SEGMENTATION OF CONNECTED RED BLOOD CELLS BASED ON DISTANCE PER DISPLACEMENT RATIO MAXIMIZATION CRITERION

Authors

  • Tamnuwat Valeeprakhon Department of Computer Engineering, Faculty of Engineering, Khon Kaen University, Khon Kaen, Thailand
  • Nawapak Eua-Anant Department of Computer Engineering, Faculty of Engineering, Khon Kaen University, Khon Kaen, Thailand

DOI:

https://doi.org/10.20319/mijst.2016.s11.132143

Keywords:

Red Blood Cell Counting, Segmentation of Connected Red Blood Cells, Circular Compactness Shape Factor, the Distance per Displacement Ratio

Abstract

Red blood cell counting is difficult to perform by automated visual inspection because of the large number of connected RBCs in blood smear slides. This paper presents anew algorithm to segment connected RBCs in blood smear images based on the distance per displacement ratio criterion. First, RBCs were separated from white blood cells and platelets by performing thresholding on the b* component in Lab color space. Next, connected RBCs and single RBCs were separated by using the Circular Compactness Shape Factor criterion. Later, points on boundaries of connected RBCs with high curvature were marked as concave points. Each concave point was then paired to a nearby concave point that maximizes the distance per displacement ratio criterion. Finally, a set of paired concave points was used as information for segmenting connected RBCs. Experimental results of RBC counting, including connected and single RBCs, on 50 blood smear images, revealed that the proposed algorithm can achieve an average accuracy of up to 99.22%

References

N Kanitsap, (2010) Iron status and prevalence of iron deficiency anemia in the elderly. Official Journal of the Thai Society of Hematology and the National Blood Centre The Thai Red Cross Society, 20, 287-296.

S Kareem, R.C.S Morling, I Kale (2011). A novel method to count the red blood cells in thin blood films, IEEE International Symposium Circuits and Systems, 1021- 1024. doi: 10.1109/ISCAS.2011.5937742

Pradipta Maji, Ankita Mandal, Madhura Ganguly, Sanjoy Saha. (2015) an automated method for counting and characterizing red blood cells using mathematical morphology. International conference Advances in Pattern Recognition, 1-6. Doi: 10.1109/ICAPR.2015.70506

Sumeet, G Rani. (2014). Automatic red blood cell counting using watershed segmentation. International Journal of Computer Science and Information Technologies, 5(4), 4834-483.

Siti Madihah Mazalan, Nasrul Humaimi Mahmood, Mohd Azhar Abdul Razak. (2013). Automated red blood cells counting in peripheral blood smear image using circular hough transform. International Conference on Artificial Intelligence, Modeling & Simulation, 320-324. Doi: 10.1109/AIMS.2013.59

Heidi Berge, Dale Taylor, Sriram Krishnan, Tania S. Douglas. (2011). Improved red blood cell counting in thin blood smear. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 204 – 207. Doi: 10.1109/ISBI.2011.5872388

Lorenzo Putzu, Cecilia Di Ruberto. (2013). White blood cells identification and counting from microscopic blood image. International Journal of Medical, Health, Biomedical and Pharmaceutical Engineering, 7(1), 189-196. Doi: scholar.waset.org/1999.9/189

Nasrul Humaimi Mahmood, Poon Che Lim, Siti Madihah Mazalan, Mohd Azhar Abdul Razak. (2013). Blood cells extraction using color based segmentation technique. International Journal of Medical, Health, Biomedical and Pharmaceutical Engineering. 7(1). doi: 10.1.1.300.3596

Nasution, A.M.T., EK Suryaningtyas. (2008). Comparison of red blood cells counting using two algorithms: connected component labeling and back projection of artificial neural network. IEEE Photonics Global Singapore, 1–4. Doi: 10.1109/IPGC.2008.4781402

Wilhelm Burger, Mark J. Burge. (2011). Digital image processing: an algorithmic introduction using java, Springer, 223-226.

Matt Sottile. (2013, January 11). Finding dents in a blobby shape. Mjsottile computational science and languages. Retrieved from http://syntacticsalt.com/2013/01/11/finding-dents-in-an-blobby-shape

Downloads

Published

2015-07-01

How to Cite

Valeeprakhon, T., & Eua-Anant, N. (2015). SEGMENTATION OF CONNECTED RED BLOOD CELLS BASED ON DISTANCE PER DISPLACEMENT RATIO MAXIMIZATION CRITERION. MATTER: International Journal of Science and Technology, 1(1), 132–143. https://doi.org/10.20319/mijst.2016.s11.132143