Academic Journal
Reusability report: Unpaired deep-learning approaches for holographic image
| Τίτλος: | Reusability report: Unpaired deep-learning approaches for holographic image |
|---|---|
| Συγγραφείς: | Zhang, Yuhe, Ritschel, Tobias, Villanueva Perez, Pablo |
| Συνεισφορές: | Lund University, Faculty of Science, Department of Physics, Synchrotron Radiation Research, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Synkrotronljusfysik, Originator, Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), NanoLund: Centre for Nanoscience, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), NanoLund: Centre for Nanoscience, Originator, Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Nanoscience and Semiconductor Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Nanovetenskap och halvledarteknologi, Originator, Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Light and Materials, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Ljus och material, Originator, Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Photon Science and Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Avancerade ljuskällor, Originator |
| Πηγή: | Nature Machine Intelligence Advancing X-ray imaging with deep learning. 6(3):284-290 |
| Θεματικοί όροι: | Natural Sciences, Physical Sciences, Atom and Molecular Physics and Optics, Naturvetenskap, Fysik, Atom- och molekylfysik och optik (Här ingår: Kemisk fysik, kvantoptik), Computer and Information Sciences, Computer graphics and computer vision, Data- och informationsvetenskap (Datateknik), Datorgrafik och datorseende |
| Περιγραφή: | Deep-learning methods using unpaired datasets hold great potential for image reconstruction, especially in biomedical imaging where obtaining paired datasets is often difficult due to practical concerns. A recent study by Lee et al. (Nature Machine Intelligence 2023) has introduced a parameterized physical model (referred to as FMGAN) using the unpaired approach for adaptive holographic imaging, which replaces the forward generator network with a physical model parameterized on the propagation distance of the probing light. FMGAN has demonstrated its capability to reconstruct the complex phase and amplitude of objects, as well as the propagation distance, even in scenarios where the object-to-sensor distance exceeds the range of the training data. We performed additional experiments to comprehensively assess FMGAN’s capabilities and limitations. As in the original paper, we compared FMGAN to two state-of-the-art unpaired methods, CycleGAN and PhaseGAN, and evaluated their robustness and adaptability under diverse conditions. Our findings highlight FMGAN’s reproducibility and generalizability when dealing with both in-distribution and out-of-distribution data, corroborating the results reported by the original authors. We also extended FMGAN with explicit forward models describing the response of specific optical systems, which improved performance when dealing with non-perfect systems. However, we observed that FMGAN encounters difficulties when explicit forward models are unavailable. In such scenarios, PhaseGAN outperformed FMGAN. |
| Σύνδεσμος πρόσβασης: | https://doi.org/10.1038/s42256-024-00798-7 |
| Βάση Δεδομένων: | SwePub |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://doi.org/10.1038/s42256-024-00798-7# Name: EDS - SwePub (ns324271) Category: fullText Text: View record in SwePub |
|---|---|
| Header | DbId: edsswe DbLabel: SwePub An: edsswe.oai.portal.research.lu.se.publications.3144bef6.0304.4a57.a1fd.9eb291c75aa7 RelevancyScore: 1064 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 1064.42810058594 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Reusability report: Unpaired deep-learning approaches for holographic image – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Yuhe%22">Zhang, Yuhe</searchLink><br /><searchLink fieldCode="AR" term="%22Ritschel%2C+Tobias%22">Ritschel, Tobias</searchLink><br /><searchLink fieldCode="AR" term="%22Villanueva+Perez%2C+Pablo%22">Villanueva Perez, Pablo</searchLink> – Name: Author Label: Contributors Group: Au Data: Lund University, Faculty of Science, Department of Physics, Synchrotron Radiation Research, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Synkrotronljusfysik, Originator<br />Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), NanoLund: Centre for Nanoscience, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), NanoLund: Centre for Nanoscience, Originator<br />Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Nanoscience and Semiconductor Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Nanovetenskap och halvledarteknologi, Originator<br />Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Light and Materials, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Ljus och material, Originator<br />Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Photon Science and Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Avancerade ljuskällor, Originator – Name: TitleSource Label: Source Group: Src Data: <i>Nature Machine Intelligence Advancing X-ray imaging with deep learning</i>. 6(3):284-290 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Natural+Sciences%22">Natural Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Physical+Sciences%22">Physical Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Atom+and+Molecular+Physics+and+Optics%22">Atom and Molecular Physics and Optics</searchLink><br /><searchLink fieldCode="DE" term="%22Naturvetenskap%22">Naturvetenskap</searchLink><br /><searchLink fieldCode="DE" term="%22Fysik%22">Fysik</searchLink><br /><searchLink fieldCode="DE" term="%22Atom-+och+molekylfysik+och+optik+%28Här+ingår%3A+Kemisk+fysik%22">Atom- och molekylfysik och optik (Här ingår: Kemisk fysik</searchLink><br /><searchLink fieldCode="DE" term="%22kvantoptik%29%22">kvantoptik)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+and+Information+Sciences%22">Computer and Information Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+graphics+and+computer+vision%22">Computer graphics and computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Data-+och+informationsvetenskap+%28Datateknik%29%22">Data- och informationsvetenskap (Datateknik)</searchLink><br /><searchLink fieldCode="DE" term="%22Datorgrafik+och+datorseende%22">Datorgrafik och datorseende</searchLink> – Name: Abstract Label: Description Group: Ab Data: Deep-learning methods using unpaired datasets hold great potential for image reconstruction, especially in biomedical imaging where obtaining paired datasets is often difficult due to practical concerns. A recent study by Lee et al. (Nature Machine Intelligence 2023) has introduced a parameterized physical model (referred to as FMGAN) using the unpaired approach for adaptive holographic imaging, which replaces the forward generator network with a physical model parameterized on the propagation distance of the probing light. FMGAN has demonstrated its capability to reconstruct the complex phase and amplitude of objects, as well as the propagation distance, even in scenarios where the object-to-sensor distance exceeds the range of the training data. We performed additional experiments to comprehensively assess FMGAN’s capabilities and limitations. As in the original paper, we compared FMGAN to two state-of-the-art unpaired methods, CycleGAN and PhaseGAN, and evaluated their robustness and adaptability under diverse conditions. Our findings highlight FMGAN’s reproducibility and generalizability when dealing with both in-distribution and out-of-distribution data, corroborating the results reported by the original authors. We also extended FMGAN with explicit forward models describing the response of specific optical systems, which improved performance when dealing with non-perfect systems. However, we observed that FMGAN encounters difficulties when explicit forward models are unavailable. In such scenarios, PhaseGAN outperformed FMGAN. – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="https://doi.org/10.1038/s42256-024-00798-7" linkWindow="_blank">https://doi.org/10.1038/s42256-024-00798-7</link> |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.portal.research.lu.se.publications.3144bef6.0304.4a57.a1fd.9eb291c75aa7 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1038/s42256-024-00798-7 Languages: – Text: English PhysicalDescription: Pagination: PageCount: 7 StartPage: 284 Subjects: – SubjectFull: Natural Sciences Type: general – SubjectFull: Physical Sciences Type: general – SubjectFull: Atom and Molecular Physics and Optics Type: general – SubjectFull: Naturvetenskap Type: general – SubjectFull: Fysik Type: general – SubjectFull: Atom- och molekylfysik och optik (Här ingår: Kemisk fysik Type: general – SubjectFull: kvantoptik) Type: general – SubjectFull: Computer and Information Sciences Type: general – SubjectFull: Computer graphics and computer vision Type: general – SubjectFull: Data- och informationsvetenskap (Datateknik) Type: general – SubjectFull: Datorgrafik och datorseende Type: general Titles: – TitleFull: Reusability report: Unpaired deep-learning approaches for holographic image Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Yuhe – PersonEntity: Name: NameFull: Ritschel, Tobias – PersonEntity: Name: NameFull: Villanueva Perez, Pablo – PersonEntity: Name: NameFull: Lund University, Faculty of Science, Department of Physics, Synchrotron Radiation Research, Lunds universitet, Naturvetenskapliga fakulteten, Fysiska institutionen, Synkrotronljusfysik, Originator – PersonEntity: Name: NameFull: Lund University, Profile areas and other strong research environments, Strategic research areas (SRA), NanoLund: Centre for Nanoscience, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Strategiska forskningsområden (SFO), NanoLund: Centre for Nanoscience, Originator – PersonEntity: Name: NameFull: Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Nanoscience and Semiconductor Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Nanovetenskap och halvledarteknologi, Originator – PersonEntity: Name: NameFull: Lund University, Profile areas and other strong research environments, Lund University Profile areas, LU Profile Area: Light and Materials, Lunds universitet, Profilområden och andra starka forskningsmiljöer, Lunds universitets profilområden, LU profilområde: Ljus och material, Originator – PersonEntity: Name: NameFull: Lund University, Faculty of Engineering, LTH, LTH Profile areas, LTH Profile Area: Photon Science and Technology, Lunds universitet, Lunds Tekniska Högskola, LTH profilområden, LTH profilområde: Avancerade ljuskällor, Originator IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 02 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 25225839 – Type: issn-locals Value: SWEPUB_FREE – Type: issn-locals Value: LU_SWEPUB Numbering: – Type: volume Value: 6 – Type: issue Value: 3 Titles: – TitleFull: Nature Machine Intelligence Advancing X-ray imaging with deep learning Type: main |
| ResultId | 1 |