Automatic Classification of M-FISH Human Chromosome Images using Fuzzy Classifier and Statistical Classifier Images using Fuzzy Classifier and Statistical Classifier

DOI

10.2991/iccasp-16.2017.80How to use a DOI?

Keywords

M-FISH, Expectation Maximization, Fuzzy, Bayes

Abstract

Identification of abnormalities in the chromosomes is a tedious job. Conventionally gray-scale imaging was used for chromosome analysis and was based on features like relative length, banding pattern, centromere posi-tion. As an alternate, Multiplex fluorescence in-situ hybridization (M-FISH) is a combinatorial labeling tech-nique which does not require these features and has many advantages over the conventional method. Our con-tribution includes implementation of joint segmentation classification technique with a) high classification accu-racy, b) low computational complexity and c) high speed for automated Karyotyping of M-FISH chromosome images. We show effect of image preprocessing on classification accuracy. We propose the use of univariate approach instead of multivariate in Fuzzy and Statistical Classifier for pixel-by-pixel joint segmentation classi-fication which results in significant reduction in computational and time complexity with increased accuracy. The overall classification accuracy with Fuzzy and Statistical classifier is 96.47 % and 97.32 % respectively.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - B. Baheti
AU  - G. Ahuja
AU  - A. Parode
PY  - 2016/12
DA  - 2016/12
TI  - Automatic Classification of M-FISH Human Chromosome Images using Fuzzy Classifier and Statistical Classifier Images using Fuzzy Classifier and Statistical Classifier
BT  - Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016)
PB  - Atlantis Press
SP  - 549
EP  - 556
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccasp-16.2017.80
DO  - 10.2991/iccasp-16.2017.80
ID  - Baheti2016/12
ER  -