Feedback

Faculté des Sciences appliquées
Faculté des Sciences appliquées
MASTER THESIS
VIEW 70 | DOWNLOAD 76

A distributed deep learning approach for histopathology image retrieval

Download
Defraire, Stephan ULiège
Promotor(s) : Marée, Raphaël ULiège
Date of defense : 6-Sep-2021/7-Sep-2021 • Permalink : http://hdl.handle.net/2268.2/13016
Details
Title : A distributed deep learning approach for histopathology image retrieval
Translated title : [fr] Une approche distribuée d'apprentissage profond pour la recherche d'images histopathologiques similaires
Author : Defraire, Stephan ULiège
Date of defense  : 6-Sep-2021/7-Sep-2021
Advisor(s) : Marée, Raphaël ULiège
Committee's member(s) : Geurts, Pierre ULiège
Phillips, Christophe ULiège
Language : English
Number of pages : 88
Keywords : [fr] Deep Learning
[fr] Cytomine
[fr] Computer Vision
[fr] Histopathology
[fr] Image Retrieval
Discipline(s) : Engineering, computing & technology > Computer science
Research unit : Institut Monetfiore
Name of the research project : Cytomine R&D
Target public : Researchers
Professionals of domain
Student
General public
Complementary URL : https://github.com/stephdef08/tfe
https://github.com/stephdef08/tfe2
Institution(s) : Université de Liège, Liège, Belgique
Degree: Master en ingénieur civil en informatique, à finalité spécialisée en "intelligent systems"
Faculty: Master thesis of the Faculté des Sciences appliquées

Abstract

[en] Digital microscopy and radiology generate growing amounts of imagery data. To help practitioners find the information crucial to establish the most accurate possible diagnoses, Artificial Intelligence tools need to be developed.

This master thesis, based on the study of existing literature and open-source code, proposes a distributed deep learning architecture that allows a user, by using a fast approximate nearest neighbour search, to retrieve similar histopathology images to a query image.

The retained Deep Learning architecture, ResNet50 with some modifications, was distributed on different servers in order to allow the handling of up to million or billion images.

It was trained on a large-scale dataset of 67 classes of annotated medical images and the obtained results are quite promising, as well for the visual similarity of the retrieved images as for the search time. This research also analyses the generalisation to classes on which the system was not trained, and the impact of the approximated search on the accuracy and the retrieval time.

Nevertheless, even though the results are positive, this system might present some limitations as it was tested on only one dataset and was not reviewed by medical practitioners.


File(s)

Document(s)

File
Access thesis.pdf
Description:
Size: 52.17 MB
Format: Adobe PDF
File
Access summary.pdf
Description:
Size: 217.36 kB
Format: Adobe PDF

Author

  • Defraire, Stephan ULiège Université de Liège > Master ingé. civ. info., à fin.

Promotor(s)

Committee's member(s)

  • Geurts, Pierre ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Algorith. des syst. en interaction avec le monde physique
    ORBi View his publications on ORBi
  • Phillips, Christophe ULiège Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore)
    ORBi View his publications on ORBi
  • Total number of views 70
  • Total number of downloads 76










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.