Common-Unique Decomposition Driven Diffusion Model for Contrast-Enhanced Liver MR Images Multi-Phase Interconversion

Basit Öğe Kaydı
dc.authorscopusid57195625791
dc.authorscopusid59204933500
dc.authorscopusid57222120373
dc.authorscopusid59203970200
dc.authorscopusid8945093900
dc.authorscopusid56404673400
dc.authorscopusid57189925356
dc.contributor.authorXu, Chenchu
dc.contributor.authorTian, Shijie
dc.contributor.authorWang, Boyan
dc.contributor.authorZhang, Jie
dc.contributor.authorPolat, Kemal
dc.contributor.authorAlhudhaif, Adi
dc.contributor.authorLi, Shuo
dc.date.accessioned2024-09-25T19:45:05Z
dc.date.available2024-09-25T19:45:05Z
dc.date.issued2024
dc.departmentAbant İzzet Baysal Üniversitesien_US
dc.description.abstractAll three contrast-enhanced (CE) phases (e.g., Arterial, Portal Venous, and Delay) are crucial for diagnosing liver tumors. However, acquiring all three phases is constrained due to contrast agents (CAs) risks, long imaging time, and strict imaging criteria. In this paper, we propose a novel Common-Unique Decomposition Driven Diffusion Model (CUDD-DM), capable of converting any two input phases in three phases into the remaining one, thereby reducing patient wait time, conserving medical resources, and reducing the use of CAs. 1) The Common-Unique Feature Decomposition Module, by utilizing spectral decomposition to capture both common and unique features among different inputs, not only learns correlations in highly similar areas between two input phases but also learns differences in different areas, thereby laying a foundation for the synthesis of remaining phase. 2) The Multi-scale Temporal Reset Gates Module, by bidirectional comparing lesions in current and multiple historical slices, maximizes reliance on previous slices when no lesions and minimizes this reliance when lesions are present, thereby preventing interference between consecutive slices. 3) The Diffusion Model-Driven Lesion Detail Synthesis Module, by employing a continuous and progressive generation process, accurately captures detailed features between data distributions, thereby avoiding the loss of detail caused by traditional methods (e.g., GAN) that overfocus on global distributions. Extensive experiments on a generalized CE liver tumor dataset have demonstrated that our CUDD-DM achieves state-of-the-art performance (improved the SSIM by at least 2.2% (lesions area 5.3%) comparing the seven leading methods). These results demonstrate that CUDD-DM advances CE liver tumor imaging technology. IEEEen_US
dc.description.sponsorshipNational Natural Science Foundation of China, NSFC, (62106001, U1908211); National Natural Science Foundation of China, NSFC; University Synergy Innovation Program of Anhui Province, (GXXT-2021-007); Natural Science Foundation of Anhui Province, (2208085Y19); Natural Science Foundation of Anhui Provinceen_US
dc.identifier.doi10.1109/JBHI.2024.3421254
dc.identifier.endpage14en_US
dc.identifier.issn2168-2194
dc.identifier.scopus2-s2.0-85197523193en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage1en_US
dc.identifier.urihttps://doi.org/10.1109/JBHI.2024.3421254
dc.identifier.urihttps://hdl.handle.net/20.500.12491/12852
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Journal of Biomedical and Health Informaticsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzYK_20240925en_US
dc.subjectAccuracyen_US
dc.subjectContrast-enhanced Liver Magnetic Resonance Imagingen_US
dc.subjectDelaysen_US
dc.subjectFeature Decompositionen_US
dc.subjectFeature extractionen_US
dc.subjectInterferenceen_US
dc.subjectLesionsen_US
dc.subjectLiveren_US
dc.subjectLogic gatesen_US
dc.subjectMulti-phase interconversionen_US
dc.titleCommon-Unique Decomposition Driven Diffusion Model for Contrast-Enhanced Liver MR Images Multi-Phase Interconversionen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu