Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks - 20/01/23

Doi : 10.1016/j.diii.2023.01.003

Vincent Couteaux ^a,^⁎ , Cheng Zhang ^a, Sébastien Mulé ^b,^c, Laurent Milot ^d, Pierre-Jean Valette ^d, Caroline Raynaud ^a, Anna Sesilia Vlachomitrou ^a, Cybele Ciofolo-Veit ^a, Littisha Lawrance ^e, Younes Belkouchi ^e,^f, Valérie Vilgrain ^g,^h, Maité Lewin ^i,^j, Hervé Trillaud ^k, Christine Hoeffel ^l, Valérie Laurent ^m, Samy Ammari ^e,ⁿ, Eric Morand ^o, Orphee Faucoz ^o, Arthur Tenenhaus ^p, Hugues Talbot ^f, Alain Luciani ^b,^c, Nathalie Lassau ^e,ⁿ, Carole Lazarus ^a
^a Philips Research France, 92150 Suresnes, France
^b Medical Imaging Department, AP-HP, Henri Mondor University Hospital, 94000 Créteil, France
^c INSERM, U955, Team 18, 94000 Créteil, France
^d Body and VIR Radiology Department, Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France
^e Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France
^f OPIS – Optimisation Imagerie et Santé, Université Paris-Saclay, Inria, CentraleSupélec, CVN - Centre de vision numérique, 91190 Gif-Sur-Yvette, France
^g Department of Radiology, APHP, University Hospitals Paris Nord-Val de Seine, Hôpital Beaujon, 92210 Clichy, France
^h Université Paris Cité, CRI INSERM, 75006 Paris, France
ⁱ Department of Radiology, AP-HP Hôpital Paul Brousse, 94800 Villejuif, France
^j Faculté de Médecine, Université Paris-Saclay, 94270 Le Kremlin-Bicêtre, France
^k CHU de Bordeaux, Department of Radiology, Université de Bordeaux, F-33000 Bordeaux, France
^l Department of Radiology, Reims University Hospital, 51092 Reims, France; CRESTIC, University of Reims Champagne-Ardenne, 51100 Reims, France
^m Department of Radiology, Nancy University Hospital, University of Lorraine, 54500 Vandoeuvre-lès-Nancy, France
ⁿ Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay, 94800 Villejuif, France
^o Centre National d'Etudes Spatiales, Centre Spatial de Toulouse, 31000 Toulouse, France
^p Université Paris-Saclay, Centrale Supélec, Laboratoire des Signaux et Systèmes, 91190 Gif-sur-Yvette, France

^⁎Corresponding author.

Sous presse. Épreuves corrigées par l'auteur. Disponible en ligne depuis le Friday 20 January 2023
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder

Highlights

•	Generative adversarial network-based methods can be used to generate realistic synthetic MR images of rare liver tumors.
•	Generative adversarial network-based methods help generate a set of synthetic data mimicking the variability of real tumors in terms of size, shape and texture.
•	Generative adversarial network-based methods can leverage the high availability of routine MR images to generate a large-scale dataset of a rare liver tumor.

Le texte complet de cet article est disponible en PDF.

Abstract

Purpose

The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC).

Materials and methods

A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance.

Results

A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64.

Conclusion

This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.

Le texte complet de cet article est disponible en PDF.

Keywords : Artificial intelligence, Data augmentation, Generative adversarial networks, Hepatocellular carcinoma, Magnetic resonance imaging

Abbreviations : FID, GAN, HCC, MTM-HCC, MR, MRI, SAGAN