MC-PDNET: Deep unrolled neural network for multi-contrast mr image reconstruction from undersampled k-space data

Kumari Pooja (1, 2, 3) , Zaccharie Ramzi (2, 1, 3, 4) , Chaithya Giliyar Radhakrishna (1, 2, 3) , Philippe Ciuciu (1, 2, 3)

1 NEUROSPIN - Service NEUROSPIN
2 PARIETAL - Modelling brain structure, function and variability based on high-field MRI data
3 MIND - Modèles et inférence pour les données de Neuroimagerie
4 DAP - Département d'Astrophysique (ex SAP)

Multi-contrast (MC) MR images are similar in structure and can leverage anatomical structure to perform joint reconstruction especially from a limited number of k-space data in the Compressed Sensing (CS) setting. However CS-based multi-contrast image reconstruction has shown limited performance in these highly accelerated regimes due to the use of hand-crafted group sparsity priors. Deep learning can improve outcomes by learning the joint prior across multiple weighting contrasts. In this work, we extend the primal-dual neural network (PDNet) in the multi-contrast sense. We propose a MC-PDNet architecture which takes full advantage of multi-contrast information. Using an in-house database consisting of images from T2TSE, T2*GRE and FLAIR contrasts acquired in 65 healthy volunteers, we performed a retrospective study from 4fold under-sampled data. It was shown that MC-PDNet improves image quality by at least 1dB in PSNR for each contrast individually in comparison with PD-Net and U-Net architectures.

Mots clés: MRI reconstruction; Deep learning; Multicontrast imaging

Domaines: Traitement du signal et de l'image [eess.SP]; Imagerie médicale; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]; Imagerie

Kumari Pooja, Zaccharie Ramzi, Chaithya Giliyar Radhakrishna, Philippe Ciuciu. MC-PDNET: Deep unrolled neural network for multi-contrast mr image reconstruction from undersampled k-space data. ISBI 2022 - IEEE International Symposium on Biomedical Imaging 2022, IEEE, Mar 2022, Kolkata, India. ⟨hal-03389390⟩