Supervised parametric and non-parametric classification of chromosome images

Authors:
M. P. Sampat;A. C. Bovik;J. K. Aggarwal;K. R. Castleman
Affiliations:
Department of Biomedical Engineering, Laboratory for Image and Video Engineering, The University of Texas at Austin, TX 78712, USA;Department of Electrical and Computer Engineering, Laboratory for Image and Video Engineering, The University of Texas at Austin, TX 78712, USA;Department of Electrical and Computer Engineering, Computer & Vision Research Center, The University of Texas at Austin, TX 78712, USA;Advanced Digital Imaging Research, LLC, League City, Texas 77573, USA
Venue:
Pattern Recognition
Year:
2005

Citing 4
Cited 3

Digital image processing

Digital image processing
Automated Chromosome Classification Using Wavelet-Based Band Pattern Descriptors

CBMS '00 Proceedings of the 13th IEEE Symposium on Computer-Based Medical Systems (CBMS'00)
Digital Imaging and Cytogenetics: A Historical Perspective

CBMS '00 Proceedings of the 13th IEEE Symposium on Computer-Based Medical Systems (CBMS'00)
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)

Biological shape characterization for automatic image recognition and diagnosis of protozoan parasites of the genus Eimeria

Pattern Recognition
Enhancement of multichannel chromosome classification using a region-based classifier and vector median filtering

IEEE Transactions on Information Technology in Biomedicine - Special section on biomedical informatics
Identifying touching and overlapping chromosomes using the watershed transform and gradient paths

Pattern Recognition Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes a fully automatic chromosome classification algorithm for Multiplex Fluorescence In Situ Hybridization (M-FISH) images using supervised parametric and non-parametric techniques. M-FISH is a recently developed chromosome imaging method in which each chromosome is labelled with 5 fluors (dyes) and a DNA stain. The classification problem is modelled as a 25-class 6-feature pixel-by-pixel classification task. The 25 classes are the 24 types of human chromosomes and the background, while the six features correspond to the brightness of the dyes at each pixel. Maximum likelihood estimation, nearest neighbor and k-nearest neighbor methods are implemented for the classification. The highest classification accuracy is achieved with the k-nearest neighbor method and k=7 is an optimal value for this classification task.