Physics-based network fine-tuning for robust susceptibility mapping from high-pass filtered phase
Lists
Only you see this
Abstract
A network fine-tuning step based on signal physics is proposed for deep learning based quantitative susceptibility mapping using high-pass filtered phase only to susceptibility. The proposed method showed better robustness compared to the pre-trained networks without fine-tuning when the test dataset deviated from the training dataset, such as a change in voxel size or high-pass filter cutoff frequency.
BibTeX
@inproceedings{zhang2023physics,
author = {Jinwei Zhang and Alexey Dimov and Hang Zhang and Chao Li and Thanh Nguyen and Pascal Spincemaille and Yi Wang},
title = {{Physics-based network fine-tuning for robust susceptibility mapping from high-pass filtered phase}},
booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
year = {2023},
doi = {10.58530/2022/3558},
}