White blood cell (WBC) counting analysis in blood smear images using various color segmentation methods

Abstract White blood cells (WBCs) is closely related to human immunity system which is useful to fight viruses and bacteria. Cancer therapy effectiveness and some of the blood-related diseases can be determined from the count of cell region. Traditionally, WBC count is done manually which yields inaccurate results as the blood sample increases. Moreover, even though hematology counter device is fast and accurate, it is very costly. These problems has led to the invention of cost effective Computer Aided System (CAS) which analyzes the blood smeared images obtained from microscope. In CAS, the most important step is segmentation and any failure at this stage will cause inaccuracy in the subsequent stages. Realizing the importance of segmentation, this paper investigated various segmentation methods for the purpose of WBC counting based on color band thresholding procedure. Initially, color space correction based on L∗a∗b∗ color space was applied to standardize the image color intensity. Next, segmentation process was conducted to prune out the WBC region from the background by combining color analysis of RGB, CMYK and HSV with Otsu thresholding. Morphological filter was employed as the segmented image contained noises would affect the system performance. Henceforth, Connected Component Labelling (CCL) was done to distinguish the small particles that still existed in the image. Eventually, Circle Hough Transform (CHT) was applied to identify and count the WBC including the one in the clump region. Overall system performance was accessed and it was found that by using S color component of HSV, color space provided the highest WBC segmentation accuracy which was 96.92%. Meanwhile, for the combination of two color bands; S-C produced 96.56% of WBC counting accuracy. Another interesting finding was that the usage of nucleus based detection was superior compared to cytoplasm-based detection for WBC counting purpose.

[1]  Salim Arslan,et al.  A color and shape based algorithm for segmentation of white blood cells in peripheral blood and bone marrow images , 2014, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[2]  N. J. Janwe,et al.  Segmentation Based Approach to Detect Parasites and RBCs in Blood Cell Images , 2011 .

[3]  Osman Kalender,et al.  Automatic segmentation, counting, size determination and classification of white blood cells , 2014 .

[4]  Leyza Baldo Dorini,et al.  Semiautomatic White Blood Cell Segmentation Based on Multiscale Analysis , 2013, IEEE Journal of Biomedical and Health Informatics.

[5]  Cecilia Di Ruberto,et al.  White Blood Cells Identification and Counting from Microscopic Blood Image , 2013 .

[6]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[7]  V. A. Chakkarwar,et al.  White Blood Cell Segmentation and Counting Using Global Threshold , 2013 .

[8]  Vincenzo Piuri,et al.  All-IDB: The acute lymphoblastic leukemia image database for image processing , 2011, 2011 18th IEEE International Conference on Image Processing.

[9]  Mohd Razali Md Tomari,et al.  An empirical framework for automatic red blood cell morphology identification and counting , 2015 .

[10]  Wan Nurshazwani Wan Zakaria,et al.  RED BLOOD CELL COUNTING ANALYSIS BY CONSIDERING AN OVERLAPPING CONSTRAINT , 2015 .

[11]  Chirag Juyal,et al.  Architecture for Playing Songs using Audio Content Analysis according to First Chosen Song , 2012 .

[12]  Haider Adnan Khan,et al.  Counting clustered cells using distance mapping , 2013, 2013 International Conference on Informatics, Electronics and Vision (ICIEV).

[13]  Xiongfei Li,et al.  A multi-scale 3D Otsu thresholding algorithm for medical image segmentation , 2017, Digit. Signal Process..

[14]  May D. Wang,et al.  Automated cell counting and cluster segmentation using concavity detection and ellipse fitting techniques , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[15]  Erik Valdemar Cuevas Jiménez,et al.  An Improved Computer Vision Method for White Blood Cells Detection , 2013, Comput. Math. Methods Medicine.

[16]  Rahul Kumar Gupta,et al.  Detection and Counting of Red Blood Cells in Blood Cell Images using Hough Transform , 2012 .

[17]  Dipti Patra,et al.  Automated cell nucleus segmentation and acute leukemia detection in blood microscopic images , 2010, 2010 International Conference on Systems in Medicine and Biology.

[18]  Xiaomei Li,et al.  White Blood Cell Segmentation by Color-Space-Based K-Means Clustering , 2014, Sensors.

[19]  K. Thilagavathi,et al.  Automatic red blood cell counting using hough transform , 2013, 2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES.