Paper published in a book (Scientific congresses and symposiums)
Deep Learning approaches for Head and Operculum Segmentation in Zebrafish Microscopy Images
Kumar, Navdeep; Carletti, Alessio; Gavaia, Paulo Jorge et al.
2021In Part of the Lecture Notes in Computer Science book series (LNIP, volume 13052)
Peer reviewed
 

Files


Full Text
CAIP_FinalVersion.pdf
Publisher postprint (787.9 kB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Deep Learning; image segmentation; microscopy; biomedical image analysis; zebrafish
Abstract :
[en] In this paper, we propose variants of deep learning methods to segment head and operculum of the zebrafish larvae in microscopic images. In the first approach, we used a three-class model to jointly segment head and operculum area of zebrafish larvae from background. In the second, two-step, approach, we first trained binary segmentation model to segment head area from the background followed by another binary model to segment the operculum area within cropped head area thereby minimizing the class imbalance problem. Both of our approaches use a modified, simpler, U-Net architecture, and we also evaluate different loss functions to tackle the class imbalance problem. We systematically compare all these variants using various performance metrics. Data and open-source code are available at https://uliege.cytomine.org.
Disciplines :
Human health sciences: Multidisciplinary, general & others
Computer science
Author, co-author :
Kumar, Navdeep ;  Université de Liège - ULiège > GIGA I3 - Laboratory for Organogenesis and Regeneration
Carletti, Alessio
Gavaia, Paulo Jorge
Muller, Marc  ;  Université de Liège - ULiège > Département des sciences de la vie > GIGA I3 - Laboratory for Organogenesis and Regeneration
Cancela, Leonor
Geurts, Pierre  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
Marée, Raphaël  ;  Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques
Language :
English
Title :
Deep Learning approaches for Head and Operculum Segmentation in Zebrafish Microscopy Images
Publication date :
28 September 2021
Event name :
International Conference on Computer Analysis of Images and Patterns (CAIP-2021)
Event place :
Cyprus
Event date :
From 27-09-2021 to 1-10-2021
Audience :
International
Main work title :
Part of the Lecture Notes in Computer Science book series (LNIP, volume 13052)
Publisher :
Springer, Switzerland
ISBN/EAN :
978-3-030-89128-2
Peer reviewed :
Peer reviewed
European Projects :
H2020 - 766347 - BioMedaqu - Aquaculture meets Biomedicine: Innovation in Skeletal Health research.
Name of the research project :
BIOMEDAQU
Funders :
EC - European Commission
EU - European Union
Funding text :
This work, as well as N.K. and A. C. are supported by the EU MSCA-ITN project BioMedAqu (766347). R.M. was partially supported by ADRIC Wallonia Grant and EU IMI BIGPICTURE grant. M.M. is a “Maître de Recherche” at the Fund for Scientific Research (F.R.S.–FNRS).
Available on ORBi :
since 17 November 2021

Statistics


Number of views
178 (29 by ULiège)
Number of downloads
170 (14 by ULiège)

Scopus citations®
 
1
Scopus citations®
without self-citations
0
OpenAlex citations
 
2

Bibliography


Similar publications



Contact ORBi