Super-Resolution with compressively sensed MR/PET signals at its input

Abstract

Abstract The aim of this paper is to present a highly effective Magnetic Resonance Imaging- Positron Emission Tomography (MR/PET) image reconstruction strategy allowing for simultaneous resolution enhancing and scanning time minimisation. The presented algorithm employs the combined sparsity, compressed sensing (CS) theory and super resolution to achieve high-resolution output maintaining data collecting steps at the lowest possible levels. This paper presents a very promising application of super-resolution of highly sensitively compressed MR/PET raw data. The presented algorithm nests image priors, deblurring, and a discrete dense displacement sampling for the deformable registration of high-resolution images at its core. Data from preliminary trials can also be valuable in providing background information useful in reducing examinations times. In accordance with expectations, the presented algorithm can enhance image resolution without any hardware modifications. However, the motion estimation algorithm can drastically eliminate diagnostic image artifacts that increase the chances of a correct diagnosis. The robustness of the suggested algorithm was subjected to state-of-the art image resolution enhancement algorithms: 3D kernel regression, Enhanced Deep Residual Networks for Single Image Super-Resolution, Image Super-Resolution Using Very Deep Residual Channel Attention Networks, Residual Dense Network for Image Super-Resolution. It is worth underlining that combining Compressed Sensing with its conjugate symmetry, as well as Partial Fourier methodology leads to data acquisition acceleration when compared to the different and unmodified k-space sampling patterns. It can be clearly seen that the obtained improvements have led to much better sharpness, edge interpretations, and contrast. Moreover, the accomplishments have been validated by PSNR. In accordance with expectations, the presented algorithm is able to enhance image resolution without any hardware adjustments. Besides the resolution tradeoffs, this method is able to minimise motion artifacts what is especially important for effective physician-to-physician communication and unbiased diagnosis.