ORBi: Stern Olivier - Automatic localization of interest points in zebrafish images with tree-based methods

Reference : Automatic localization of interest points in zebrafish images with tree-based methods


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Life sciences : Biochemistry, biophysics & molecular biology Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/99199

Title :	Automatic localization of interest points in zebrafish images with tree-based methods
Language :	English
Author, co-author :	Stern, Olivier [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Marée, Raphaël [Université de Liège - ULg > > GIGA-Management : Plateforme bioinformatique >]
	Aceto, Jessica [Université de Liège - ULg > Département des sciences de la vie > GIGA-R : Biologie et génétique moléculaire >]
	Jeanray, Nathalie [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Muller, Marc [Université de Liège - ULg > Département des sciences de la vie > GIGA-R : Biologie et génétique moléculaire >]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Geurts, Pierre [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Publication date :	2011
Main document title :	Proceedings of the 6th IAPR International Conference on Pattern Recognition in Bioinformatics
Publisher :	Springer
Collection and collection volume :	LNCS
On invitation :	No
Audience :	International
Event name :	6th IAPR International Conference on Pattern Recognition in Bioinformatics (2011)
Event date :	November 2-4 2011
Event organizer :	Delft University of Technology
Event place (city) :	Delft
Event country :	The Netherlands
Abstract :	[en] In many biological studies, scientists assess effects of experimental conditions by visual inspection of microscopy images. They are able to observe whether a protein is expressed or not, if cells are going through normal cell cycles, how organisms evolve in different experimental conditions, etc. But, with the large number of images acquired in high-throughput experiments, this manual inspection becomes lengthy, tedious and error-prone. In this paper, we propose to automatically detect specific interest points in microscopy images using machine learning methods with the aim of performing automatic morphometric measurements in the context of Zebrafish studies. We systematically evaluate variants of ensembles of classification and regression trees on four datasets corresponding to different imaging modalities and experimental conditions. Our results show that all variants are effective, with a slight advantage for multiple output methods, which are more robust to parameter choices.
Research units :	Giga-Systems Biology and Chemical Biology ; Giga-Development and Stem Cells
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS ; Politique Scientifique Fédérale (Belgique) = Belgian Federal Science Policy ; Région wallonne : Direction générale des Technologies, de la Recherche et de l'Energie - DGTRE ; Fonds Européen de Développement Régional - FEDER ; Action de Recherche Concertée BIOMOD (Université de Liège)
Permalink :	http://hdl.handle.net/2268/99199

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	stern_prib2011.pdf		Author preprint	1.1 MB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5