Detecting distorted and benign blood cells using the Hough transform based on neural networks and decision trees - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 395

tion algorithm. Based on the experimental results, these procedures have demonstrated high
accuracies, and these models appear successful at predicting the healthy and distorted cells
present in blood from a person with sickle-cell anemia. I calculated the performance of the
models, using three statistical measures: classification accuracy, sensitivity, and specificity. As
a result, I have concluded that this algorithm has correctly segmented and classified about
99.98% of all input cells, which may have contributed to the improved diagnosis of sickle-cell
anemia. The experimental results have shown that the effectiveness reaches to 96.9% in the
case of applying an NN and 92.9% when using a C&R tree. Therefore, the proposed algorithm
is very effective for detecting benign and distorted RBCs, and the NN is more efficient than a
C&R tree for testing the quality of the detection algorithm.
References
[1] U. S. Department of Health & Human Services, National Institute of Health, 2014. ht-
tp://www.nhlbi.nih.gov/ .
[2] Image Processing Toolbox, is available through MATLAB's help menu, or online at:
http://www.mathworks.com/help/images/index.html .
[3] Stockman GC, Agrawala AK. Equivalence of Hough curve detection to template
matching. Commun ACM. 1977;20:820-822.
[4] Elsalamony HA, Elsayad AM. Bank direct marketing based on neural network. Int J
Eng Adv Technol IJEAT. 2013;2(6):392 ISSN: 2249-8958.
[5] Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. Bel-
mont, CA: Wadsworth; 1998.
[6] Devi BR, Rao KN, Sety SP, Rao MN. Disaster prediction system using IBM SPSS data
mining tool. Int J Eng Trends Technol (IJETT). 2013;4(8):3352 ISSN Volume: 2231.
[7] Hirimutugoda YM, Wijayarathna G. Image analysis system for detection of red cell
disorders using artificial neural networks. Sri Lanka J Biomed Inform 2010;1(1):35-42.
[8] Das DK, Chakraborty C, Mitra B, Maiti AK, Ray AK. Quantitative microscopy ap-
proach for shape-based erythrocytes characterization in anaemia. J Microsc
2013;249(Pt 2):136-49. Received 7 August 2012; accepted 11 November 2012.
[9] Thirusitampalam K, Hossain MJ, Ghita O, Whelan PF. A novel framework for cellu-
lar tracking and mitosis detection in dense phase contrast microscopy images. IEEE J
Biomed Health Informat. 2013;17(3):42-653.
[10] Khan HA, Maruf GM. Counting clustered cells using distance mapping. In: International
conference on informatics, electronics & vision (ICIEV); 2013:1-6.
[11] Mushabe MC, Dendere R, Douglas TS. Automated detection of malaria in Giemsa-stained
thin blood smears. In: 35th annual international conference of the IEEE engineering in
medicine and biology society EMBC; 2013:3698-3701.
[12] Mukherjee R. Morphometric evaluation of preeclamptic placenta using light micro-
scopic images. Biomed Res Int 2014;2014:9 pages. Article ID 293690.
[13] Fleyeh H, Biswas R, Davami E. Traffic sign detection based on AdaBoost color segmentation
and SVM classification. In: EUROCON conference, IEEE, 1-4 July; 2013:2005-2010.
[14] Freeman WJ. The physiology of perception. Sci Am. 1991;264(2):78-85 University of
California, Berkeley.
[15] Chaudhuri B, Bhatacharya U. Eicient training and improved performance of mul-
tilayer perceptron in patern classiication. Neurocomputing. 2000;34:1-27.