Recognition and classification of red blood cells using digital holographic microscopy and data clustering with discriminant analysis.

Details

Serval ID
serval:BIB_4DBF725FE3C4
Type
Article: article from journal or magazin.
Collection
Publications
Title
Recognition and classification of red blood cells using digital holographic microscopy and data clustering with discriminant analysis.
Journal
Journal of the Optical Society of America. A, Optics, Image Science, and Vision
Author(s)
Liu R., Dey D.K., Boss D., Marquet P., Javidi B.
ISSN
1520-8532 (Electronic)
ISSN-L
1084-7529
Publication state
Published
Issued date
2011
Peer-reviewed
Oui
Volume
28
Number
6
Pages
1204-1210
Language
english
Notes
Publication types: Journal ArticlePublication Status: ppublish
Abstract
We propose to apply statistical clustering algorithms on a three-dimensional profile of red blood cells (RBCs) obtained through digital holographic microscopy (DHM). We show that two classes of RBCs stored for 14 and 38 days can be effectively classified. Two-dimensional intensity images of these cells are virtually the same. DHM allows for measurement of the RBCs' biconcave profile, resulting in a discriminative dataset. Two statistical clustering algorithms are compared. A model-based clustering approach classifies the pixels of an RBC and recognizes the RBC as either new or old based. The K-means algorithm is applied to the four-dimensional feature vector extracted from the RBC profile.
Keywords
Algorithms, Cluster Analysis, Discriminant Analysis, Erythrocytes/classification, Holography/methods, Humans, Microscopy/methods
Pubmed
Web of science
Create date
05/04/2013 9:27
Last modification date
20/08/2019 14:02
Usage data