Three artificial intelligence data challenges based on CT and MRI - Archive ouverte HAL
Article Dans Une Revue Diagnostic and Interventional Imaging Année : 2020

Three artificial intelligence data challenges based on CT and MRI

1 BIOMAPS - LaBoratoire d'Imagerie biOmédicale MultimodAle Paris-Saclay
2 IGR - Institut Gustave Roussy
3 OPIS - OPtimisation Imagerie et Santé
4 IR4M/U8081 éq.3 - Imagerie multimodale en cancérologie.
5 CRNL - Centre de recherche en neurosciences de Lyon - Lyon Neuroscience Research Center
6 DR- Bichat - Département de Radiologie [Bichat]
7 LIB - Laboratoire d'Imagerie Biomédicale [Paris]
8 CHU Henri Mondor [Créteil]
9 CHU Nîmes - Centre Hospitalier Universitaire de Nîmes
10 Département de Radiologie [CHU de Rennes]
11 CHU Bordeaux - Centre Hospitalier Universitaire de Bordeaux
12 Hôpital Cochin [AP-HP]
13 CHRU Lille - Centre Hospitalier Régional Universitaire [CHU Lille]
14 CHUGA - Centre Hospitalier Universitaire [CHU Grenoble]
15 CHU Nice - Centre Hospitalier Universitaire de Nice
16 Hôpital Avicenne [AP-HP]
17 Hôpital Bicêtre [AP-HP, Le Kremlin-Bicêtre]
18 IP - Institut Pascal
19 Centre hospitalier Saint-Joseph [Paris]
20 Centre Hospitalier [Douai, Nord]
21 Nouvel Hôpital Civil de Strasbourg
22 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
23 Centre Léon Bérard [Lyon]
24 Clinique Hartmann [Neuilly-sur-Seine]
25 CHRU Besançon - Centre Hospitalier Régional Universitaire de Besançon
26 MOTIVATE - Imagerie et modélisation Vasculaires, Thoraciques et Cérébrales
27 HCL - Hospices Civils de Lyon
28 HEGP - Hôpital Européen Georges Pompidou [APHP]
29 CERF - Collège des Enseignants de Radiologie de France
30 CIC Henri Mondor - Centre d'Investigation Clinique Henri Mondor
31 Centre Hospitalier Sainte Anne [Paris]
Emilie Chouzenoux
Antoine Khalil
Yann Diascorn
Pierre Yves Brillet
Lucie Cassagnes
Laure Fournier
Marc Zins
Alain Luciani

Résumé

Purpose: The second edition of the artificial intelligence (AI) data challenge was organized by the French Society of Radiology with the aim to: (i), work on relevant public health issues; (ii), build large, mul-ticentre, high quality databases; and (iii), include three-dimensional (3D) information and prognostic questions. Materials and methods: Relevant clinical questions were proposed by French subspecialty colleges of radiology. Their feasibility was assessed by experts in the field of AI. A dedicated platform was set up for inclusion centers to safely upload their anonymized examinations in compliance with general data protection regulation. The quality of the database was checked by experts weekly with annotations performed by radiologists. Multidisciplinary teams competed between September 11 th and October 13 th 2019. Results: Three questions were selected using different imaging and evaluation modalities, including: pulmonary nodule detection and classification from 3D computed tomography (CT), prediction of expanded disability status scale in multiple sclerosis using 3D magnetic resonance imaging (MRI) and segmentation of muscular surface for sarcopenia estimation from two-dimensional CT. A total of 4347 examinations were gathered of which only 6% were excluded. Three independent databases from 24 individual centers were created. A total of 143 participants were split into 20 multidisciplinary teams. Conclusion: Three data challenges with over 1200 general data protection regulation compliant CT or MRI examinations each were organized. Future challenges should be made with more complex situations combining histopathological or genetic information to resemble real life situations faced by radiologists in routine practice.
Fichier principal
Vignette du fichier
DIII_pdf_merged.pdf (450.62 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02921345 , version 1 (26-08-2020)

Identifiants

Citer

Nathalie Lassau, Imad Bousaid, Emilie Chouzenoux, Jean-Philippe Lamarque, Benoit Charmettant, et al.. Three artificial intelligence data challenges based on CT and MRI. Diagnostic and Interventional Imaging, In press, ⟨10.1016/j.diii.2020.03.006⟩. ⟨hal-02921345⟩
407 Consultations
910 Téléchargements

Altmetric

Partager

More