Open Access Open Access  Restricted Access Subscription or Fee Access

Novel Methods for G-Band Chromosome Classification

S. Janani


Chromosome analysis is an essential task for detecting genetic abnormality, damage due to environmental factors such as X-ray, or diagnosis of cancer. One of the standard tool used for analysis is karyotyping, a process of classification and visualization of chromosomes. A karyotype is required to assign each chromosome to one of 24 classes. Automatic pairing of chromosomes is a difficult task because these chromosomes appear distorted, overlapped, and their images are usually blurred with undefined edges and low level of detail. A new metric method is proposed in this work towards the design of an automatic pairing algorithm for diagnostic purposes. The G-banding technique is routinely used for generating characteristic banding patterns for chromosome identification and karyotyping. Besides the features used in the traditional, mutual information is proposed to increase the discriminate power of the G-banding pattern dissimilarity between chromosomes and improve the performance of the classifier. Chromosome banding patterns are very important features for karyotyping, based on which cytogenetic diagnosis procedures are conducted. Banding pattern is utilized as vital discrimination criterion for human chromosome classification. Dimensional feature like area and perimeter is used to classify chromosome into standard seven groups. Appropriate feature selection and classifier training substantially improve classification performance.


Chromosome, Karyotyping, G-Band Chromosome Image, Features, Band Profile, Mutual Information (MI), Classification.

Full Text:



J.Swansbury, Cancer Cytogenetics: Methods and Protocols (Methods in Molecular Biology). Totowa, NJ: Humana Press, 2003.

B.Czepulkowski, Analyzing Chromosomes. Abingdon, U.K.: BIOS Scientific Publishing, 2001.

T.K.Moon and W.C.Stirling, Mathematical Methods and Algorithms for Signal Processing. Upper Saddle River, NJ: Prentice- Hall, 2000.

J. P.W. Pluim, J. B. A. Maintz, andM.A.Viergever,“Mutual-information based registration of medical images: A survey,” IEEETrans. Med. Imag., vol. 22, no. 8, pp. 986–1004, Aug. 2003.

J. Piper and E. Granum, “On fully automatic feature measurement for banded chromosome classification,” Cytometry, vol. 10, pp. 242–255, 1989.

J. R. Stanley, M. J. Keller, P. Gader, and W. C. Caldwell, “Data-driven homologue matching for chromosome identification,” IEEE Trans. Med. Imag., vol. 17, no. 3, pp. 451–462, Jun. 1998.

M. Zardoshti-Kermani and A. Afshordi, “Classification of chromosomes using higher- order neural networks,” in Proc. IEEE Int. Conf. Neural Netw., Nov. /Dec., 1995, vol. 5,pp. 2587–2591.

B. Lerner, “Toward a completely automatic neural network based human chromosome analysis,” IEEE Trans. Syst. Man Cybern.(Special Issue on Artificial Neural Networks), vol. 28, pp. 544–552, 1998.

Q. wu and K. R. Castleman, "Automated chromosome classification using wavelet-based band pattern descriptors," 13th IEEE Symposium on Computer-Based Medical Systems (CBMS'00), pp. 189- 194, 2000.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.