Fluid-attenuated inversion recovery MRI synthesis from multisequence MRI using three-dimensional fully convolutional networks for multiple sclerosis

Wen Wei (1, 2, 3, 4) , Emilie Poirion (2) , Benedetta Bodini (2) , Stanley Durrleman (4, 2) , Olivier Colliot (4, 2, 5) , Bruno Stankoff (2) , Nicholas Ayache (3, 1)

1 EPIONE - E-Patient : Images, données & mOdèles pour la médeciNe numériquE
2 ICM - Institut du Cerveau = Paris Brain Institute
3 COMUE UCA - COMUE Université Côte d'Azur (2015-2019)
4 ARAMIS - Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris]
5 CHU Pitié-Salpêtrière [AP-HP]

Multiple sclerosis (MS) is a white matter (WM) disease characterized by the formation of WM lesions, which can be visualized by magnetic resonance imaging (MRI). The fluid-attenuated inversion recovery (FLAIR) MRI pulse sequence is used clinically and in research for the detection of WM lesions. However, in clinical settings, some MRI pulse sequences can be missing because of various constraints. We propose to use 3D fully convolutional neural networks to predict FLAIR pulse sequences from other MRI pulse sequences. In addition, we evaluate the contribution of each input pulse sequence with a pulse-sequence-specific saliency map. Our approach is tested on a real multiple sclerosis image dataset and evaluated by comparing our approach to other methods and by assessing the lesion contrast in the synthetic FLAIR pulse sequence. Both the qualitative and quantitative results show that our method is competitive for FLAIR synthesis.

Mots clés: MR Images; FLAIR Synthesis; 3D Fully Convolutional Networks; Multiple Sclerosis; Deep Learning

Domaines: Intelligence artificielle [cs.AI]; Imagerie médicale

Wen Wei, Emilie Poirion, Benedetta Bodini, Stanley Durrleman, Olivier Colliot, et al.. Fluid-attenuated inversion recovery MRI synthesis from multisequence MRI using three-dimensional fully convolutional networks for multiple sclerosis. Journal of Medical Imaging, 2019, 6 (01), ⟨10.1117/1.JMI.6.1.014005⟩. ⟨hal-02042526v2⟩