Automatic counting of trypanosomatid amastigotes in infected human cells

This article presents an automatic approach to counting amastigotes in human cells infected with Chagas. The approach is divided into four steps: first, morphological pretreatment removes the complex image background; sets are then segmented by unsupervised classification; the infected cells are the...

Full description

Saved in:

Bibliographic Details
Published in:	Computers in biology and medicine Vol. 89; pp. 222 - 235
Main Authors:	de Souza Relli, Cleber, Facon, Jacques, Ayala, Horacio Legal, De Souza Britto, Alceu
Format:	Journal Article
Language:	English
Published:	United States Elsevier Ltd 01-10-2017 Elsevier Limited
Subjects:	Amastigotes Automation Chagas disease Chagas Disease - diagnostic imaging Clustering Counting Cytoplasm Filtration Humans Image classification Image Processing, Computer-Assisted Image retrieval Infections Leishmania Mathematical morphology Morphology Nuclei Parasites Parasitic diseases Protozoa Segmentation Tropical diseases Trypanosoma cruzi Trypanosoma cruzi - cytology Vector-borne diseases Watersheds Chagas disease Segmentation Mathematical morphology Counting Trypanosoma cruzi
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This article presents an automatic approach to counting amastigotes in human cells infected with Chagas. The approach is divided into four steps: first, morphological pretreatment removes the complex image background; sets are then segmented by unsupervised classification; the infected cells are then preserved using a thresholding process; and, finally, they undergo morphological granulometric processing and are filtered by the average. An experimental protocol was employed to compare the amastigotes nuclei labeled by a professional biochemist with the results obtained by the proposed approach. We observed that using the granulometric sieving conducted with square SE plus average size filtering is the best option to obtain the minor error and the best precision and using the granulometric sieving conducted with rhombus SE without average size filtering represents the best combination for obtaining the best F-measure and recall rates. •The first contribution of this proposed approach is the use of TSL color space in the Fuzzy C-means clustering process.•The second contribution is the use of HSL color space in the mathematical color morphology with lexicographical ordering.•The third contribution of this proposed approach is the use of the color top-hat morphological process by reconstruction.•The fourth contribution was to highlight some interesting based- metric combinations.•The fifth contribution is planning to provide a public available software that will be used by other researchers.
Bibliography:	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-3 content type line 23 ObjectType-Review-1
ISSN:	0010-4825 1879-0534
DOI:	10.1016/j.compbiomed.2017.08.010