LAUSR

Spatial resolution of diffusion tensor (DT) images is usually compromised to accelerate the acquisitions and the state-of-the-art (SOTA) image super-resolution (SR) reconstruction methods are commonly based on supervised learning models. Considering that the matched low-resolution (LR) and high-resolution (HR) diffusion weighted (DW) image pairs are not easily available, we propose a semi-supervised DW image SR reconstruction method based on multiple references (MRSR) extracted from other subjects. In MRSR, the prior information of multiple high-resolution (HR) reference images is migrated into a residual-like network to assist SR reconstruction of DW images, and a CycleGAN-based semi-supervised strategy is used to train the network with 30% matched and 70% unmatched LR-HR image pairs. We evaluate the performance of the MRSR by comparing against SOTA methods on HCP dataset in terms of the quality of reconstructed DW images and diffusion metrics. MRSR achieves the best performance, with the mean PSNR/SSIM of DW images being improved at least by 14.3% /28.8% and 1% /1.4% respectively relative to SOTA unsupervised and supervised learning methods, and with the fiber orientations deviating from the ground-truth about 6.28° on average, the RMSEs of fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD) and radial diffusivity (RD) being 3.0%, 4.6%, 5.7% and 4.5% respectively relative to the ground truth. We validate the effectiveness of the proposed network structure, multiple-reference and CycleGAN-based semi-supervised learning strategies for SR reconstruction of DT images through the ablation studies. The proposed method allows us to achieve SR reconstruction for DT images with limited matched image pairs.