SOFNet: Optical-flow based large-scale slice augmentation of brain MRI

Bingxin Wei, Yang Wen, Xiaohong Liu, Xing Qi, Bin Sheng

Abstract: Highlights•The Optical-flow based data augmentation is developed as a novel approach for MRI slices. This method shows great potential in enhancing MRI super-resolution and analysis.•We introduced the Cost Volume Module (CVM) for cost volume computation and flow estimation. The proposed method outperforms state-of-the-arts, as demonstrated through extensive experiments conducted on both public datasets.