% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Li:278685,
author = {Li, Tong and Liu, Anran and Kügler, David and Reuter,
Martin},
editor = {Colliot, Olivier and Mitra, Jhimli},
title = {{B}oost the adversarial learning with {F}ourier regulator:
bias-field correction on {MRI}},
publisher = {SPIE},
reportid = {DZNE-2025-00616},
pages = {134060Y},
year = {2025},
comment = {Medical Imaging 2025: Image Processing : [Proceedings] -
SPIE, 2025. - ISBN 97815106859019781510685901 -
doi:10.1117/12.3047299},
booktitle = {Medical Imaging 2025: Image Processing
: [Proceedings] - SPIE, 2025. - ISBN
97815106859019781510685901 -
doi:10.1117/12.3047299},
abstract = {In magnetic resonance imaging, signal intensity
inhomogeneities due to intrinsic bias field pose a
significant challenge for automated medical image analysis.
Conventional methods to mitigate these effects, such as
N4ITK, are time-consuming and unstable. The exploration of
deep learning alternative approaches is still at an unknown
stage. Previous studies have obtained preliminary results in
GAN-based models, but we found the difficulty in aligning
bias-corrected image domains with clean image domains during
adversarial learning may affect the retention of normal
organizational structures. Therefore, we propose a novel
Fourier regulator structure that can be integrated into the
general adversarial learning framework. It explicitly
decouples different levels of semantic features based on the
Fourier field and utilizes explicit feature learning to
enhance intrinsic coherence and promote more organized
domain alignment. By separating amplitude and phase features
as well as splitting low and high-frequency information, our
model preserves organizational details more efficiently and
explicitly separates intensities across organizational
boundaries. During the training process of adversarial
learning, the generator generates the target domain while
the regulator and discriminator are fixed; the regulator and
discriminator are updated in parallel while the generator is
fixed. Such a learning approach extends the original min-max
optimization problem of adversarial learning to a
multi-player mix-max optimization problem. The discriminator
can quickly draw the generative domain closer to the target
domain, while the regulator aligns the distance to the
target domain in a more explicit feature-learning manner.
Evaluated on the OASIS and BrainWeb datasets, our model
outperforms traditional and deep learning methods to enhance
homogeneity. It also shows consistent performance in other
image reconstruction tasks, demonstrating its generalization
capabilities.},
month = {Feb},
date = {2025-02-16},
organization = {SPIE Medical Imaging 2025: Image
Processing, San Diego (United States),
16 Feb 2025 - 21 Feb 2025},
cin = {AG Reuter},
cid = {I:(DE-2719)1040310},
pnm = {354 - Disease Prevention and Healthy Aging (POF4-354)},
pid = {G:(DE-HGF)POF4-354},
typ = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
doi = {10.1117/12.3047299},
url = {https://pub.dzne.de/record/278685},
}