The diagnostic formulations in patients rest on a tripod consisting of clinical history, physical examination and laboratory investigations. In most of the cases diagnoses are mainly done based on laboratory medicine. Current manual techniques lack precision and reproducibility and hence automated methods where an image of the smear is captured and analyzed offers more precision and accuracy. Accurate analysis of the cells including the red cells in the blood smear images is vital for the diagnosis of various diseases and pathological conditions in patients. This calls for accurate detection and segmentation of the Red Blood Cells (RBCs) prior to analysis. Normal RBCs are biconcave in shape with a central pale area and any deviation in most of the RBCs in their size and ratio of the total surface area of the cell to the central pale area from the normal represents an abnormality. If the size and volume of an RBC is less than a normal cell it is indicative of a pathological process called as microcytosis and on the other hand macrocytosis is the condition where the cell is enlarged. This paper proposes an automated method of analyzing the RBCs in blood smear images for morphological abnormalities, which is an extension of an earlier work focusing on segmentation of all the cells in the blood smear images using Watershed Transform.

Segmentation, Watershed Algorithm, Morphological Operations, Mean Corpuscular Volume

[1] F. Sheeba, H.M. Thomas, J.J. Mammen, “Segmentation and Watermarking of Peripheral Blood Smear Images” In the Proceedings of the 5th IEEE Conference on Bio-Inspired Computing – Theory and Applications (BICTA), Liverpool Hope University, UK, pp. 1373-1376, 2010.
[2] J.J. Mammen, P. Maqlin, F. Sheeba, T. Robinson, “Making Malarial Diagnosis More Reliable: Using Image Analysis for Identification of Plasmodium Falciparum Gameotcytes”, Journal of Pathology Informatics, vol.2:43e, pp. s19-20., 2011
[3] F. Sheeba, T. Robinson, J.J. Mammen, H.M. Thomas, A.K. Nagar, “White Blood Cell Segmentation and Reversible Watermarking”, in the Proceedings of the IASTED International Symposia on Imaging and Signal Processing in Healthcare and Technology (ISPHT), Washington DC, USA,, 2011.
[4] F. Sheeba, A.K. Nagar, T. Robinson, J.J. Mammen, “Segmentation of Peripheral Blood Smear Images Using Tissue-Like P Systems”, International Journal of Natural Computing Research, 3(1), pp, 16-27, 2012.
[5] F. Sheeba, T. Robinson, J.J. Mammen, A.K. Nagar, “Detection of Plasmodium Falciparum in Peripheral Blood Smear Images”, in the Proceedings of the International Conference on Bio-Inspired Computing – Theory and Applications (BICTA) 2012, ABV-IITM, Gwalior, India, 2012.
[6] F. Sheeba, T. Robinson, J. Michael, P. Maqlin, J.J. Mammen, “Segmentation of Sputum Smear Images for Detection of Tuberculosis Bacilli”, BMC Infectious Diseases, 2012
[7] F. Sheeba, T. Robinson, J.J. Mammen, A.K. Nagar, “Splitting of Overlapping Cells in Peripheral Blood Smear Images by Concavity Analysis”, Lecture Notes in Computer Science, Volume: 8466, 2015.
[8] F. Sheeba, T. Robinson, J.J. Mammen, M. Kumar, V. Rangslang, “Convex Hull Based Detection of Overlapping Red Blood Cells In Peripheral Blood Smear Images”, in the IFMBE Proceedings of 7th WACBE World Congress on Bioengineering, Vol. 52, pp. 51-53, 2015.
[9] F. Sheeba, T. Robinson, J.J. Mammen, A.K. Nagar, “Segmentation of Overlapping Gametocytes of P.falciparum using the Active Contour Model”, in the RPS Proceedings of 17th International Workshop on Combinatorial Image Analysis, ISI, Kolkatta, 2015.
[10] F. Sheeba, T. Robinson, J.J. Mammen, R. Nithish, S. Karthick, “Detection Of Overlapping Tuberculosis Bacilli in Sputum Smear Images”, in the IFMBE Proceedings of the 7th WACBE World Congress on Bioengineering, pp 54-56, 2015.
[11] N.H. Mahmood, M.A Mansor, “Red Blood Cells Estimation using Hough Transform Technique”, Signal & Image Processing : an International Journal (SIPIJ)”, Vol.3, No.2, 2012.
[12] H. Khajehpour, A.M. Dehnavi, H. Taghizad, E. Khajehpour, M. Naeemabadi, “Detection and Segmentation of Erythrocytes in Blood Smear Images Using a Line Operator and Watershed Algorithm”, Journal of Medical Signals and Sensors, Jul-Sep 3(3), pp. 164–171, 2013.
[13] J.M. Sharif, M.F. Miswan, M,A, Ngadi, M.D. Sah, H.J. Salam, M. Mahadi, B.A. Jamil, “Red Blood Cell Segmentation using Masking and Watershed Algorithm: A Preliminary Study”, In the Proceedings of the International Conference on Biomedical Engineering (ICoBE), 2012.
[14] A.P Janwale, “Plant Leaves Image Segmentation Techniques: A Review”, International Journal of Computer Sciences and Engineering 5(5), pp. 147-150, 2017
[15] K. P. Palli, S. R. Edara, K. Chandrasekharaiah, “Segmentation of RBC in Blood Smear Image using Discrete Shearlet Transform”, International Journal of Computer Applications 137(6), pp. 1-4, 2016.
[16] S. Kulasekaran; F. Sheeba; J.J. Mammen; B. Saivigneshu; S. Mohankumar, “Morphology Based Detection of Abnormal Red Blood Cells in Peripheral Blood Smear Images”, in the IFMBE Proceedings of the 7th WACBE World Congress on Bioengineering pp 57-60, 2015.
[17] D. N. Patil, U. P. Khot, “Image Processing Based Abnormal Blood Cells Detection”, International Journal of Technical Research and Applications Special Issue 31, pp. 37-43, 2015.
[18] Razalitomari, W.N. Wanzakaria, M.M. Abduljamil, F. Mohdnor, N. F. Nikfuad, “Computer Ai.ded System For Red Blood Cell Classification In Blood Smear Image”, Procedia Computer Science, Volume 42, pp. 206-213, 2014.
[19] S. Bala, A. Doegar , “Automatic Detection of Sickle cell in Red Blood cell using Watershed Segmentation” International Journal of Advanced Research in Computer and Communication Engineering, Vol. 4, Issue 6, June 2015.