Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 30 | DOWNLOAD 8

Master thesis : Image Segmentation of Zebrafish Images

Download
Bellefroid, Sarah ULiège
Promotor(s) : Marée, Raphaël ULiège ; Geurts, Pierre ULiège
Date of defense : 27-Jan-2023 • Permalink : http://hdl.handle.net/2268.2/16766
Details
Title : Master thesis : Image Segmentation of Zebrafish Images
Translated title : [fr] Segmentation d'images de poisson zèbre
Author : Bellefroid, Sarah ULiège
Date of defense  : 27-Jan-2023
Advisor(s) : Marée, Raphaël ULiège
Geurts, Pierre ULiège
Committee's member(s) : Wehenkel, Louis ULiège
Muller, Marc ULiège
Language : English
Number of pages : 102
Keywords : [en] zebrafish
[en] image segmentation
[en] class imbalance
Discipline(s) : Engineering, computing & technology > Computer science
Target public : Researchers
Professionals of domain
Student
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master : ingénieur civil en science des données, à finalité spécialisée
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] The Biomedaqu project's goal is to find solutions for skeletal disorders. They have been taking advantage of the transparent body of zebrafish as a way to study the development of the skeleton under various conditions. However, their work is slowed down by the time-consuming task of annotating images. This project aims to automate the annotation process using image segmentation. However, this project will run into the problem of class imbalance as the many features to extract from zebrafish are extremely small. To counter this problem, two methods will be used. Cost-level methods will be used to study the effect of various loss functions on the performances of different models, while a data-level method will be used in order to reduce the class imbalance in the data. Even though not all methods were proven to be successful in dealing with class imbalance, this work provides valuable insight and findings that can guide future research in this area.


File(s)

Document(s)

File
Access Thesis_Sarah_Bellefroid.pdf
Description: Full text of the thesis
Size: 25.96 MB
Format: Adobe PDF
File
Access Abstract_Sarah_Bellefroid.pdf
Description: Summary
Size: 140.38 kB
Format: Adobe PDF

Author

  • Bellefroid, Sarah ULiège Université de Liège > Master ingé. civ. sc. don. à . fin.

Promotor(s)

Committee's member(s)

  • Wehenkel, Louis ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Méthodes stochastiques
    ORBi View his publications on ORBi
  • Muller, Marc ULiège Université de Liège - ULiège > GIGA I3 - Laboratory for Organogenesis and Regeneration
    ORBi View his publications on ORBi
  • Total number of views 30
  • Total number of downloads 8










All documents available on MatheO are protected by copyright and subject to the usual rules for fair use.
The University of Liège does not guarantee the scientific quality of these students' works or the accuracy of all the information they contain.