Volume 15, Issue 2 (9-2018)                   JSDP 2018, 15(2): 45-54 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Karimi A, Hoseini L S. An Optimal Algorithm for Dividing Microscopic Images of Blood for the Diagnosis of Acute Pulmonary Lymphoblastic Cell Using the FCM Algorithm and Genetic Optimization. JSDP. 2018; 15 (2) :45-54
URL: http://jsdp.rcisp.ac.ir/article-1-567-en.html
Arak Branch, Islamic Azad UNiversity
Abstract:   (800 Views)
Cancer is type of disease caused by irregular, uncontrollable growth of blood cells in bone marrow. The process of generating three main blood cells including pallets, red and white blood cells, is started from a progenitor cell called as blast. Blast generates a considerable number of immature cells which are developed affected by differentiation factors. If any interruption occurs during this process, leukemia may be initiated. 
Diagnosis of leukemia is performed at hospitals or medical centers by examination of the blood tissue smeared across a slide and under a microscope by a pathologist. Processing the digital images of blood cells, in order to improve the quality of the image or highlighting the malicious segments of the image, is important in early stages of the disease. 
There are four types of leukemia consisting acute or chronic and myeloid or lymphocytic. Acute lymphocytic (or lymphoblastic) leukemia (ALL) is concentrated in this study. ALL is caused by continuous generation of immature, malignant lymphocytes in bone marrow which are speeded by blood circulation to other organs. 
In this research, fuzzy C-means (FCM) algorithm is applied to blood digital images for clustering purpose, neural networks for feature selection and Genetic Algorithm (GA) for optimization. This model diagnoses ALL at early stages and categorizes it into three morphological subcategories (i.e., L1, L2, and L3).
For performance evaluation of the proposed method, 38 samples of patients with ALL were collected. It was performed on 68 microscopic images in terms of 15 features and yielded to higher percentage of sensitivity, specificity, and accuracy for 10 out of 15 features. The proposed method was compared to three recent methods. The evaluations showed that the sensitivity, specificity and accuracy reached to 85.15%, 98.17% and 96.53%, respectively. 

Full-Text [PDF 2627 kb]   (318 Downloads)    
Type of Study: Research | Subject: Paper
Received: 2017/08/3 | Accepted: 2018/05/16 | Published: 2018/09/16 | ePublished: 2018/09/16

1. [1] Amin MM, Kermani S, Talebi A, Oqhli MG. Recognition of Acute Lymphoblastic Leukemia Cells in Microscopic Images Using K-Means Clustering and Support Vector Machine Classi-fier J Med Signals Sens. 2015 Jan-Mar;5(1):49-58. [PMID]
2. [2] Dan L. Longo, Anthony S. Fauci, Dennis L. Kasper, Stephen L. Hauser, Larry Jameson, Joseph Loscalzo. Harrison's Principles of Inter-nal Medicine, 18th Edition, Chapter 110. Malig-nancies of Lymphoid Cells. Clinical Features, Treatment, and Prognosis of Specific Lymphoid Malignancies. 2015.
3. [3] Collier, J.A.B Oxford Handbook of Clinical Specialties, Third Edition. Oxford. 1991; pp. 810. ISBN 0-19-262116-5.
4. [4] ACS : How Is Acute Lymphocytic Leukemia Classified?". 2016. [Available from:http:// www. Cancer. org/docroot/CRI/ content/ CR-I_2_4_3X_ How_ Is_ Acute_ Lymphocytic_ Leukemia_ Classified. asp? rnav= cri].
5. [5] Hoffbrand AV, Moss PAH and Pettit JE. "Essential Haematology", Blackwell, 5th ed., 2006.
6. [6] Messinger YH, Gaynon PS, Sposto R, van der Giessen J, Eckroth E, Malvar J, et al. Therapeutic Advances in Childhood Leukemia & Lymphoma (TACL) Consortium. "Bortezomib with chemo-therapy is highly active in advanced B-precursor acute lymphoblastic leukemia: Thera-peutic Advances in Childhood Leukemia & Lymphoma (TACL) Study". Blood. 2012; 120 (2): 285–90. [DOI:10.1182/blood-2012-04-418640] [PMID]
7. [7] Lambrou GI, Papadimitriou L, Chrousos GP, Vlahopoulos SA. "Glucocorticoid and pro-teasome inhibitor impact on the leukemic lymphoblast: multiple, diverse signals converg-ing on a few key downstream regulators". Mol Cell Endocrinol. 2012; 351 (2): 142–51. [DOI:10.1016/j.mce.2012.01.003] [PMID]
8. [8] Halim NH, Mashor MY, Hassan R. Automatic blasts counting for acute leukemia based on blood samples. Int J Res Rev Comput Sci 2:971, 2011.
9. [9] Heydari H, Souratgar A.A, Rashidi I, Malekpoor N, Parvizi A. Diagnosis of leukemia [a particular type of acute lymphoblastic leukemia by using artificial neural networks. Iranian Student Conference on Electrical Engineering, Tarbiat Modarres University. 24- 26 September 1389. [PMID] [PMCID]
10. [10] Luque-Baena RM, Urda D, Subirats JL, Franco L, Jerez JM. Application of genetic algorithms and constructive neural networks for the analysis of microarray cancer data. Theoretical Biology and Medical Modelling 2014, 11(Suppl 1):S7. [DOI:10.1186/1742-4682-11-S1-S7] [PMID] [PMCID]
11. [11] Soltanzadeh R, Rabbani H. Talebi A. Classification of Three Types of Red Blood Cells in Peripheral Blood Smear in Proc. IEEE Int. Conf. on Signal Processing, pp. 707 – 710, China, 2010. [DOI:10.1109/ICOSP.2010.5655754]
12. [12] Moradi P, Ahmadian S, Akhalghian F. An effective trust-based recommendation method using a novel graph clustering algorithm. Statis-tical Mechanics and its Applications. Volume 436, 15 October 2015, Pages 462–481
13. [13] ZohourParvaz F, Fatemizadeh E, Behnam H. Speed improvement in graph-cuts-based registra-tion for non-rigid image registration of brain magnetic resonance images. JSDP. 2017; 13 (4) :79-92 [DOI:10.18869/acadpub.jsdp.13.4.79]

Add your comments about this article : Your username or Email:

Send email to the article author

© 2015 All Rights Reserved | Signal and Data Processing