Computed tomography reconstruction using deep image prior and learned reconstruction methods
In this paper we describe an investigation into the application of deep learning methods for low-dose and sparse angle computed tomography using small training datasets. To motivate our work we review some of the existing approaches and obtain quantitative results after training them with different...
Saved in:
| Published in | Inverse problems Vol. 36; no. 9; pp. 94004 - 94027 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
IOP Publishing
01.09.2020
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | In this paper we describe an investigation into the application of deep learning methods for low-dose and sparse angle computed tomography using small training datasets. To motivate our work we review some of the existing approaches and obtain quantitative results after training them with different amounts of data. We find that the learned primal-dual method has an outstanding performance in terms of reconstruction quality and data efficiency. However, in general, end-to-end learned methods have two deficiencies: (a) a lack of classical guarantees in inverse problems and (b) the lack of generalization after training with insufficient data. To overcome these problems, we introduce the deep image prior approach in combination with classical regularization and an initial reconstruction. The proposed methods achieve the best results in the low-data regime in three challenging scenarios. |
|---|---|
| AbstractList | In this paper we describe an investigation into the application of deep learning methods for low-dose and sparse angle computed tomography using small training datasets. To motivate our work we review some of the existing approaches and obtain quantitative results after training them with different amounts of data. We find that the learned primal-dual method has an outstanding performance in terms of reconstruction quality and data efficiency. However, in general, end-to-end learned methods have two deficiencies: (a) a lack of classical guarantees in inverse problems and (b) the lack of generalization after training with insufficient data. To overcome these problems, we introduce the deep image prior approach in combination with classical regularization and an initial reconstruction. The proposed methods achieve the best results in the low-data regime in three challenging scenarios. |
| Author | Schmidt, Maximilian Baguer, Daniel Otero Leuschner, Johannes |
| Author_xml | – sequence: 1 givenname: Daniel Otero orcidid: 0000-0001-6550-6043 surname: Baguer fullname: Baguer, Daniel Otero email: {otero,jleuschn,schmidt4}@uni-bremen.de organization: University of Bremen Center for Industrial Mathematics (ZeTeM), Bibliothekstraße 5, 28359 Bremen, Germany – sequence: 2 givenname: Johannes orcidid: 0000-0001-7361-9523 surname: Leuschner fullname: Leuschner, Johannes organization: University of Bremen Center for Industrial Mathematics (ZeTeM), Bibliothekstraße 5, 28359 Bremen, Germany – sequence: 3 givenname: Maximilian orcidid: 0000-0001-8710-1389 surname: Schmidt fullname: Schmidt, Maximilian organization: University of Bremen Center for Industrial Mathematics (ZeTeM), Bibliothekstraße 5, 28359 Bremen, Germany |
| BookMark | eNp9kD1rwzAQhkVJoUnavaOmTnUjWbJsjyX0CwJd2q0gzrKUKMSSkeQh_742KR1KyXRwvM_x3rNAM-edRuiWkgdKqmpFmaCZ4DlZQQOcFhdo_ruaoTnJhcgKQekVWsS4J4TSipZz9LX2XT8k3eLkO78N0O-OOGjlXUxhUMl6h4do3Ra3WvfYdrDVuA_WBwyuxQcNwY3wH6LTaefbeI0uDRyivvmZS_T5_PSxfs027y9v68dNpljBUkZzYtpGl4zysmkqQUUjOOSKKMgFV0qDYqANr0vKm7ISpAHdCqGBGw51YdgSkdNdFXyMQRs5NuwgHCUlcrIjJxVyUiFPdkZE_EGUTTCVTwHs4Rx4fwKt7-XeD8GNn52L3_0Tt71kQtaS1JwQLvvWsG8TCola |
| CODEN | INPEEY |
| CitedBy_id | crossref_primary_10_1137_20M1376790 crossref_primary_10_3390_jimaging9090170 crossref_primary_10_1109_TGRS_2021_3114101 crossref_primary_10_1109_TAP_2021_3083741 crossref_primary_10_1109_TRPMS_2022_3217517 crossref_primary_10_1038_s41598_021_97226_2 crossref_primary_10_1002_nbm_5145 crossref_primary_10_1109_TCI_2022_3175309 crossref_primary_10_1088_1361_6420_ad35e3 crossref_primary_10_1109_TRPMS_2022_3148373 crossref_primary_10_1088_1361_6420_ad5d0d crossref_primary_10_1016_j_eswa_2024_125105 crossref_primary_10_1088_1361_6560_ad69f7 crossref_primary_10_3390_s23020563 crossref_primary_10_1088_1361_6420_acb2ed crossref_primary_10_1109_TPAMI_2022_3204527 crossref_primary_10_1016_j_bspc_2023_105513 crossref_primary_10_1016_j_bspc_2022_103598 crossref_primary_10_1016_j_nima_2023_168690 crossref_primary_10_1088_1361_6420_acce5e crossref_primary_10_1109_JBHI_2022_3225697 crossref_primary_10_1145_3528223_3530121 crossref_primary_10_1364_OPTICA_470712 crossref_primary_10_1109_JSTSP_2022_3215849 crossref_primary_10_1088_1361_6560_ac7e17 crossref_primary_10_1088_1361_6420_ad7d30 crossref_primary_10_1088_2399_6528_abebcf crossref_primary_10_1109_TCI_2021_3132190 crossref_primary_10_1016_j_compbiomed_2025_109853 crossref_primary_10_1186_s40658_021_00426_y crossref_primary_10_1016_j_compmedimag_2025_102530 crossref_primary_10_7498_aps_71_20211761 crossref_primary_10_1007_s12046_023_02107_1 crossref_primary_10_1007_s42979_023_02295_x crossref_primary_10_1109_TCI_2024_3414320 crossref_primary_10_3390_sym14112248 crossref_primary_10_1007_s42979_023_02210_4 crossref_primary_10_1109_TGRS_2024_3492059 crossref_primary_10_1088_1361_6560_acfdf1 crossref_primary_10_1088_1361_6501_ad7eed crossref_primary_10_1038_s41597_021_00893_z crossref_primary_10_3390_e23111481 crossref_primary_10_1002_mp_17379 crossref_primary_10_1002_mp_17413 crossref_primary_10_1007_s11431_023_2629_2 crossref_primary_10_1259_dmfr_20210437 crossref_primary_10_1016_j_media_2025_103454 crossref_primary_10_1016_j_media_2022_102382 crossref_primary_10_1109_TRPMS_2023_3281148 crossref_primary_10_1016_j_ejmp_2024_104491 crossref_primary_10_3390_s24041213 crossref_primary_10_1088_1361_6420_ac9011 crossref_primary_10_1007_s13137_024_00253_0 crossref_primary_10_3390_jimaging7030044 crossref_primary_10_1109_TCI_2024_3458397 crossref_primary_10_1109_TCI_2023_3347916 crossref_primary_10_1088_1361_6420_ac8ac6 crossref_primary_10_1109_ACCESS_2024_3509640 crossref_primary_10_3390_math11143201 crossref_primary_10_1016_j_jappgeo_2022_104645 crossref_primary_10_1109_TMM_2022_3204440 crossref_primary_10_1016_j_engappai_2022_105467 crossref_primary_10_1109_TCI_2024_3365371 crossref_primary_10_1109_TGRS_2021_3116455 crossref_primary_10_1109_TPAMI_2023_3240565 crossref_primary_10_1051_bioconf_202412902012 crossref_primary_10_3389_fcvm_2022_928546 crossref_primary_10_1190_geo2023_0428_1 crossref_primary_10_1016_j_jag_2023_103430 crossref_primary_10_1016_j_engappai_2024_108617 crossref_primary_10_1109_TGRS_2021_3062688 crossref_primary_10_1190_geo2021_0006_1 crossref_primary_10_3390_ma16041654 crossref_primary_10_1088_1361_6420_acb569 crossref_primary_10_1016_j_asoc_2024_111436 crossref_primary_10_1002_appl_202300016 crossref_primary_10_11648_j_ijmi_20251301_12 crossref_primary_10_1371_journal_pone_0304738 crossref_primary_10_1016_j_eswa_2023_120277 crossref_primary_10_1109_TCI_2024_3440063 crossref_primary_10_1016_j_neunet_2024_106740 crossref_primary_10_1038_s41377_023_01181_8 crossref_primary_10_1142_S1752890923500083 crossref_primary_10_3390_en16031387 crossref_primary_10_1109_ACCESS_2024_3382939 crossref_primary_10_1080_10589759_2023_2170374 crossref_primary_10_1109_TIP_2024_3418347 crossref_primary_10_1109_TMI_2021_3095310 crossref_primary_10_1137_21M1445697 crossref_primary_10_1142_S0217732324501815 crossref_primary_10_7717_peerj_cs_1849 crossref_primary_10_1109_ACCESS_2023_3292158 crossref_primary_10_1016_j_cmpb_2022_107167 crossref_primary_10_1038_s41598_023_27627_y crossref_primary_10_1137_22M1496542 crossref_primary_10_1016_j_asoc_2024_112598 crossref_primary_10_1364_OE_469377 crossref_primary_10_1137_24M1636617 crossref_primary_10_1016_j_csda_2024_107930 crossref_primary_10_3390_jpm14040376 crossref_primary_10_1109_TCI_2022_3233188 crossref_primary_10_1007_s10589_022_00392_w crossref_primary_10_3934_ammc_2023009 crossref_primary_10_3934_math_2024706 crossref_primary_10_1002_mrm_30114 crossref_primary_10_1109_TAP_2025_3532082 crossref_primary_10_1109_TIP_2021_3125489 crossref_primary_10_1137_23M1582862 crossref_primary_10_1109_TMI_2021_3072568 crossref_primary_10_1088_1361_6420_ac8a91 crossref_primary_10_3390_jimaging10090208 crossref_primary_10_1088_1361_6560_ac4122 crossref_primary_10_1364_BOE_441901 crossref_primary_10_1007_s42967_023_00333_2 crossref_primary_10_1016_j_ejmp_2023_102535 crossref_primary_10_1002_pamm_202100166 crossref_primary_10_1088_1361_6560_acaf47 crossref_primary_10_1364_OPTICA_492666 |
| Cites_doi | 10.1148/ryai.2020190007 10.1088/0266-5611/23/3/009 10.1137/1.9780898719284 10.1007/s10851-019-00923-x 10.1109/tmi.2018.2827462 10.1088/1361-6420/ab10ca 10.1109/tmi.2018.2888491 10.1093/biomet/81.3.425 10.1088/1361-6420/ab6d57 10.1088/1361-6420/aa9581 10.1109/tmi.1986.4307775 10.1109/tmi.2020.2964266 10.1109/tmi.2017.2715284 10.1038/nature25988 10.1109/tmi.2018.2832656 10.3390/jimaging4110128 10.1118/1.3528204 10.1109/tmi.2018.2799231 10.1109/tip.2017.2713099 10.1088/1361-6420/aaf14a 10.1073/pnas.1907377117 10.1017/s0962492919000059 10.1109/CVPR.2019.00559 10.1109/tmi.2018.2820382 |
| ContentType | Journal Article |
| Copyright | 2020 The Author(s). Published by IOP Publishing Ltd |
| Copyright_xml | – notice: 2020 The Author(s). Published by IOP Publishing Ltd |
| DBID | O3W TSCCA AAYXX CITATION |
| DOI | 10.1088/1361-6420/aba415 |
| DatabaseName | Institute of Physics Open Access Journal Titles IOPscience (Open Access) CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: O3W name: Institute of Physics Open Access Journal Titles url: http://iopscience.iop.org/ sourceTypes: Enrichment Source Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Mathematics |
| DocumentTitleAlternate | Computed tomography reconstruction using deep image prior and learned reconstruction methods |
| EISSN | 1361-6420 |
| ExternalDocumentID | 10_1088_1361_6420_aba415 ipaba415 |
| GrantInformation_xml | – fundername: Deutsche Forschungsgemeinschaft (DFG) grantid: GRK 2224/1 pi3 |
| GroupedDBID | -~X .DC 1JI 4.4 5B3 5GY 5PX 5VS 5ZH 7.M 7.Q AAGCD AAGID AAJIO AAJKP AATNI ABCXL ABHFT ABHWH ABJNI ABQJV ABVAM ACAFW ACBEA ACGFO ACGFS ACHIP AEFHF AENEX AFYNE AKPSB ALMA_UNASSIGNED_HOLDINGS AOAED ASPBG ATQHT AVWKF AZFZN CBCFC CEBXE CJUJL CRLBU CS3 DU5 EBS EDWGO EMSAF EPQRW EQZZN F5P HAK IHE IJHAN IOP IZVLO KOT KZ1 LAP LMP M45 N5L N9A O3W P2P PJBAE R4D RIN RNS RO9 ROL RPA SY9 TN5 TSCCA UCJ W28 XPP ZMT ~02 AAYXX ADACN ADEQX CITATION |
| ID | FETCH-LOGICAL-c353t-120fdbe73147bb8616b64a2c0ca264cceac3aef49714b7860baed66ea4f4a95f3 |
| IEDL.DBID | O3W |
| ISSN | 0266-5611 |
| IngestDate | Thu Apr 24 22:58:08 EDT 2025 Tue Jul 01 00:41:27 EDT 2025 Thu Jan 07 14:56:20 EST 2021 Wed Aug 21 03:33:31 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| Language | English |
| License | Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c353t-120fdbe73147bb8616b64a2c0ca264cceac3aef49714b7860baed66ea4f4a95f3 |
| Notes | IP-102631.R1 |
| ORCID | 0000-0001-8710-1389 0000-0001-7361-9523 0000-0001-6550-6043 |
| OpenAccessLink | https://iopscience.iop.org/article/10.1088/1361-6420/aba415 |
| PageCount | 24 |
| ParticipantIDs | crossref_primary_10_1088_1361_6420_aba415 crossref_citationtrail_10_1088_1361_6420_aba415 iop_journals_10_1088_1361_6420_aba415 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2020-09-01 |
| PublicationDateYYYYMMDD | 2020-09-01 |
| PublicationDate_xml | – month: 09 year: 2020 text: 2020-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Inverse problems |
| PublicationTitleAbbrev | IP |
| PublicationTitleAlternate | Inverse Problems |
| PublicationYear | 2020 |
| Publisher | IOP Publishing |
| Publisher_xml | – name: IOP Publishing |
| References | Engl (ipaba415bib16) 1996 Pelt (ipaba415bib42) 2018; 4 Leuschner (ipaba415bib33) 2019 Lunz (ipaba415bib37) 2018 Zhu (ipaba415bib49) 2018; 555 Chakrabarty (ipaba415bib10) 2019 Jin (ipaba415bib27) 2019 Gong (ipaba415bib18) 2019; 38 Hofmann (ipaba415bib25) 2007; 23 Cheng (ipaba415bib12) 2019 Jin (ipaba415bib28) 2017; 26 He (ipaba415bib23) 2016 Mataev (ipaba415bib38) 2019 Denker (ipaba415bib13) 2020 Louis (ipaba415bib36) 1989 Chen (ipaba415bib11) 2017; 36 Zuhair Nashed (ipaba415bib39) 1987 Bubba (ipaba415bib8) 2019; 35 Leuschner (ipaba415bib32) 2019 Bora (ipaba415bib7) 2017 Schwab (ipaba415bib46) 2019; 35 Hauptmann (ipaba415bib21) 2018; 37 Antun (ipaba415bib4) 2020 Armato (ipaba415bib5) 2011; 38 Kingma (ipaba415bib29) 2015 Li (ipaba415bib34) 2020 Arridge (ipaba415bib6) 2019; 28 Lempitsky (ipaba415bib31) 2018 Adler (ipaba415bib3) 2018; 37 Radon (ipaba415bib43) 1986; 5 Ronneberger (ipaba415bib45) 2015 Liu (ipaba415bib35) 2019 Gandelsman (ipaba415bib17) 2019 Buzug (ipaba415bib9) 2008 Knoll (ipaba415bib30) 2020; 2 Natterer (ipaba415bib40) 2001 Adler (ipaba415bib2) 2018 Paszke (ipaba415bib41) 2017 Yang (ipaba415bib48) 2018; 37 He (ipaba415bib22) 2020; 39 Donoho (ipaba415bib15) 1994; 81 Hoyer (ipaba415bib26) 2019 Dittmer (ipaba415bib14) 2019; 62 Van Veen (ipaba415bib47) 2018 Rieder (ipaba415bib44) 2003 Adler (ipaba415bib1) 2017; 33 Heckel (ipaba415bib24) 2020 Gottschling (ipaba415bib19) 2020 Gupta (ipaba415bib20) 2018; 37 |
| References_xml | – volume: 2 year: 2020 ident: ipaba415bib30 article-title: fastMRI: a publicly available raw k-space and DICOM dataset of knee images for accelerated MR image reconstruction using machine learning publication-title: Radiology. Artificial intelligence doi: 10.1148/ryai.2020190007 – year: 2019 ident: ipaba415bib10 article-title: The spectral bias of the deep image prior – volume: 23 start-page: 987 year: 2007 ident: ipaba415bib25 article-title: A convergence rates result for tikhonov regularization in banach spaces with non-smooth operators publication-title: Inverse Problems doi: 10.1088/0266-5611/23/3/009 – year: 2019 ident: ipaba415bib33 article-title: Deep inversion validation library – year: 2001 ident: ipaba415bib40 article-title: The mathematics of computerized tomography doi: 10.1137/1.9780898719284 – year: 2019 ident: ipaba415bib26 article-title: Neural reparameterization improves structural optimization – volume: 62 start-page: 456 year: 2019 ident: ipaba415bib14 article-title: Regularization by architecture: a deep prior approach for inverse problems publication-title: J. Math. Imaging Vis. doi: 10.1007/s10851-019-00923-x – start-page: pp 8516 year: 2018 ident: ipaba415bib37 article-title: Adversarial regularizers in inverse problems – volume: 37 start-page: 1348 year: 2018 ident: ipaba415bib48 article-title: Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2018.2827462 – volume: 35 year: 2019 ident: ipaba415bib8 article-title: Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography publication-title: Inverse Problems doi: 10.1088/1361-6420/ab10ca – volume: 38 start-page: 1655 year: 2019 ident: ipaba415bib18 article-title: PET image reconstruction using deep image prior publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2018.2888491 – year: 1996 ident: ipaba415bib16 – volume: 81 start-page: 425 year: 1994 ident: ipaba415bib15 article-title: Ideal spatial adaptation by wavelet shrinkage publication-title: Biometrika doi: 10.1093/biomet/81.3.425 – year: 2020 ident: ipaba415bib34 article-title: NETT: Solving inverse problems with deep neural networks publication-title: Inverse Problems doi: 10.1088/1361-6420/ab6d57 – year: 2020 ident: ipaba415bib13 article-title: Conditional normalizing flows for low-dose computed tomography image reconstruction – start-page: pp 7715 year: 2019 ident: ipaba415bib35 article-title: Image restoration using total variation regularized deep image prior – volume: 33 year: 2017 ident: ipaba415bib1 article-title: Solving ill-posed inverse problems using iterative deep neural networks publication-title: Inverse Problems doi: 10.1088/1361-6420/aa9581 – volume: 5 start-page: 170 year: 1986 ident: ipaba415bib43 article-title: On the determination of functions from their integral values along certain manifolds publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.1986.4307775 – year: 2003 ident: ipaba415bib44 – volume: 39 start-page: 2076 year: 2020 ident: ipaba415bib22 article-title: Radon inversion via deep learning publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2020.2964266 – volume: 36 start-page: 2524 year: 2017 ident: ipaba415bib11 article-title: Low-dose CT with a residual encoder-decoder convolutional neural network publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2017.2715284 – volume: 555 start-page: 487 year: 2018 ident: ipaba415bib49 article-title: Image reconstruction by domain-transform manifold learning publication-title: Nature doi: 10.1038/nature25988 – volume: 37 start-page: 1440 year: 2018 ident: ipaba415bib20 article-title: CNN-based projected gradient descent for consistent CT image reconstruction publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2018.2832656 – volume: 4 start-page: 128 year: 2018 ident: ipaba415bib42 article-title: Improving tomographic reconstruction from limited data using mixed-scale dense convolutional neural networks publication-title: J. Imaging doi: 10.3390/jimaging4110128 – volume: 38 start-page: 915 year: 2011 ident: ipaba415bib5 article-title: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans publication-title: Med. Phys. doi: 10.1118/1.3528204 – start-page: pp 770 year: 2016 ident: ipaba415bib23 article-title: Deep residual learning for image recognition – year: 2019 ident: ipaba415bib27 article-title: Time-dependent deep image prior for dynamic MRI – year: 2008 ident: ipaba415bib9 – start-page: pp 11018 year: 2019 ident: ipaba415bib17 article-title: “Double-DIP”: Unsupervised image decomposition via coupled deep-image-priors – year: 2020 ident: ipaba415bib24 article-title: Denoising and regularization via exploiting the structural bias of convolutional generators – year: 2020 ident: ipaba415bib19 article-title: The troublesome kernel: why deep learning for inverse problems is typically unstable – year: 2017 ident: ipaba415bib41 article-title: Automatic differentiation in PyTorch – volume: 37 start-page: 1322 year: 2018 ident: ipaba415bib3 article-title: Learned primal-dual reconstruction publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2018.2799231 – volume: 26 start-page: 4509 year: 2017 ident: ipaba415bib28 article-title: Deep convolutional neural network for inverse problems in imaging publication-title: IEEE Trans. Image Process. doi: 10.1109/tip.2017.2713099 – start-page: 53 year: 1987 ident: ipaba415bib39 article-title: A new approach to classification and regularization of ill-posed operator equations – year: 2015 ident: ipaba415bib29 article-title: Adam: a method for stochastic optimization – start-page: 234 year: 2015 ident: ipaba415bib45 article-title: U-Net: convolutional networks for biomedical image segmentation – year: 2019 ident: ipaba415bib32 article-title: The LoDoPaB-CT dataset: a benchmark dataset for low-dose CT reconstruction methods – year: 2019 ident: ipaba415bib38 article-title: DeepRED: deep image prior powered by RED – year: 2018 ident: ipaba415bib47 article-title: Compressed sensing with deep image prior and learned regularization – volume: 35 year: 2019 ident: ipaba415bib46 article-title: Deep null space learning for inverse problems: convergence analysis and rates publication-title: Inverse Problems doi: 10.1088/1361-6420/aaf14a – year: 2020 ident: ipaba415bib4 article-title: On instabilities of deep learning in image reconstruction and the potential costs of AI publication-title: Proc. Natl Acad. Sci. doi: 10.1073/pnas.1907377117 – volume: 28 start-page: 1 year: 2019 ident: ipaba415bib6 article-title: Solving inverse problems using data-driven models publication-title: Acta Numerica doi: 10.1017/s0962492919000059 – year: 2019 ident: ipaba415bib12 article-title: A bayesian perspective on the deep image prior doi: 10.1109/CVPR.2019.00559 – start-page: pp 9446 year: 2018 ident: ipaba415bib31 article-title: Deep image prior – year: 1989 ident: ipaba415bib36 – year: 2018 ident: ipaba415bib2 article-title: Deep Bayesian inversion – volume: 37 start-page: 1382 year: 2018 ident: ipaba415bib21 article-title: Model-based learning for accelerated, limited-view 3-D photoacoustic tomography publication-title: IEEE Trans. Med. Imaging doi: 10.1109/tmi.2018.2820382 – start-page: pp 537 year: 2017 ident: ipaba415bib7 article-title: Compressed sensing using generative models |
| SSID | ssj0011817 |
| Score | 2.606286 |
| Snippet | In this paper we describe an investigation into the application of deep learning methods for low-dose and sparse angle computed tomography using small training... |
| SourceID | crossref iop |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 94004 |
| SubjectTerms | computed tomography deep image prior deep learning inverse problems neural networks |
| Title | Computed tomography reconstruction using deep image prior and learned reconstruction methods |
| URI | https://iopscience.iop.org/article/10.1088/1361-6420/aba415 |
| Volume | 36 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3NS8MwFA9OL3oQP3F-zBz04CEubdIkxZOIYwp-HBzuIIR8VQZuK27_P6ZNLE5keGvhvbT82r6PvpffA-DMGmNphi3CxlpEvY9DOtUKpUJZzQulAmX-wyPrD-j9MBuugKtmL8y0jKb_0h8GouAAYWyIE92EsAT5sBl3lVb1BvM1IpioMq8n8tqUELzr4uEHC0M-SEhijfKvFRZ8Ustf94eL6W2BzRgbwutwJ9tgxU12wMYPxkB_9tDQrM52wVucyWDhfDqO3NOwTnEbWlhYNba_Q-tcCUdjbzxg-TmafkI1sbCeGOGVf2mEodKzPTDo3b7c9FEcl4AMycgcJSkurHacJJRrLVjCNKMqNdgoH_UY400sUa6gOU-o5oJhrZxlzClaUJVnBdkHq5PpxB0A6LjmViQq53lGbS50ZonGnNEi9yEaxW3Q_QZMmsglXo20-JB1TVsIWUEsK4hlgLgNLhqNMvBoLJE9989Axo9ptkTudEFuVErCZC4rSkBMZWmLw3-udATW0yqPrnvHjsGqR9yd-GBjrjugdff03KlfrS_8Q8-b |
| linkProvider | IOP Publishing |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LS8NAEF60guhBfGJ9dQ968LB2k93sJkdRS317sNiDsOwrUrBtaPv_cZKsRUXEWwI7m_BlMzObmXwfQsfOWscT6gi1zhEOMY6Y2GgSp9oZmWtdU-bfP4huj9_0k37QOa3-hRkXwfWfwWFNFFxDGBri0nbEREQgbaZtbTTEn3bh8kW0lDAhSu2GR_YyLyNA-JL1RxZBIFGIQp3yt1m-xaVFuPaXMNNZR2shP8Tn9d1soAU_2kSrX1gD4ex-TrU63UKvQZfB4dl4GPincbXNnVPD4rK5_Q077ws8GIIDwcVkMJ5gPXK4Uo0A4x8WtbD0dBv1OlfPF10SJBOIZQmbkSimuTNesohLY1IRCSO4ji21GjIfa8HNMu1znsmIG5kKarR3QnjNc66zJGc7qDEaj_wuwl4a6dJIZzJLuMtSkzhmqBQ8zyBN47SJ2p-AKRv4xEtZi3dV1bXTVJUQqxJiVUPcRKdzi6Lm0vhj7Ak8AxVeqOkf41rfxg0KxYTKVEkLSLmCpbH3z5laaPnpsqPurh9u99FKXG6rq1ayA9QA8P0h5B4zc1Strw_6EdKB |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Computed+tomography+reconstruction+using+deep+image+prior+and+learned+reconstruction+methods&rft.jtitle=Inverse+problems&rft.au=Baguer%2C+Daniel+Otero&rft.au=Leuschner%2C+Johannes&rft.au=Schmidt%2C+Maximilian&rft.date=2020-09-01&rft.issn=0266-5611&rft.eissn=1361-6420&rft.volume=36&rft.issue=9&rft.spage=94004&rft_id=info:doi/10.1088%2F1361-6420%2Faba415&rft.externalDBID=n%2Fa&rft.externalDocID=10_1088_1361_6420_aba415 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0266-5611&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0266-5611&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0266-5611&client=summon |