A self-supervised super-resolution algorithm for 3D medical images. It does not require the user to provide any training data.
The code is wrapped and released in IACL website:
Setting iteration number=1 in iSMORE is equivalent to SMORE.
http://iacl.ece.jhu.edu/index.php?title=ISMORE
The methods are described in:
C Zhao, B.E. Dewey, D.L. Pham, P.A. Calabresi, D.S. Reich, and J.L. Prince, "SMORE: A Self-supervised Anti-aliasing and Super-resolution Algorithm for MRI Using Deep Learning", IEEE Trans. on Medical Imaging (TMI), 40(3):805-817, 2021. (doi)
C. Zhao, M. Shao, A. Carass, H. Li, B.E. Dewey, L.M. Ellingsen, J. Woo, M.A. Guttman, A.M. Blitz, M. Stone, P.A. Calabresi, H. Halperin, and J.L. Prince, "Applications of a deep learning method for anti-aliasing and super-resolution in MRI", Magnetic Resonance in Medicine, 64:132-141, 2019. (doi) (PubMed)
C. Zhao, S. Son, Y. Kim, and J.L. Prince, "iSMORE: An Iterative Self Super-Resolution Algorithm", 130-139, Simulation and Synthesis in Medical Imaging (SASHIMI 2019) held in conjunction with the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2019), Shenzhen, China, October 13 - 17, 2019. (best paper award)