Erratum to: Knowledge-driven deep learning for fast MR imaging: Undersampled MR image reconstruction from supervised to un-supervised learning (Magn Reson Med., (2024), 92, (496-518),10.1002/MRM.30105)

Due to a misunderstanding of a vendor approach to their reconstruction algorithm, the authors wish to remove the following sentence in the fifth paragraph of Section 4.4: “GE and Siemens solutions are applied to DICOM data after parallel imaging (PI) reconstruction, whereas Philips and UIH solutions attempt to build upon traditional CSPI and iterative algorithms to provide interpretability, and to fully utilize the domain specific experience and knowledge.”.