Machine Learning Classifiers Evaluation for Automatic Karyogram Generation from G-Banded Metaphase Images
Source abstract
Abstract
This work proposes the evaluation of a set of algorithms of machine learning and the selection of the most appropriate one for the classification of segmented chromosomes images acquired using the Giemsa staining technique (G-banding). The evaluation and selection of the best classification algorithms was carried out over a dataset of 119 Q-banding chromosomes images, and the obtained results were then applied to a dataset of 24 G-band chromosomes images, manually classified by an expert of the Laboratory of Cytogenetic of the Children’s Hospital of Tamaulipas. The results of evaluation of 51 classifiers yielded that the best classification accuracy for the selected features was obtained by a backpropagation neural network. One of the main contributions of this study is the proposal of a two-stage classification scheme based on the best classifier found by the initial evaluation. In stage 1, chromosome images are classified into three major groups. In stage 2, the output of phase 1 is used as the input of a multiclass classifier. Using this scheme, 82% of the IGB bank samples and 88% of the samples of a bank of images obtained with a Q-band available in the literature consisting of 119 chromosome studies were successfully classified. The proposed work is a part of an desktop application that allows cytogeneticist to automatically generate cytogenetic reports.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Genomic variations and chromosomal abnormalities · Gene expression and cancer classification · Fractal and DNA sequence analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Intelligent Systems Department, Polytechnic University of Victoria, Tamaulipas 87138, Mexico
Funding
Consejo Tamaulipeco de Ciencia y Tecnología
References (40)
Show source-provided references
1. Karyotyping Techniques of Chromosomes: A Survey10.14445/22312803/IJCTT-V22P107 ↗
2. Cytogenetics: Past, Present And Future
3. Performance of machine learning methods applied to structural MRI and ADAS cognitive scores in diagnosing Alzheimer’s disease10.1016/j.bspc.2018.08.009 ↗
4. Detection of Parkinson’s disease based on voice patterns ranking and optimized support vector machine10.1016/j.bspc.2018.08.029 ↗
5. Performance of machine learning methods in diagnosing Parkinson’s disease based on dysphonia measures10.1007/s13534-017-0051-2 ↗
6. Parallel Patient Karyotype Information System using Multi-threads
7. Zhang, H., and Albitar, M. (2016). Computer-Assisted Karyotyping. (U.S. Patent 9,336,430).
8. Hosny, K., and de la Calleja, J. (2013). Automatic Chromosome Classification using Support Vector Machines. Pattern Recognition: Methods and Applications, CreateSpace Independent Publishing Platform. Chapter 13.
9. A review of metaphase chromosome image selection techniques for automatic karyotype generation10.1007/s11517-015-1419-z ↗
10. A Survey of Hierarchical Classification Across Different Application Domains10.1007/s10618-010-0175-9 ↗
11. Xiong, Z., Wu, Q., and Castlemen, K.R. (2002, January 12–13). Enhancement, Classification And Compression Of Chromosome Images. Proceedings of the Workshop on Genomic Signal Processing and Statistics (GENSIPS), Raleigh, NC, USA.
12. Qiu, Y., Song, J., Lu, X., Li, Y., Zheng, B., Li, S., and Liu, H. (2014). Feature Selection for the Automated Detection of Metaphase Chromosomes: Performance Comparison Using a Receiver Operating Characteristic Method. Anal. Cell. Pathol.10.1155/2014/565392 ↗
13. On the Application of Artificial Neural Networks in Analyzing and Classifying the Human Chromosomes10.3844/jcssp.2006.72.75 ↗
14. Mashadi, N.T., and Seyedin, S.A. (2007, January 12–15). Direct classification of human G-banded chromosome images using support vector machines. Proceedings of the 2007 9th International Symposium on Signal Processing and Its Applications, Sharjah, United Arab Emirates.
15. Kusakci, A.O., and Gagula-Palalic, S. (2014). Human Chromosome Classification Using Competitive Support Vector Machine Teams. Southeast Eur. J. Soft Comput.10.1109/BHI.2014.6864442 ↗
16. Karyotyping of comparative genomic hybridization human metaphases by using support vector machines10.1002/cyto.10027 ↗
17. Hadziabdic, K. (2012). Classification of chromosomes using nearest neighbor classifier. South. Eur. J. Soft Comput.
18. Sethakulvichai, W., Manitpornsut, S., Wiboonrat, M., Lilakiatsakun, W., Assawamakin, A., and Tongsima, S. (June, January 30). Estimation of band level resolutions of human chromosome images. Proceedings of the 2012 Ninth International Conference on Computer Science and Software Engineering (JCSSE), Bangkok, Thailand.10.1109/JCSSE.2012.6261965 ↗
19. Automatic Karyotyping of Human Chromosomes Using Band Patterns
20. Chromosome classification using dynamic time warping10.1016/j.patrec.2007.09.017 ↗
21. Polarity-free automatic classification of chromosomes10.1016/S0167-9473(00)00022-0 ↗
22. A classification-driven partially occluded object segmentation (CPOOS) method with application to chromosome analysis10.1109/78.720391 ↗
23. A survey of neural network based automated systems for human chromosome classification10.1007/s10462-016-9515-5 ↗
24. Application of artificial neural networks to chromosome classification10.1002/cyto.990140607 ↗
25. Automated Classification of Metaphase Chromosomes: Optimization of an Adaptive Computerized Scheme10.1016/j.jbi.2008.05.004 ↗
26. A modular framework for the automatic classification of chromosomes in Q-band images10.1016/j.cmpb.2011.07.013 ↗
27. Nabil, A., and Sarra, F. (2017). Q-Banding. Reference Module in Life Sciences, Elsevier.10.1016/B978-0-12-809633-8.06986-7 ↗
28. Yang, X., Wen, D., Cui, Y., Cao, X., Lacny, J., and Tseng, C. (2009, January 1–7). Computer Based Karyotyping. Proceedings of the 2009 Third International Conference on Digital Society, Cancun, Mexico.10.1109/ICDS.2009.9 ↗
29. A novel and maximum-likelihood segmentation algorithm for touching and overlapping human chromosome images
30. Gagula-Palalic, S., and Can, M. (2012). Automatic Segmentation of Human Chromosomes. South. Eur. J. Soft Comput.10.21533/scjournal.v1i2.65 ↗
31. Moradi, M., Setarehdan, S.K., and Ghaffari, S.R. (2003, January 26–27). Automatic Locating the Centromere on Human Chromosome Pictures. Proceedings of the 16th IEEE Conference on Computer-based Medical Systems, New York, NY, USA. CBMS’03.
32. Automatic segmentation of metaphase cells based on global context and variant analysis10.1016/j.patcog.2007.05.013 ↗
33. Chromosome classification based on the band profile similarity along approximate medial axis10.1016/j.patcog.2007.05.016 ↗
34. Gagula-Palalic, S., and Can, M. (2012). Extracting Gray Level Profiles of Human Chromosomes by Curve Fitting. South. Eur. J. Soft Comput.10.21533/scjournal.v1i2.63 ↗
35. Separation of overlapped chromosomes and pairing of similar chromosomes for karyotyping analysis10.1016/j.measurement.2013.11.024 ↗
36. New Features for Automatic Classification of Human Chromosomes: A Feasibility Study10.1016/j.patrec.2005.06.011 ↗
37. Badawi, A.M., Hassan, K., Aly, E., and Messiha, R.A. (2003, January 27–30). Chromosomes classification based on neural networks, fuzzy rule based, and template matching classifiers. Proceedings of the 2003 46th Midwest Symposium on Circuits and Systems, Cairo, Egypt.
38. Poletti, E., Grisan, E., and Ruggeri, A. (2008, January 20–25). Automatic classification of chromosomes in Q-band images. Proceedings of the 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancouver, BC, Canada.10.1109/IEMBS.2008.4649560 ↗
39. Markou, C., Maramis, C., Delopoulos, A., Daiou, C., and Lambropoulos, A. (2012). Automatic Chromosome Classification Using Support Vector Machines, iConceptPress.
40. Shaffer, L.G., McGowan-Jordan, J., and Schmid, M. (2013). ISCN 2013: An International System for Human Cytogenetic Nomenclature (2013), Karger Medical and Scientific Publishers.