Back to Search Start Over

Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: The SFR 2021 Artificial Intelligence Data Challenge.

Authors :
Mulé S
Lawrance L
Belkouchi Y
Vilgrain V
Lewin M
Trillaud H
Hoeffel C
Laurent V
Ammari S
Morand E
Faucoz O
Tenenhaus A
Cotten A
Meder JF
Talbot H
Luciani A
Lassau N
Source :
Diagnostic and interventional imaging [Diagn Interv Imaging] 2023 Jan; Vol. 104 (1), pp. 43-48. Date of Electronic Publication: 2022 Oct 05.
Publication Year :
2023

Abstract

Purpose: The 2021 edition of the Artificial Intelligence Data Challenge was organized by the French Society of Radiology together with the Centre National d'Études Spatiales and CentraleSupélec with the aim to implement generative adversarial networks (GANs) techniques to provide 1000 magnetic resonance imaging (MRI) cases of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC), a rare and aggressive subtype of HCC, generated from a limited number of real cases from multiple French centers.<br />Materials and Methods: A dedicated platform was used by the seven inclusion centers to securely upload their anonymized MRI examinations including all three cross-sectional images (one late arterial and one portal-venous phase T1-weighted images and one fat-saturated T2-weighted image) in compliance with general data protection regulation. The quality of the database was checked by experts and manual delineation of the lesions was performed by the expert radiologists involved in each center. Multidisciplinary teams competed between October 11 <superscript>th</superscript> , 2021 and February 13 <superscript>th</superscript> , 2022.<br />Results: A total of 91 MTM-HCC datasets of three images each were collected from seven French academic centers. Six teams with a total of 28 individuals participated in this challenge. Each participating team was asked to generate one thousand 3-image cases. The qualitative evaluation was performed by three radiologists using the Likert scale on ten randomly selected cases generated by each participant. A quantitative evaluation was also performed using two metrics, the Frechet inception distance and a leave-one-out accuracy of a 1-Nearest Neighbor algorithm.<br />Conclusion: This data challenge demonstrates the ability of GANs techniques to generate a large number of images from a small sample of imaging examinations of a rare malignant tumor.<br />Competing Interests: Declaration of Competing Interest The authors declare that they have no competing interest.<br /> (Copyright © 2022 Société française de radiologie. Published by Elsevier Masson SAS. All rights reserved.)

Details

Language :
English
ISSN :
2211-5684
Volume :
104
Issue :
1
Database :
MEDLINE
Journal :
Diagnostic and interventional imaging
Publication Type :
Academic Journal
Accession number :
36207277
Full Text :
https://doi.org/10.1016/j.diii.2022.09.005