Spinet-QSM: model-based deep learning with schatten p-norm regularization for improved quantitative susceptibility mapping

CONCLUSION: The proposed SpiNet-QSM showed a consistent improvement of at least 5% in terms of the high-frequency error norm (HFEN) and normalized root mean squared error (NRMSE) over other QSM reconstruction methods with limited training data.PMID:38598165 | DOI:10.1007/s10334-024-01158-7
Source: Magma - Category: Radiology Authors: Source Type: research