The watershed transform in pathological image analysis: application in rectiulocyte count from supravital stained smears

Parikshit Sanyal, Sanghita Barui


Background: Morphometric studies based on image analysis are a useful adjunct for quantitative analysis of microscopic images. However, effective separation of overlapping objects if often the bottleneck in image analysis techniques. We employ the watershed transform for counting reticulocytes from images of supravitally stained smears.

Methods: The algorithm was developed with the Python programming platform, using the Numpy, Scipy and OpenCV libraries. The initial development and testing of the software were carried out with images from the American Society of Hematology Image Library. Then a pilot study with 30 samples was then taken up. The samples were incubated with supravital stain immediately after collection, and smears prepared. The smears were microphotographed at 100X objective, with no more than 150 RBCs per field. Reticulocyte count was carried out manually as well as by image analysis.

Results: 600 out of 663 reticulocytes (90.49%) were correctly identified, with a specificity of 98%. The major difficulty faced was the slight bluish tinge seen in polychromatic RBCs, which were inconsistently detected by the software.

Conclusions: The watershed transform can be used successfully to separate overlapping objects usually encountered in pathological smears. The algorithm has the potential to develop into a generalized cell classifier for cytopathology and hematology.


Automated, Cell classification, Image analysis, Reticulocyte, Watershed transform

Full Text:



Bacus JW, inventor; Rush-Presbyterian-St Luke's Medical Center, assignee. Dual resolution method and apparatus for use in automated classification of pap smear and other samples. United States patent US 4,175,860. 1979 Nov 27.

Sanyal P, Ganguli P, Barui S, Deb P. Pilot study of an open-source image analysis software for automated screening of conventional cervical smears. J Cytol. 2018;35:71-4.

Plissiti MR, Charchanti A, Krikoni O, and Fotiadis DI. Automated segmentation of cell nuclei in pap smear images. In ITAB 2006-Proceedings of Informational Technology in Biomedicine; 2006.

Patale SS, Pansambal BH. Acute myeloid leukemia detection in blood, microscopic image by using PNN. Int J Innovative Res Computer Communication Eng. 2016;4(4):7094.

Nikitaev VG, Nagornov OV, Pronichev AN, Polyakov EV, Dmitrieva VV. The blood smear image processing for the acute leukemia diagnostics. Int J Biol Biomed Engg. 2016;10:109.

Amin MM, Kermani S, Talebi A, Oghli MG. Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier. J Medical Signals Sensors. 2015 Jan;5(1):49.

James R. Hackney JR, Cembrowski GS, Prystowsky MB, Kant JA. Automated reticulocyte counting by image analysis and flow cytometry. Lab Med. 1989:551.

Schimenti KJ, Lacerna K, Wamble A, Maston L, Iaffaldano C, Straight M, et al. Reticulocyte quantification by flow cytometry, image analysis, and manual counting. Cytometry. 1992;13(8):853-62.

Tanke HJ, Rothbarth PH, Vossen JM, Koper GJ, Ploem JS. Flow cytometry of reticulocytes applied to clinical hematology. Blood. 1983 Jun;61(6):1091-7.

Seligman PA, Allen RH, Kirchanski SJ, Natale PJ. Automated analysis of reticulocytes using fluorescent staining with both acridine orange and an immunofluorescence technique. Am J Hematol. 1983 Feb;14(1):57-66.

Metzger DK, Charache S. Flow cytometric reticulocyte counting with thioflavin T in a clinical hematology laboratory. Arch Pathol Lab Med. 1987;111(6):540-4.