New Approach to Accelerated Image Annotation by Leveraging Virtual Reality and Cloud Computing
Corentin Guérinot
(1, 2, 3)
,
Valentin Marcon
(1)
,
Charlotte Godard
(1, 4)
,
Thomas Blanc
(3, 5)
,
Hippolyte Verdier
(1)
,
Guillaume Planchon
(1)
,
Francesca Raimondi
(1, 6)
,
Nathalie Boddaert
(6)
,
Mariana Alonso
(2)
,
Kurt Sailor
(2)
,
Pierre-Marie Lledo
(2)
,
Bassam Hajj
(5)
,
Mohamed El Beheiry
(1)
,
Jean-Baptiste Masson
(1)
Hippolyte Verdier
- Fonction : Auteur
- PersonId : 1091581
- ORCID : 0000-0002-3650-0555
- IdRef : 275806316
Francesca Raimondi
- Fonction : Auteur
- PersonId : 1065185
- ORCID : 0000-0003-2580-151X
- IdRef : 240881435
Mariana Alonso
- Fonction : Auteur
- PersonId : 746867
- IdHAL : mariana-alonso
- ORCID : 0000-0002-6127-6030
- IdRef : 243127170
Mohamed El Beheiry
- Fonction : Auteur correspondant
Jean-Baptiste Masson
Connectez-vous pour contacter l'auteur
- Fonction : Auteur correspondant
- PersonId : 853561
- IdHAL : jean-baptiste-masson
- ORCID : 0000-0002-5484-9056
- IdRef : 26091522X
Connectez-vous pour contacter l'auteur
Résumé
Three-dimensional imaging is at the core of medical imaging and is becoming a standard in biological research. As a result, there is an increasing need to visualize, analyze and interact with data in a natural three-dimensional context. By combining stereoscopy and motion tracking, commercial virtual reality (VR) headsets provide a solution to this critical visualization challenge by allowing users to view volumetric image stacks in a highly intuitive fashion. While optimizing the visualization and interaction process in VR remains an active topic, one of the most pressing issue is how to utilize VR for annotation and analysis of data. Annotating data is often a required step for training machine learning algorithms. For example, enhancing the ability to annotate complex three-dimensional data in biological research as newly acquired data may come in limited quantities. Similarly, medical data annotation is often time-consuming and requires expert knowledge to identify structures of interest correctly. Moreover, simultaneous data analysis and visualization in VR is computationally demanding. Here, we introduce a new procedure to visualize, interact, annotate and analyze data by combining VR with cloud computing. VR is leveraged to provide natural interactions with volumetric representations of experimental imaging data. In parallel, cloud computing performs costly computations to accelerate the data annotation with minimal input required from the user. We demonstrate multiple proof-of-concept applications of our approach on volumetric fluorescent microscopy images of mouse neurons and tumor or organ annotations in medical images.
Domaines
Informatique [cs]Format du dépôt | Fichier |
---|---|
Type de dépôt | Article dans une revue |
Titre |
en
New Approach to Accelerated Image Annotation by Leveraging Virtual Reality and Cloud Computing
|
Résumé |
en
Three-dimensional imaging is at the core of medical imaging and is becoming a standard in biological research. As a result, there is an increasing need to visualize, analyze and interact with data in a natural three-dimensional context. By combining stereoscopy and motion tracking, commercial virtual reality (VR) headsets provide a solution to this critical visualization challenge by allowing users to view volumetric image stacks in a highly intuitive fashion. While optimizing the visualization and interaction process in VR remains an active topic, one of the most pressing issue is how to utilize VR for annotation and analysis of data. Annotating data is often a required step for training machine learning algorithms. For example, enhancing the ability to annotate complex three-dimensional data in biological research as newly acquired data may come in limited quantities. Similarly, medical data annotation is often time-consuming and requires expert knowledge to identify structures of interest correctly. Moreover, simultaneous data analysis and visualization in VR is computationally demanding. Here, we introduce a new procedure to visualize, interact, annotate and analyze data by combining VR with cloud computing. VR is leveraged to provide natural interactions with volumetric representations of experimental imaging data. In parallel, cloud computing performs costly computations to accelerate the data annotation with minimal input required from the user. We demonstrate multiple proof-of-concept applications of our approach on volumetric fluorescent microscopy images of mouse neurons and tumor or organ annotations in medical images.
|
Auteur(s) |
Corentin Guérinot
1, 2, 3
, Valentin Marcon
1
, Charlotte Godard
1, 4
, Thomas Blanc
3, 5
, Hippolyte Verdier
1
, Guillaume Planchon
1
, Francesca Raimondi
1, 6
, Nathalie Boddaert
6
, Mariana Alonso
2
, Kurt Sailor
2
, Pierre-Marie Lledo
2
, Bassam Hajj
5
, Mohamed El Beheiry
1
, Jean-Baptiste Masson
1
1
Décision et processus Bayesiens - Decision and Bayesian Computation
( 1090708 )
- Département de Biologie Computationnelle, 25-28 rue du Docteur Roux, 75724 Paris 15
- France
2
Perception et Mémoire / Perception and Memory
( 1090731 )
- Département de Neuroscience - 25-28, rue du docteur Roux, 75724 Paris cedex 15
- France
3
Collège Doctoral
( 1084505 )
- 21, rue de l'école de médecine
75006 Paris
- France
4
PSL -
Université Paris Sciences et Lettres
( 564132 )
- 60 rue Mazarine 75006 Paris
- France
5
PCC -
Laboratoire Physico-Chimie Curie [Institut Curie]
( 541732 )
- 11 rue Pierre et Marie Curie
75005 Paris
- France
6
Hôpital Necker - Enfants Malades [AP-HP]
( 414766 )
- 149 Rue de Sèvres 75015 Paris
- France
|
Licence |
Paternité
|
Page/Identifiant |
777101
|
Langue du document |
Anglais
|
Nom de la revue |
|
Vulgarisation |
Non
|
Comité de lecture |
Oui
|
Audience |
Internationale
|
Date de publication |
2022-01-31
|
Volume |
1
|
Projet(s) ANR |
|
Domaine(s) |
|
Financement |
|
Mots-clés |
en
virtual reality, cloud computation, one-shot learning, inference, human-in-the-loop, MRI, CT-scan
|
DOI | 10.3389/fbinf.2021.777101 |
Pubmed Id | 36303792 |
PubMed Central | PMC9580868 |
Origine :
Fichiers éditeurs autorisés sur une archive ouverte
Loading...