Current Science

Open Access Open Access  Restricted Access Subscription Access

Automatic Recognition of Acute Lymphoblastic Leukemia using Multi-SVM Classifier


Affiliations
1 Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Islamic Republic of
2 Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran, Islamic Republic of
 

Acute lymphoblastic leukemia (ALL) is the most popular form of white blood cells cancer in children. It is classified into three forms of L1, L2 and L3. Typically, it is identified through screening of blood smearsvia pathologists. Since this is laborious and tedious, automatic systems are desired for suitable detection; but the high similarity between morphology of ALL forms and that of normal, reactive and a typical lymphocytes, makes the automatic detection a challenging problem. This study tried to improve the accuracy of detection based on principle component analysis (PCA). After segmenting nuclei of cells, numerous features were extracted. The first six components of this feature space were used for the binary and multiclass support vector machine classifiers. An expert pathologist was used to appraise this method as a gold standard. A collation with similar work indicated that using PCA instead of using exclusively selected features enhanced the average sensitivity and specificity of classification up to 10%. The results demonstrate that this algorithm performs better than similar studies. Its permissible efficiency for identifying ALL and its sub-types as well as other lymphocyte forms makes it an associate diagnostic device for pathologists.

Keywords

ALL, Fuzzy C-means Method, PCA Analysis, SVM Classifier.
User
Notifications
Font Size

  • Sinha, N. and Ramakrishnan, A., Automation of differential blood count. In TENCON 2003, Conference on Convergent Technologies for the Asia-Pacific Region, IEEE, 2003.

  • Theera-Umpon, N., White Blood Cell Segmentation and Classification in Microscopic Bone Marrow Images, Fuzzy systems and knowledge discovery, 2005, p. 485.

  • Theera-Umpon, N. and Dhompongsa, S., Morphological granulometric features of nucleus in automatic bone marrow white blood cell classification. In IEEE Transactions on Information Technology in Biomedicine, 2007, vol. 11, issue 3.

  • Madhloom, H. et al., An automated white blood cell nucleus localization and segmentation using image arithmetic and automatic threshold. J. Appl. Sci., 2010, 10, 959-966.

  • Halim, N. H. A., Mashor, M. Y. and Hassan, R., Automatic blasts counting for acute leukemia based on blood samples. Int. J. Res. Rev. Comput. Sci., 2011, 2(4), 278-284.

  • Nee, L. H., Mashor, M. Y. and Hassan, R., White blood cell segmentation for acute leukemia bone marrow images. J. Med. Imaging Health Inform., 2012, 2(3), 278-284.

  • Mohapatra, S., Patra, D. and Satpathy, S., An ensemble classifier system for early diagnosis of acute lymphoblastic leukemia in blood microscopic images. Neural Comput. Appl., 2014, 24(7-8), 1887-1904.

  • Abbas, N. and Mohamad, D., Automatic color nuclei segmentation of leukocytes for acute leukemia. Res. J. Appl. Sci., Eng. Technol., 2014, 7(14), 2987-2993.

  • Amin, M. M. et al., Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier. J. Med. Signals Sensing, 2015, 5(1), 49.

  • Mokhtar, N. et al., Image enhancement techniques using local, global, bright, dark and partial contrast stretching for acute leukemia images. Anal. Cell. Pathol., 2003, 25, 1-36.

  • Rodenacker, K. and Bengtsson, E., A feature set for cytometry on digitized microscopic images. Anal. Cell. Pathol., 2003, 25(1), 1-36.

  • Keller, J., Krisnapuram, R. and Pal, N. R., Fuzzy Models and Algorithms fo r Pattern Recognition and Image Processing, Springer Science & Business Media, 2005, vol. 4.

  • Ashtiyani, M., Asadi, S. and Birgani, P. M., ICA-based EEG classification using fuzzy C-mean algorithm. In 3rd International Conference on IEEE, Information and Communication Technologies: From Theory to Applications, 2008.

  • Ashtiani, M., Asadi, S. and Goudarzi, P. H., A new method in transmitting encrypted data by FCM algorithm. In Information and Communication Technologies, ICTTA’06, IEEE, 2006.

  • Birgani, P. M., Ashtiyani, M. and Asadi, S., MRI segmentation using fuzzy c-means clustering algorithm basis neural network. In 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA, IEEE, 2008.

  • Khajehpour, H. et al., Detection and segmentation of erythrocytes in blood smear images using a line operator and watershed algorithm. J. Med. Signals Sens., 2013, 3(3), 164.

  • Ashtiyani, M. et al., Transmitting encrypted data by wavelet transform and neural network. In IEEE International Symposium on Signal Processing and Information Technology, 2007.

  • Alizadeh, A., Fatemizadeh, E. and Deevband, M. R., Investigation of Brain Default Network’s activation in autism spectrum disorders using group independent component analysis. In 21st Iranian Conference on Biomedical Engineering, IEEE, 2014.

  • Abdi, H. and Williams, L. J., Principal Component Analysis, Wiley interdisciplinary reviews: computational statistics, 2010, 2(4), 433-459.

  • Mansoory, M. S., Ashtiyani, M. and Tajik, H., Cardiac motion evaluation for disease diagnosis using ICA basis neural network. In IACSITSC'09, International Association, IEEE Computer Science and Information Technology-Spring Conference, 2009.

  • Osman, N. A. A. et al., 4th Kuala Lumpur International Conference on Biomedical Engineering 2008, BIOMED 2008, 25-28 June 2008, Kuala Lumpur, Malaysia, Springer Science & Business Media, 2008, vol. 21.

  • Mirmohammadi, P., Taghavi, A. and Ameri, A., Automatic Recognition of Acute Lymphoblastic Leukemia Cells from Microscopic Images.

  • Ashtiyani, M. et a l., EEG classification using neural networks and independent component analysis. In 4th Kuala Lumpur International Conference on Biomedical Engineering, Springer, 2008, pp. 179-182; https://link.springer.com/chapter/10.1007/978-3-540-69139-6 48

  • Jolliffe, I., Principal Component Analysis, Wiley Online Library, 2002.

  • Smith, L. I., A Tutorial on Principal Components Analysis, Cornell University, USA, 2002, vol. 51, p. 52.

  • Mohapatra, S. and Patra, D., Automated cell nucleus segmentation and acute leukemia detection in blood microscopic images. In International Conference on IEEE Systems in Medicine and Biology (ICSMB), 2010.

  • Smola, A. J. and Scholkopf, B., A tutorial on support vector regression. Stat. Comput., 2004, 14(3), 199-222.

  • Alvar, A. A., Deevband, M. R. and Ashtiyani, M., Neutron spectrum unfolding using radial basis function neural networks. Appl. Radiat. Isot., 2017, 129, 35-41.


Abstract Views: 359

PDF Views: 114




  • Automatic Recognition of Acute Lymphoblastic Leukemia using Multi-SVM Classifier

Abstract Views: 359  |  PDF Views: 114

Authors

Pouria Mirmohammadi
Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Islamic Republic of
Amirhossien Rasooli
Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran, Islamic Republic of
Meghdad Ashtiyani
Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Islamic Republic of
Morteza Moradi Amin
Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran, Islamic Republic of
Mohammad Reza Deevband
Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of Medical Sciences, Tehran, Iran, Islamic Republic of

Abstract


Acute lymphoblastic leukemia (ALL) is the most popular form of white blood cells cancer in children. It is classified into three forms of L1, L2 and L3. Typically, it is identified through screening of blood smearsvia pathologists. Since this is laborious and tedious, automatic systems are desired for suitable detection; but the high similarity between morphology of ALL forms and that of normal, reactive and a typical lymphocytes, makes the automatic detection a challenging problem. This study tried to improve the accuracy of detection based on principle component analysis (PCA). After segmenting nuclei of cells, numerous features were extracted. The first six components of this feature space were used for the binary and multiclass support vector machine classifiers. An expert pathologist was used to appraise this method as a gold standard. A collation with similar work indicated that using PCA instead of using exclusively selected features enhanced the average sensitivity and specificity of classification up to 10%. The results demonstrate that this algorithm performs better than similar studies. Its permissible efficiency for identifying ALL and its sub-types as well as other lymphocyte forms makes it an associate diagnostic device for pathologists.

Keywords


ALL, Fuzzy C-means Method, PCA Analysis, SVM Classifier.

References





DOI: https://doi.org/10.18520/cs%2Fv115%2Fi8%2F1512-1518