria computed by taking into account between-class and within-class scatter. The classification errors, estimated using cross-validation, are significantly lower than those produced by classical variants of the k-NN algorithm. Multidimensional scaling and hierarchical clustering dendrograms are used to visualize the separation of the three subtypes of lymphoma.

Paper Details

Date Published: 22 June 2004
PDF: 12 pages
Proc. SPIE 5328, Microarrays and Combinatorial Techniques: Design, Fabrication, and Analysis II, (22 June 2004); doi: 10.1117/12.529580
Show Author Affiliations
Cristian Mircean, Tampere Univ. of Technology (Finland)
Ioan Tabus, Tampere Univ. of Technology (Finland)
Jaakko Astola, Tampere Univ. of Technology (Finland)
Tohru Kobayashi, Mie Univ. School of Medicine (Japan)
Hiroshi Shiku, Mie Univ. School of Medicine (Japan)
Motoko Yamaguchi, Mie Univ. School of Medicine (Japan)
Ilya Shmulevich, Univ. of Texas M. D. Anderson Cancer Ctr. (United States)
Wei Zhang, Univ. of Texas M. D. Anderson Cancer Ctr. (United States)


Published in SPIE Proceedings Vol. 5328:
Microarrays and Combinatorial Techniques: Design, Fabrication, and Analysis II
Dan V. Nicolau; Ramesh Raghavachari, Editor(s)

© SPIE. Terms of Use
Back to Top