Five simultaneous artificial intelligence data challenges on ultrasound, CT, and MRI

• Lassau N.
• Estienne T.
• de Vomecourt P.
• Azoulay M.
• Cagnol John
• Garcia G.
• Majer M.
• Jehanno E.
• Renard-Penna R.
• Balleyguier C.
• Bidault F.
• Caramella C.
• Jacques T.
• Dubrulle F.
• Behr J.
• Poussange N.
• Bocquet J.
• Montagne S.
• Cornelis F.
• Faruch M.
• Brunelle S.
• Bresson B.
• Jalaguier-Coudray A.
• Amoretti N.
• Blum A.
• Paisant A.
• Herreros V.
• Rouviere O.
• Si-Mohamed S.
• Di Marco L.
• Hauger O.
• Garetier M.
• Pigneur F.
• Bergère A.
• Cyteval C.
• Fournier L.
• Malhaire C.
• Drape J.-L.
• Poncelet E.
• Bordonne C.
• Cauliez H.
• Budzik J.-F.
• Boisserie M.
• Willaume T.
• Molière S.
• Peyron Faure N.
• Caius Giurca S.
• Juhan V.
• Caramella T.
• Perrey A.
• Desmots F.
• Faivre-Pierre M.
• Abitbol M.
• Lotte R.
• Istrati D.
• Guenoun D.
• Luciani A.
• Zins M.
• Meder J.-F.
• Cotten A.

• Magnetic resonance imaging MRI
• Deep learning
• Computed Tomography CT
• Artificial intelligence AI
• Ultrasound

PurposeThe goal of this data challenge was to create a structured dynamic with the following objectives: (1) teach radiologists the new rules of General Data Protection Regulation (GDPR), while building a large multicentric prospective database of ultrasound, computed tomography (CT) and MRI patient images; (2) build a network including radiologists, researchers, start-ups, large companies, and students from engineering schools, and; (3) provide all French stakeholders working together during 5 data challenges with a secured framework, offering a realistic picture of the benefits and concerns in October 2018.Materials and methodsRelevant clinical questions were chosen by the Société Francaise de Radiologie. The challenge was designed to respect all French ethical and data protection constraints. Multidisciplinary teams with at least one radiologist, one engineering student, and a company and/or research lab were gathered using different networks, and clinical databases were created accordingly.ResultsFive challenges were launched: detection of meniscal tears on MRI, segmentation of renal cortex on CT, detection and characterization of liver lesions on ultrasound, detection of breast lesions on MRI, and characterization of thyroid cartilage lesions on CT. A total of 5,170 images within 4 months were provided for the challenge by 46 radiology services. Twenty-six multidisciplinary teams with 181 contestants worked for one month on the challenges. Three challenges, meniscal tears, renal cortex, and liver lesions, resulted in an accuracy > 90%. The fourth challenge (breast) reached 82% and the lastone (thyroid) 70%.ConclusionTheses five challenges were able to gather a large community of radiologists, engineers, researchers, and companies in a very short period of time. The accurate results of three of the five modalities suggest that artificial intelligence is a promising tool in these radiology modalities.