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

Vaddadi VenkateshRaji Susan MathewPhaneendra K Yalavarthy

Published in: Magma (New York, N.Y.) (2024)

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.

Keyphrases

high frequency
transcranial magnetic stimulation
deep learning
high resolution
electronic health record
big data
machine learning
artificial intelligence
convolutional neural network
virtual reality
high density