LAUSR

BACKGROUND: High-resolution (HR) magnetic resonance imaging (MRI) provides rich pathological information which is of great significance in diagnosis and treatment of brain lesions. However, obtaining HR brain MRI images comes at the cost of extending scan time and using sophisticated expensive instruments. OBJECTIVE: This study aims to reconstruct HR MRI images from low-resolution (LR) images by developing a deep learning based super-resolution (SR) method. METHODS: We propose a feedback network with self-attention mechanism (FNSAM) for SR reconstruction of brain MRI images. Specifically, a feedback network is built to correct shallow features by using a recurrent neural network (RNN) and the self-attention mechanism (SAM) is integrated into the feedback network for extraction of important information as the feedback signal, which promotes image hierarchy. RESULTS: Experimental results show that the proposed FNSAM obtains more reasonable SR reconstruction of brain MRI images both in peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) than some state-of-the-arts. CONCLUSION: Our proposed method is suitable for SR reconstruction of MRI images.