N Lassau1, I Bousaid2, E Chouzenoux3, J P Lamarque4, B Charmettant4, M Azoulay2, F Cotton5, A Khalil6, O Lucidarme7, F Pigneur8, Y Benaceur9, A Sadate9, M Lederlin10, F Laurent11, G Chassagnon12, O Ernst13, G Ferreti14, Y Diascorn15, P Y Brillet16, M Creze17, L Cassagnes18, C Caramella19, A Loubet20, A Dallongeville21, N Abassebay22, M Ohana23, N Banaste24, M Cadi25, J Behr26, L Boussel27, L Fournier28, M Zins29, J P Beregi30, A Luciani8, A Cotten31, J F Meder32. 1. Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; Department of Imaging, Institut Gustave Roussy, 94800 Villejuif, France. Electronic address: nathalie.lassau@gustaveroussy.fr. 2. Direction de la Transformation Numérique et des Systèmes d'Information, Gustave Roussy, 94800 Villejuif, France. 3. CVN, INRIA Saclay, 91190 Gif-sur-Yvette, France. 4. Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France. 5. Observatoire Français de la Sclérose en Plaques, Centre de Recherche en Neurosciences de Lyon, INSERM 1028 et CNRS UMR 5292, 69003 Lyon, France. 6. Department of Radiology, Hôpital Bichat, Assistance Publique-Hopitaux de Paris, 75018 Paris, France. 7. Sorbonne Université, CNRS, INSERM, Laboratoire d'Imagerie Biomédicale (LIB), Department of Radiology, Hôpital Pitié-Salpêtrière Assistance Publique-Hopitaux de Paris, 75013 Paris, France. 8. Department of Radiology, Assistance Publique-Hopitaux de Paris, Groupe Henri Mondor-Albert Chenevier, 94010 Créteil, France. 9. Department of Radiology, CHU Nîmes, 30189 Nîmes, France. 10. Department of Radiology, CHU Rennes, 35033 Rennes, France. 11. Department of Radiology, CHU de Bordeaux, 33000 Bordeaux, France. 12. Department of Radiology, Cochin Hospital, Assistance Publique-Hopitaux de Paris, 75014 Paris, France; Université de Paris, Descartes-Paris 5, 75006 Paris, France. 13. Department of Radiology, CHU de Lille, Hôpital Huriez, 59037 Lille, France. 14. Department of Diagnostic & Interventional Radiology, CS 10217, 38043 Grenoble, France. 15. Department of Radiology, CHU de Nice, Hôpital Pasteur, 06000 Nice, France. 16. Department of Radiology, Hôpital Avicenne, Assistance Publique-Hopitaux de Paris & Université Paris 13, INSERM UMR 1272 Hypoxie et Poumon, 93022 Bobigny, France. 17. Department of Radiology, Hôpital Bicêtre, Assistance Publique-Hopitaux de Paris, 94270 Le Kremlin-Bicêtre, France. 18. Department of Radiology, CHU de Clermont-Ferrand, Hôpital Montpied, 63003 Clermont-Ferrand, France. 19. Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; Department of Imaging, Institut Gustave Roussy, 94800 Villejuif, France. 20. Department of Radiology, CHU Montpellier, 34295 Montpellier, France. 21. Department of Radiology, GHSPJ, 75014 Paris, France. 22. Department of Radiology, CH Douai, 59507 Douai, France. 23. Department of Radiology, Nouvel Hôpital Civil, 67000 Strasbourg, France. 24. Department of Radiology, Centre Leon Berard, 69008 Lyon, France. 25. Clinique Hartmann, 92200 Neuilly, France. 26. Department of Radiology, CHRU de Jean-Minjoz Besançon, 25030 Besançon, France. 27. Department of Radiology, Hospices Civils de Lyon, Université de Lyon, 69000 Lyon, France. 28. Department of Radiology, Université de Paris, Descartes-Paris 5, Hôpital Européen Georges-Pompidou Assistance Publique-Hopitaux de Paris, 75015 Paris, France. 29. Department of Radiology, Groupe Hospitalier Paris Saint Joseph, 75014 Paris, France. 30. Collège des Enseignants de Radiologie de France (CERF, French College of Radiology Teachers), 47, rue de la Colonie, 75013 Paris, France. 31. Lille Regional University Hospital, Musculoskeletal Imaging Department, 59000 Lille, France. 32. Department of Neuroradiology, Centre Hospitalier Sainte-Anne, 75014 Paris, France; Université de Paris, Descartes-Paris 5, 75006 Paris, France.
Abstract
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, multicentre, 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 11th and October 13th 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.
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, multicentre, 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 11th and October 13th 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.