Anisotropic Super Resolution In Prostate Mri Using Super Resolution Generative Adversarial Networks

Acquiring High Resolution (HR) Magnetic Resonance (MR) images requires the patient to remain still for long periods of time, which causes patient discomfort and increases the probability of motion induced image artifacts. A possible solution is to acquire low resolution (LR) images and to process them with the Super Resolution Generative Adversarial Network (SRGAN) to create a super-resolved version. This work applies SRGAN to MR images of the prostate and performs three experiments. The first experiment explores improving the in-plane MR image resolution by factors of 4 and 8, and shows that, while the PSNR and SSIM (Structural SIMilarity) metrics are lower than the isotropic bicubic interpolation baseline, the SRGAN is able to create images that have high edge fidelity. The second experiment explores anisotropic super-resolution via synthetic images, in that the input images to the network are anisotropically downsampled versions of HR images. This experiment demonstrates the ability of the modified SRGAN to perform anisotropic super-resolution, with quantitative image metrics that are comparable to those of the anisotropic bicubic interpolation baseline. Finally, the third experiment applies a modified version of the SRGAN to super-resolve anisotropic images obtained from the through-plane slices of the volumetric MR data. The output super-resolved images contain a significant amount of high frequency information that make them visually close to their HR counterparts. Overall, the promising results from each experiment show that super-resolution for MR images is a successful technique and that producing isotropic MR image volumes from anisotropic slices is an achievable goal.

[1]  Jeff Wood,et al.  Super‐resolution musculoskeletal MRI using deep learning , 2018, Magnetic resonance in medicine.

[2]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[3]  Feng Shi,et al.  Brain MRI super resolution using 3D deep densely connected neural networks , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[4]  Jinhua Yu,et al.  Reconstruction of Thin-Slice Medical Images Using Generative Adversarial Network , 2017, MLMI@MICCAI.

[5]  Anant Madabhushi,et al.  Prostatome: a combined anatomical and disease based MRI atlas of the prostate. , 2014, Medical physics.

[6]  Changsheng Hu,et al.  Super-resolution of medical image using representation learning , 2016, 2016 8th International Conference on Wireless Communications & Signal Processing (WCSP).

[7]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  François Rousseau,et al.  A non-local approach for image super-resolution using intermodality priors , 2010, Medical Image Anal..

[9]  Mirabela Rusu,et al.  An Application of Generative Adversarial Networks for Super Resolution Medical Imaging , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[10]  Rachid Deriche,et al.  The use of super‐resolution techniques to reduce slice thickness in functional MRI , 2004, Int. J. Imaging Syst. Technol..