Automatic classification of cells using morphological shape in peripheral blood images

K. S. Kim, J. J. Song, F. Golshani, Sethuraman Panchanathan

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

A novel technique for automatic analysis and classification of cells in peripheral blood images is presented. The purposes of this research are to analyze and classify morphological shapes of mature red-blood cells and white-blood cells in peripheral blood images. We first, identify red-blood cells and white-blood cells in a blood image captured from CCD camera attached to microscope. Feature extraction is the second step. Finally blood cells are classified using back propagation neural network. Fifteen different classification clusters including normal cells are in red blood cell. However, there are five different normal categories in discrimination of white blood cells. In other words, the system can tell whether a given white cell belongs to a one of five normal classes or not. A novel segmentation method is presented for extraction of nucleus and cytoplasm which inherently posses valuable clues in white blood cell classification. Initially, seventy-six dimensions of a feature vector that includes UNL Fourier descriptor, shape, and color are considered in red-blood cell classification. While, thirty-eight dimensions of a feature vector are considered in red blood cell classification. Based on the proposed method, a prototype system has implemented and evaluated with various classification algorithms such as LVQ-3 (Learning Vector Quantization) and K-NN (K-nearest neighbor). The experiment results show that the proposed method out performs on blood cell classification compared with other alternatives.

Original languageEnglish (US)
Pages (from-to)290-298
Number of pages9
JournalUnknown Journal
Volume4210
StatePublished - 2000
Externally publishedYes

Fingerprint

blood
Blood
erythrocytes
leukocytes
Cells
Erythrocytes
cells
Leukocytes
blood cells
Blood Cells
vector quantization
cytoplasm
CCD cameras
pattern recognition
learning
discrimination
Cytoplasm
Color
microscopes
prototypes

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Automatic classification of cells using morphological shape in peripheral blood images. / Kim, K. S.; Song, J. J.; Golshani, F.; Panchanathan, Sethuraman.

In: Unknown Journal, Vol. 4210, 2000, p. 290-298.

Research output: Contribution to journalArticle

@article{071da53e6fb54008a567eb23d548a9c8,
title = "Automatic classification of cells using morphological shape in peripheral blood images",
abstract = "A novel technique for automatic analysis and classification of cells in peripheral blood images is presented. The purposes of this research are to analyze and classify morphological shapes of mature red-blood cells and white-blood cells in peripheral blood images. We first, identify red-blood cells and white-blood cells in a blood image captured from CCD camera attached to microscope. Feature extraction is the second step. Finally blood cells are classified using back propagation neural network. Fifteen different classification clusters including normal cells are in red blood cell. However, there are five different normal categories in discrimination of white blood cells. In other words, the system can tell whether a given white cell belongs to a one of five normal classes or not. A novel segmentation method is presented for extraction of nucleus and cytoplasm which inherently posses valuable clues in white blood cell classification. Initially, seventy-six dimensions of a feature vector that includes UNL Fourier descriptor, shape, and color are considered in red-blood cell classification. While, thirty-eight dimensions of a feature vector are considered in red blood cell classification. Based on the proposed method, a prototype system has implemented and evaluated with various classification algorithms such as LVQ-3 (Learning Vector Quantization) and K-NN (K-nearest neighbor). The experiment results show that the proposed method out performs on blood cell classification compared with other alternatives.",
author = "Kim, {K. S.} and Song, {J. J.} and F. Golshani and Sethuraman Panchanathan",
year = "2000",
language = "English (US)",
volume = "4210",
pages = "290--298",
journal = "Scanning Electron Microscopy",
issn = "0586-5581",
publisher = "Scanning Microscopy International",

}

TY - JOUR

T1 - Automatic classification of cells using morphological shape in peripheral blood images

AU - Kim, K. S.

AU - Song, J. J.

AU - Golshani, F.

AU - Panchanathan, Sethuraman

PY - 2000

Y1 - 2000

N2 - A novel technique for automatic analysis and classification of cells in peripheral blood images is presented. The purposes of this research are to analyze and classify morphological shapes of mature red-blood cells and white-blood cells in peripheral blood images. We first, identify red-blood cells and white-blood cells in a blood image captured from CCD camera attached to microscope. Feature extraction is the second step. Finally blood cells are classified using back propagation neural network. Fifteen different classification clusters including normal cells are in red blood cell. However, there are five different normal categories in discrimination of white blood cells. In other words, the system can tell whether a given white cell belongs to a one of five normal classes or not. A novel segmentation method is presented for extraction of nucleus and cytoplasm which inherently posses valuable clues in white blood cell classification. Initially, seventy-six dimensions of a feature vector that includes UNL Fourier descriptor, shape, and color are considered in red-blood cell classification. While, thirty-eight dimensions of a feature vector are considered in red blood cell classification. Based on the proposed method, a prototype system has implemented and evaluated with various classification algorithms such as LVQ-3 (Learning Vector Quantization) and K-NN (K-nearest neighbor). The experiment results show that the proposed method out performs on blood cell classification compared with other alternatives.

AB - A novel technique for automatic analysis and classification of cells in peripheral blood images is presented. The purposes of this research are to analyze and classify morphological shapes of mature red-blood cells and white-blood cells in peripheral blood images. We first, identify red-blood cells and white-blood cells in a blood image captured from CCD camera attached to microscope. Feature extraction is the second step. Finally blood cells are classified using back propagation neural network. Fifteen different classification clusters including normal cells are in red blood cell. However, there are five different normal categories in discrimination of white blood cells. In other words, the system can tell whether a given white cell belongs to a one of five normal classes or not. A novel segmentation method is presented for extraction of nucleus and cytoplasm which inherently posses valuable clues in white blood cell classification. Initially, seventy-six dimensions of a feature vector that includes UNL Fourier descriptor, shape, and color are considered in red-blood cell classification. While, thirty-eight dimensions of a feature vector are considered in red blood cell classification. Based on the proposed method, a prototype system has implemented and evaluated with various classification algorithms such as LVQ-3 (Learning Vector Quantization) and K-NN (K-nearest neighbor). The experiment results show that the proposed method out performs on blood cell classification compared with other alternatives.

UR - http://www.scopus.com/inward/record.url?scp=0034427592&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034427592&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0034427592

VL - 4210

SP - 290

EP - 298

JO - Scanning Electron Microscopy

JF - Scanning Electron Microscopy

SN - 0586-5581

ER -