Simultaneous single- and multi-contrast super-resolution for brain MRI images based on a convolutional neural network

In magnetic resonance imaging (MRI), the acquired images are usually not of high enough resolution due to constraints such as long sampling times and patient comfort. High-resolution MRI images can be obtained by super-resolution techniques, which can be grouped into two categories: single-contrast super-resolution and multi-contrast super-resolution, where the former has no reference information, and the latter applies a high-resolution image of another modality as a reference. In this paper, we propose a deep convolutional neural network model, which performs single- and multi-contrast super-resolution reconstructions simultaneously. Experimental results on synthetic and real brain MRI images show that our convolutional neural network model outperforms state-of-the-art MRI super-resolution methods in terms of visual quality and objective quality criteria such as peak signal-to-noise ratio and structural similarity. •Multi-contrast MR images share similar structures but have different contrasts, e.g., the T1w and the T2w images.•MRI super-resolution (SR) can be grouped into two categories: single-contrast SR (SCSR) and multi-contrast SR (MCSR).•We attempt to simultaneously solve SCSR and MCSR problems by training a CNN.•By MCSR, similar structural information within different contrast images is integrated into the SR reconstruction.•Experimental results verify our approach to be superior to state-of-the-art super-resolution methods for MRI images.