Identification and red blood cell automated counting from bloodsmear images using computer-aided system

Acharya, Vasundara and Kumar, Preetham (2017) Identification and red blood cell automated counting from bloodsmear images using computer-aided system. Medical & Biological Engineering & Computing. ISSN 1741-0444

[img] PDF
3482.pdf - Published Version
Restricted to Registered users only

Download (2MB) | Request a copy

Abstract

Red blood cell count plays a vital role in identifying the overall health of the patient. Hospitals use the hemocytometerto count the blood cells. Conventional method ofplacing the smear under microscope and counting the cells manually lead to erroneous results, and medical laboratory technicians are put under stress. A computer-aided system willhelp to attain precise results in less amount of time. This researchwork proposes an image-processing technique for counting the number of red blood cells. It aims to examine and process the blood smear image, in order to support the counting of red blood cells and identify the number of normaland abnormal cells in the image automatically. K-medoidsalgorithm which is robust to external noise is used to extractthe WBCs from the image. Granulometric analysis is used toseparate the red blood cells from the white blood cells. The redblood cells obtained are counted using the labeling algorithmand circular Hough transform. The radius range for the circledrawingalgorithm is estimated by computing the distance ofthe pixels from the boundary which automates the entire algorithm. A comparison is done between the counts obtainedusing the labeling algorithm and circular Hough transform.Results of the work showed that circular Hough transformwas more accurate in counting the red blood cells han thelabeling algorithm as it was successful in identifying eventhe overlapping cells. The work also intends to compare the results of cell count done using the proposed methodology and manual approach. The work is designed to address all the drawbacks of the previous research work. The research work can be extended to extract various texture and shape features of abnormal cells identified so that diseases like anemiaof inflammation and chronic disease can be detected at theearliest.

Item Type: Article
Uncontrolled Keywords: Blood smear . Circular Hough transform .Granulometric analysis . Hemocytometer
Subjects: Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 25 Nov 2017 06:54
Last Modified: 25 Nov 2017 06:54
URI: http://eprints.manipal.edu/id/eprint/150066

Actions (login required)

View Item View Item