a web platform for collaborative analysis of multi-gigapixel images - - PowerPoint PPT Presentation

▶

Mar 26, 2024 284 likes •588 views

a web platform for collaborative analysis of multi-gigapixel images with machine learning Rapha el MAREE Renaud HOYOUX Gr egoire VINCKE Biomedical research and routine pathology Heavily rely on semantic annotation &

SLIDE 1

a web platform for collaborative analysis

f multi-gigapixel images

with machine learning

Rapha¨ el MAREE – Renaud HOYOUX – Gr´ egoire VINCKE

SLIDE 2

Biomedical research and routine pathology

Heavily rely on semantic annotation & quantification of tissue slides

2 / 23

SLIDE 3

Scientists and pathologist’s daily work

3 / 23

SLIDE 4

Scientists and pathologist’s daily work

3 / 23

Slide quantifications (annotations ?) are usually

Performed manually ❢ ① ✘ ✐ Performed within tissue subregions in small sample groups Created by isolated experts Stored locally (generally no backups) Proprietary formats

Hardly repeatable

SLIDE 5

Digital histology and pathology

4 / 23

SLIDE 6

Digital histology and pathology

4 / 23

Multi-gigapixel images

15 x 15 mm
≅ 0, 20µm/px
100K x 100K pixels
+100Mb → +100Gb
pyramidal structure

SLIDE 7

Digital histology and pathology

4 / 23

Slide quantifications and annotations could be

Performed automatically ➈ Performed in entire sample in large groups Shared between experts Stored on a cloud In Open formats

Easily repeatable

SLIDE 8

2010 : start of project

5 / 23

SLIDE 9

2010 : start of project

5 / 23

Authentification

Roles, permissions, LDAP

SLIDE 10

SLIDE 11

SLIDE 12

Direct upload

Several file formats supported

SLIDE 13

SLIDE 14

SLIDE 15

Rich web application

OpenStreetMap-like visualization (tiles) No extra software to install

SLIDE 16

Rich web application

Collaborative and semantic annotation

f regions of interest

SLIDE 17

Rich web application

Collaborative and semantic annotation

f regions of interest

SLIDE 18

Manual or semi-automatic analysis

Generic algorithms of machine learning Manual correction and validation (proofreading)

SLIDE 19

But also

Search similar annotations Sharing of images and annotations (URL, email) Live broadcasting

SLIDE 20

based research

14 / 23

SLIDE 21

based research

14 / 23

Research with at ULg

175 users 300 projects 20 000 images (≅6To) 500 000 annotations (≅160Go) ( ≫ )

SLIDE 22

based research

14 / 23

Research with at ULg

175 users 300 projects 20 000 images (≅6To) 500 000 annotations (≅160Go) ( ≫ )

Teaching with at l’ULg

4 000 users 50 projects 2 000 images (≅2To) 200 000 annotations (≅30Go) ( ≪ )

SLIDE 23

General architecture

15 / 23

SLIDE 24

Detailed architecture

16 / 23

SLIDE 25

Included softwares and libraries

17 / 23

SLIDE 26

Docker architecture

18 / 23

SLIDE 27

Minimal setups

19 / 23

SLIDE 28

Several kinds of setups

20 / 23

SLIDE 29

http://doc.cytomine.be

21 / 23

SLIDE 30

Acknowledgments

Systems and Modeling GIGA-Research / Montefiore Institute (ULG) : Rapha¨ el Mar´ ee, Lo¨ ıc Rollus, Benjamin St´ evens, Renaud Hoyoux, Gilles Louppe, Jean-Michel Begon, R´ emy Vandaele, Jean-Michel Begon, Pierre Geurts, Louis Wehenkel. Collaborators at University of Li` ege (ULg) : GIGA : Didier Cataldo, Natacha Rocks, Fabienne Perin, Christine Fink. IFRES : Gr´ egoire Vincke, Dominique Verpoorten. Histologie : Pascale Quatresooz, Val´ erie Defaweux, le groupe MorphoTIC. CRIFA : Brigitte Denis, C´ eline Snoeck. Students : Julien Confetti, Pierre Ansen, Olivier Caubo, Antoine Deblire. Other collaborators : Universit´ e Libre de Bruxelles (ULB) : Isabelle Salmon, Caroline Degand, Xavier Moles Lopez, Nicky d’Haene. Institut Pasteur (Paris) : Vannary Meas-Yedid, Jean-Christophe Olivo-Marin. Medical University Graz : Philippe Kainz. University of Namur : Patsy Renard, Eric Depiereux. Research grants of the Wallonia (DGO6) : CYTOMINE (2010-2016) n ˚ 1017072 SMASH (2012-2014) n ˚ 1217606 HISTOWEB (2014-2017) n ˚ 1318185 More information on : http://cytomine.be

info@cytomine.be @cytomine

22 / 23