Abstract  Leukaemia is a cancer of blood that causes more dea th than any other cancers among children and young adults under the age of 20. This disease can be cured if i t is detected and treated at the early stage. Based on this argument, the requirement for fast analysis of blood cells for le ukaemia is of paramount importance in the healthcar e industry. This paper presents the classification of White Blood Cells (W BC) inside the Acute Lymphoblastic Leukaemia (ALL) and Acute Myelogenous Leukaemia blood samples by using the Mu ltilayer Perceptron (MLP) and Simplified Fuzzy ARTMAP (SFAM) neural networks. Here, the WBC will be classified a s lymphoblast, myeloblast and normal cell for the purpose of categorization of acute leukaemia types. Two differ ent training algorithms namely Levenberg3Marquardt and Bayesian Regulation algorithms have been employed to train t he MLP network. There are a total of 42 input features that consist of the size, shape and colour based features, have been ex tracted from the segmented WBCs, and used as the ne ural network inputs for the classification process. The classification results indicating that all networks have produced good classification performance for the overall proposed features. Howe ver, the MLP network trained by Bayesian Regulation algorithm has produced the best classification performance with t esting accuracy of 95.70% for the overall proposed features. Thus, the results significantly demonstrate the suitability o f the proposed features and classification using ML P and SFAM networks for classifying the acute leukaemia cells in blood samp le.    

References

[1] Aeinfar V., Mazdarani H., Deregeh F., Hayati M., and Payandeh M., Multilayer Perceptron Neural Network with Supervised Training Method for Diagnosis and Predicting Blood Disorder and Cancer, in Proceedings of IEEE International Symposium on Industrial Electronics , Korea, pp. 2075-2080, 2009.

[2] Almadani A., Diagnosing Breast Cancer Disease Using Fuzzy ARTMAP Technique, Master s Thesis , University Utara Malaysia, 2007.

[3] Demir C. and Yener B., Automated Cancer Diagnosis Based on Histopathological Images: A Systematic Survey, Technical Report, Rensselaer Polytechnic Institute, 2005.

[4] Doan C. and Liong S., Generalization for Multilayer Neural Network Bayesian Regularization or Early Stopping, in Proceedings of the 2 nd Conference Asia Pacific Association of Hydrology and Water Resources , Singapore, pp. 1-8, 2004.

[5] Gonzalez R. and Woods R., Digital Image Processing , Prentice Hall, New Jersey, USA, 2007.

[6] Hamdan H., The Application of Backpropagation Neural Network in the Prognosis of Breast Cancer, Master s Thesis , University Malaya, Malaysia, 2004.

[7] Harun N., Mashor M., and Rosline H., Calculation of Blast Area for Acute Leukemia Blood Cells Images, in Proceedings of the International Postgraduate Conference on Engineering , Malaysia, 2010.

[8] Henry D., Latest News in Blood Cancer Research , CANCER Care, New York, 2010.

[9] Hsieh S., Wang Z., Cheng P., Lee I., Hsieh S., and Lai F., Leukemia Cancer Classification Based on Support Vector Machine, in Proceedings of the 8 th IEEE International Conference on Industrial Informatics , Japan, pp. 819-824, 2010.

[10] Kennedy J., Hematopathology V Acute Leukemia, Acute Lymphoblastic Leukemia, Chronic Lymphocytic Leukemia, and Hairy Cell Leukemia, 2002.

[11] Kisi O., Multi-Layer Perceptrons with Levenberg-Marquardt Training Algorithm for Suspended Sediment Concentration Prediction and Estimation, Hydrological Sciences Journal , vol. 49, no. 6, pp. 1025-1040, 2004.

[12] Lim G., Overview of Cancer in Malaysia, Japanese Journal of Clinical Oncology , vol. 32, no. 1, pp. 37-42, 2002.

[13] Lim G., Rampal S., and Yahaya H., Cancer Incidence in Peninsular Malaysia, The Third Report of the National Cancer Registry , Malaysia, 2008.

[14] MacKay D., A Practical Bayesian Framework for Backpropagation Networks, Neural Computation , vol. 4, no. 3, pp. 448-472, 1992.

[15] Mango L., Computer-Assisted Cervical Cancer Screening using Neural Networks, Cancer Letters , vol. 77, no. 2-3, pp. 155-162, 1994.

[16] Mohapatra S. and Patra D., Automated Cell Nucleus Segmentation and Acute Leukemia Detection in Blood Microscopic Images, in Proceedings of International Conference on Systems in Medicine and Biology , India, pp. 49- 54, 2001.

[17] Ongun G., Halici U., Leblebicioglu K., Atalay V., Beksac M., and Beksac S., Feature Extraction and Classification of Blood Cells for an Automated Differential Blood Count System, in Proceedings of the International Joint Conference on Neural Networks , USA, pp. 2461-2466, 2001.

[18] Priyankara G., Seneviratne O., Silva R., Soysa W., and Silva C., An Extensible Computer Vision Application for Blood Cell Recognition and Analysis, pp. 1-13, 2006.

[19] Rajasekaran S. and Pai G., Image Recognition Using Simplified Fuzzy ARTMAP Augmented with a Moment Based Feature Extractor, International Journal of Pattern Recognition and Artificial Intelligence , vol. 14, no. 8, pp. 1081-1095, 2000.

[20] Reta C., Altamirano L., Gonzalez J., Diaz R., and Guichard J., Segmentation of Bone Marrow Cell Images for Morphological Classification of Acute Leukemia, in Proceedings of the 23 rd International Florida Artificial Intelligence Research Society Conference , USA, pp. 86-91, 2010. 364 The International Arab Journal of Informa tion Technology, Vol. 10, No. 4, July 2013

[21] Salam M., Mohamad D., and Salleh S., Malay Isolated Speech Recognition Using Neural Network: A Work in Finding Number of Hidden Nodes and Learning Parameters, The International Arab Journal of Information Technology , vol. 8, no. 4, pp. 364-371, 2011.

[22] Salihah A., Mashor M., Harun N., Abdullah A., and Rosline H., Improving Colour Image Segmentation on Acute Myelogenous Leukaemia Images Using Contrast Enhancement Techniques, in Proceedings of IEEE EMBS Conference on Biomedical Engineering & Sciences , Malaysia, pp. 246-251, 2010.

[23] Saptoro A., Yao H., Tad M., and Vuthaluru H., Prediction of Coal Hydrogen Content for Combustion Control in Power Utility using Neural Network Approach, Chemometrics and Intelligent Laboratory Systems , vol. 94, no. 2, pp. 149-159, 2008.

[24] Toure A. and Basu M., Application of Neural Network to Gene Expression Data for Cancer Classification, in Proceedings of the International Joint Conference on Neural Networks , USA, pp. 583-587, 2001.

[25] Venkatesan P. and Suresh M., Classification of Renal Failure Using Simplified Fuzzy Adaptive Resonance Theory Map, International Journal of Computer Science and Network Security , vol. 9, no. 11, pp. 129-134, 2009. Aimi Abdul Nasir received her B.Eng (Hons) degree in Mechatronic Engineering from Universiti Malaysia Perlis in 2009 and MSc in Biomedical Electronic Engineering from the Universiti Malaysia Perlis, in 2011. Currently, she is pursuing her PhD in Biomedical Electronic Engineering at UniMAP. Her research interests include image processing, medical image analysis, artificial neur al network and medical diagnostic system. Mohd Yusoff Mashor obtained his B.Eng. degree in control and computer engineering from University of Westminster, London in 1990. Under Universiti Sains Malaysia RLKA scheme, he pursued his MSc in control engineering and information technology at University of Sheffield in 1991. In 1995, he obtained his PhD specialized in neural network from University of Sheffield. He started his service in USM in the School of Electrical and Electronic Engineering in December 1995. He is currently the Dean of Postgraduate Studies, Universiti Malaysia Perlis. He has developed his expertise in neural network, system identification, fuzzy logic, control system, intelligent forecasting/prediction, image processing and medical diagnostic systems. He has authored and co-authored for more than 100 research publications in the form of book chapters, refereed journals and conferences at the international and national levels. Rosline Hassan obtained her medical degree, MD from Universiti Kebangsaan Malaysia and MMed in Pathology from Universiti Sains Malaysia. She is currently the head of the Department of Hematology, School of Medical Sciences, Universiti Sains Malaysia. Her research interests include haematopathology with special interest in molecular aspect of haematologi cal disorders, leukaemias and myeloproliferative disorders, red cell disorders inclusive of thalasse mia, cytogenetic of leukaemia, cell culture studies and stem cell studies. She has published numerous research articles in the international journals and conferen ce proceedings.