Morphological-based adaptive segmentation and quantification of cell assays in high content screening

In fluorescence-labelled cell assays for high content screening applications, image processing software is necessary to have automatic algorithms for segmenting the cells individually and for quantifying their intensities, size/shape parameters, etc. Mathematical morphology is a non-linear image pro...

Full description

Saved in:
Bibliographic Details
Published in2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro pp. 360 - 363
Main Authors Angulo, J., Schaack, B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2008
Subjects
Application software
Filters
Fluorescence
granulometry
Image analysis
Image processing
Image segmentation
mathematical morphology
Microscopy
Morphology
multi-scale gradient
quantitative cytology
Shape
Software algorithms
watershed segmentation
Online AccessGet full text

Cover

More Information
Summary:In fluorescence-labelled cell assays for high content screening applications, image processing software is necessary to have automatic algorithms for segmenting the cells individually and for quantifying their intensities, size/shape parameters, etc. Mathematical morphology is a non-linear image processing technique which is proven to be a very powerful tool in biomedical microscopy image analysis. This paper presents a morphological methodology based on connected filters, watershed transformation and granulometries for segmenting cells of different size, contrast, etc. In particular, the performance of the algorithms is illustrated with cell images from a toxicity assay in three-labels (Hoechst, EGFP, Phalloi'din) on nanodrops cell-on-chip format.
ISBN:9781424420025
1424420024
ISSN:1945-7928
1945-8452
DOI:10.1109/ISBI.2008.4541007