000278685 001__ 278685
000278685 005__ 20250604100729.0
000278685 0247_ $$2doi$$a10.1117/12.3047299
000278685 037__ $$aDZNE-2025-00616
000278685 1001_ $$aLi, Tong$$b0
000278685 1112_ $$aSPIE Medical Imaging 2025: Image Processing$$cSan Diego$$d2025-02-16 - 2025-02-21$$wUnited States
000278685 245__ $$aBoost the adversarial learning with Fourier regulator: bias-field correction on MRI
000278685 260__ $$bSPIE$$c2025
000278685 29510 $$aMedical Imaging 2025: Image Processing : [Proceedings] - SPIE, 2025. - ISBN 97815106859019781510685901 - doi:10.1117/12.3047299
000278685 300__ $$a134060Y
000278685 3367_ $$2ORCID$$aCONFERENCE_PAPER
000278685 3367_ $$033$$2EndNote$$aConference Paper
000278685 3367_ $$2BibTeX$$aINPROCEEDINGS
000278685 3367_ $$2DRIVER$$aconferenceObject
000278685 3367_ $$2DataCite$$aOutput Types/Conference Paper
000278685 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1748937795_16670
000278685 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000278685 520__ $$aIn 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.
000278685 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0
000278685 588__ $$aDataset connected to CrossRef Conference
000278685 7001_ $$aLiu, Anran$$b1
000278685 7001_ $$0P:(DE-2719)2814290$$aKügler, David$$b2$$udzne
000278685 7001_ $$0P:(DE-2719)2812134$$aReuter, Martin$$b3$$eLast author$$udzne
000278685 7001_ $$aColliot, Olivier$$b4$$eEditor
000278685 7001_ $$aMitra, Jhimli$$b5$$eEditor
000278685 773__ $$a10.1117/12.3047299
000278685 909CO $$ooai:pub.dzne.de:278685$$pVDB
000278685 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2814290$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b2$$kDZNE
000278685 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2812134$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b3$$kDZNE
000278685 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0
000278685 9141_ $$y2025
000278685 9201_ $$0I:(DE-2719)1040310$$kAG Reuter$$lArtificial Intelligence in Medicine$$x0
000278685 980__ $$acontrib
000278685 980__ $$aVDB
000278685 980__ $$acontb
000278685 980__ $$aI:(DE-2719)1040310
000278685 980__ $$aUNRESTRICTED