Information sparsity guided transformer for multi-modal medical image super-resolution

Published: 2025, Last Modified: 12 Nov 2025Expert Syst. Appl. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Sparsity-guided SG-SRNet first explores the sparsity of medical images.•Patch selection algorithm can screen out the informative regions of medical image.•Cluster-based attention calculates attention between information-related tokens.•SG-SRNet brings significant performance enhancements with low complexity.
Loading