Geometrical vs spatial features analysis of overlap red blood cell algorithm

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Blood cell analysis is very important in human being. Red blood cell (RBC) is one of the biggest component in blood that are circular in shape. Many diseases can be diagnose based on the RBC morphology description and quantification. There are many algorithms used for circle detection, the most known algorithm is Circular Hough Transform (CHT), Randomized Circle Detection (RCD) and others. In this study, we compare the performance of Geometrical Features code: IRIC (Iterative Randomized Irregular Circle) and Edge Drawing Circle (EDCircle) with Spatial Features code: CHT. We testing the algorithm on three level overlap of images. Simple images with 2 overlap cells, Moderate images with 3 and 4 overlap cells and complex images contain 5 overlap cells in blood smear images. All images dataset captured from Hematology Unit, Pathology Department, UKM Medical Centre in Cheras. The comparison showed that, IRIC method (geometrical feature) give the best precision and recall result at all level: 2 overlap cell (85.8%, 84.3%), 3 overlap cell (54.3%, 50.2%), 4 overlap cell (37.5%, 30.4%) and 5 overlap cell (28.0%, 16.2%).

Original languageEnglish
Title of host publication2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages246-251
Number of pages6
ISBN (Electronic)9781509028894
DOIs
Publication statusPublished - 27 Mar 2017
Event2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016 - Putrajaya, Malaysia
Duration: 14 Nov 201616 Nov 2016

Other

Other2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016
CountryMalaysia
CityPutrajaya
Period14/11/1616/11/16

Fingerprint

erythrocytes
Blood
Cells
cells
Hough transforms
Medical departments (industrial plants)
blood
hematology
Pathology
smear
blood cells
pathology
Testing

Keywords

  • CHT
  • EDCircle
  • IRIC detection
  • Overlap cell red blood cell

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Biomedical Engineering
  • Control and Systems Engineering
  • Hardware and Architecture
  • Computer Networks and Communications
  • Instrumentation

Cite this

Ahmad, I., Sheikh Abdullah, S. N. H., & Raja Sabudin, R. Z. A. (2017). Geometrical vs spatial features analysis of overlap red blood cell algorithm. In 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016 (pp. 246-251). [7888047] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAEES.2016.7888047

Geometrical vs spatial features analysis of overlap red blood cell algorithm. / Ahmad, Izyani; Sheikh Abdullah, Siti Norul Huda; Raja Sabudin, Raja Zahratul Azma.

2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 246-251 7888047.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ahmad, I, Sheikh Abdullah, SNH & Raja Sabudin, RZA 2017, Geometrical vs spatial features analysis of overlap red blood cell algorithm. in 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016., 7888047, Institute of Electrical and Electronics Engineers Inc., pp. 246-251, 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016, Putrajaya, Malaysia, 14/11/16. https://doi.org/10.1109/ICAEES.2016.7888047
Ahmad I, Sheikh Abdullah SNH, Raja Sabudin RZA. Geometrical vs spatial features analysis of overlap red blood cell algorithm. In 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 246-251. 7888047 https://doi.org/10.1109/ICAEES.2016.7888047
Ahmad, Izyani ; Sheikh Abdullah, Siti Norul Huda ; Raja Sabudin, Raja Zahratul Azma. / Geometrical vs spatial features analysis of overlap red blood cell algorithm. 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 246-251
@inproceedings{3604a15140f04ef1a6ae8570e5956f02,
title = "Geometrical vs spatial features analysis of overlap red blood cell algorithm",
abstract = "Blood cell analysis is very important in human being. Red blood cell (RBC) is one of the biggest component in blood that are circular in shape. Many diseases can be diagnose based on the RBC morphology description and quantification. There are many algorithms used for circle detection, the most known algorithm is Circular Hough Transform (CHT), Randomized Circle Detection (RCD) and others. In this study, we compare the performance of Geometrical Features code: IRIC (Iterative Randomized Irregular Circle) and Edge Drawing Circle (EDCircle) with Spatial Features code: CHT. We testing the algorithm on three level overlap of images. Simple images with 2 overlap cells, Moderate images with 3 and 4 overlap cells and complex images contain 5 overlap cells in blood smear images. All images dataset captured from Hematology Unit, Pathology Department, UKM Medical Centre in Cheras. The comparison showed that, IRIC method (geometrical feature) give the best precision and recall result at all level: 2 overlap cell (85.8{\%}, 84.3{\%}), 3 overlap cell (54.3{\%}, 50.2{\%}), 4 overlap cell (37.5{\%}, 30.4{\%}) and 5 overlap cell (28.0{\%}, 16.2{\%}).",
keywords = "CHT, EDCircle, IRIC detection, Overlap cell red blood cell",
author = "Izyani Ahmad and {Sheikh Abdullah}, {Siti Norul Huda} and {Raja Sabudin}, {Raja Zahratul Azma}",
year = "2017",
month = "3",
day = "27",
doi = "10.1109/ICAEES.2016.7888047",
language = "English",
pages = "246--251",
booktitle = "2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Geometrical vs spatial features analysis of overlap red blood cell algorithm

AU - Ahmad, Izyani

AU - Sheikh Abdullah, Siti Norul Huda

AU - Raja Sabudin, Raja Zahratul Azma

PY - 2017/3/27

Y1 - 2017/3/27

N2 - Blood cell analysis is very important in human being. Red blood cell (RBC) is one of the biggest component in blood that are circular in shape. Many diseases can be diagnose based on the RBC morphology description and quantification. There are many algorithms used for circle detection, the most known algorithm is Circular Hough Transform (CHT), Randomized Circle Detection (RCD) and others. In this study, we compare the performance of Geometrical Features code: IRIC (Iterative Randomized Irregular Circle) and Edge Drawing Circle (EDCircle) with Spatial Features code: CHT. We testing the algorithm on three level overlap of images. Simple images with 2 overlap cells, Moderate images with 3 and 4 overlap cells and complex images contain 5 overlap cells in blood smear images. All images dataset captured from Hematology Unit, Pathology Department, UKM Medical Centre in Cheras. The comparison showed that, IRIC method (geometrical feature) give the best precision and recall result at all level: 2 overlap cell (85.8%, 84.3%), 3 overlap cell (54.3%, 50.2%), 4 overlap cell (37.5%, 30.4%) and 5 overlap cell (28.0%, 16.2%).

AB - Blood cell analysis is very important in human being. Red blood cell (RBC) is one of the biggest component in blood that are circular in shape. Many diseases can be diagnose based on the RBC morphology description and quantification. There are many algorithms used for circle detection, the most known algorithm is Circular Hough Transform (CHT), Randomized Circle Detection (RCD) and others. In this study, we compare the performance of Geometrical Features code: IRIC (Iterative Randomized Irregular Circle) and Edge Drawing Circle (EDCircle) with Spatial Features code: CHT. We testing the algorithm on three level overlap of images. Simple images with 2 overlap cells, Moderate images with 3 and 4 overlap cells and complex images contain 5 overlap cells in blood smear images. All images dataset captured from Hematology Unit, Pathology Department, UKM Medical Centre in Cheras. The comparison showed that, IRIC method (geometrical feature) give the best precision and recall result at all level: 2 overlap cell (85.8%, 84.3%), 3 overlap cell (54.3%, 50.2%), 4 overlap cell (37.5%, 30.4%) and 5 overlap cell (28.0%, 16.2%).

KW - CHT

KW - EDCircle

KW - IRIC detection

KW - Overlap cell red blood cell

UR - http://www.scopus.com/inward/record.url?scp=85018174427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018174427&partnerID=8YFLogxK

U2 - 10.1109/ICAEES.2016.7888047

DO - 10.1109/ICAEES.2016.7888047

M3 - Conference contribution

AN - SCOPUS:85018174427

SP - 246

EP - 251

BT - 2016 International Conference on Advances in Electrical, Electronic and Systems Engineering, ICAEES 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -