Determination of Hemoglobin Percentage Through K-Means Algorithm and Image Processing for White Blood Cell Diagnosis

White blood cell (WBC) diagnosis is often carried out by physicians manually, using a microscope to examine blood smears for the presence of WBCs. Due to the fact that it is a time-consuming, difficult, and prone to mistake procedure, an automated approach using a computerized system is ideal. The m...

Full description

Saved in:
Bibliographic Details
Published in2023 4th International Conference on Smart Electronics and Communication (ICOSEC) pp. 1467 - 1470
Main Authors S, Renukalatha, Kumar, J. Senthil, Sangeetha, A., Hema, M., Kumar, Ashok, Rawat, Ramesh Singh
Format Conference Proceeding
LanguageEnglish
Published IEEE 20.09.2023
Subjects
Blood smear
Digital images
Electronics packaging
image processing
Image segmentation
Medical services
Microscopy
Nuclear measurements
Segmentation
White blood cell
White blood cells
Online AccessGet full text

Cover

More Information
Summary:White blood cell (WBC) diagnosis is often carried out by physicians manually, using a microscope to examine blood smears for the presence of WBCs. Due to the fact that it is a time-consuming, difficult, and prone to mistake procedure, an automated approach using a computerized system is ideal. The most critical steps of this automated procedure are the segmentation and categorization of WBCs. This work proposes an automated segmentation approach for microscopic WBC images, with a particular emphasis on images obtained from fresh blood smears. It is recommended that the segmentation be carried out utilising an integration of numerous digital image processing (DIP) techniques, which are implemented in the segmentation process. Sixty microscopic blood images were evaluated, and the suggested approach achieved a cytoplasm segmentation accuracy of 93 percent and a nucleus segmentation accuracy of 89.8 percent, respectively, on the images.
DOI:10.1109/ICOSEC58147.2023.10275883