Deep Generative Medical Image Harmonization for Improving Cross‐Site Generalization in Deep Learning Predictors
Background In the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an establi...
Saved in:
| Published in | Journal of magnetic resonance imaging Vol. 55; no. 3; pp. 908 - 916 |
|---|---|
| Main Authors | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Hoboken, USA
John Wiley & Sons, Inc
01.03.2022
Wiley Subscription Services, Inc |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1053-1807 1522-2586 1522-2586 |
| DOI | 10.1002/jmri.27908 |
Cover
Loading…
| Abstract | Background
In the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross‐site generalizability.
Purpose
To develop and evaluate a deep learning‐based image harmonization method to improve cross‐site generalizability of deep learning age prediction.
Study Type
Retrospective.
Population
Eight thousand eight hundred and seventy‐six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.
Field Strength/Sequence
Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.
Assessment
StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site‐based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.
Statistical Tests
Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.
Results
Our results indicated a substantial improvement in age prediction in out‐of‐sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)‐based harmonization. In the multisite case, across the 5 out‐of‐sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN‐based harmonization.
Data Conclusion
While further research is needed, GAN‐based medical image harmonization appears to be a promising tool for improving cross‐site deep learning generalization.
Level of Evidence
4
Technical Efficacy
Stage 1 |
|---|---|
| AbstractList | BackgroundIn the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross‐site generalizability.PurposeTo develop and evaluate a deep learning‐based image harmonization method to improve cross‐site generalizability of deep learning age prediction.Study TypeRetrospective.PopulationEight thousand eight hundred and seventy‐six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.Field Strength/SequenceBrain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.AssessmentStarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site‐based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.Statistical TestsMean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.ResultsOur results indicated a substantial improvement in age prediction in out‐of‐sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)‐based harmonization. In the multisite case, across the 5 out‐of‐sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN‐based harmonization.Data ConclusionWhile further research is needed, GAN‐based medical image harmonization appears to be a promising tool for improving cross‐site deep learning generalization.Level of Evidence4Technical EfficacyStage 1 Background In the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross‐site generalizability. Purpose To develop and evaluate a deep learning‐based image harmonization method to improve cross‐site generalizability of deep learning age prediction. Study Type Retrospective. Population Eight thousand eight hundred and seventy‐six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites. Field Strength/Sequence Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. Assessment StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site‐based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data. Statistical Tests Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. Results Our results indicated a substantial improvement in age prediction in out‐of‐sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)‐based harmonization. In the multisite case, across the 5 out‐of‐sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN‐based harmonization. Data Conclusion While further research is needed, GAN‐based medical image harmonization appears to be a promising tool for improving cross‐site deep learning generalization. Level of Evidence 4 Technical Efficacy Stage 1 In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability. To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction. Retrospective. Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites. Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data. Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization. While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization. 4 TECHNICAL EFFICACY: Stage 1. In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability.BACKGROUNDIn the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability.To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction.PURPOSETo develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction.Retrospective.STUDY TYPERetrospective.Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.POPULATIONEight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites.Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.FIELD STRENGTH/SEQUENCEBrain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T.StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.ASSESSMENTStarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data.Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.STATISTICAL TESTSMean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model.Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization.RESULTSOur results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization.While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization.DATA CONCLUSIONWhile further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization.4 TECHNICAL EFFICACY: Stage 1.LEVEL OF EVIDENCE4 TECHNICAL EFFICACY: Stage 1. |
| Author | Völzke, Henry Wolk, David A. Abdulkadir, Ahmed Fripp, Jurgen Erus, Guray Satterthwaite, Theodore D. Maruff, Paul Nasrallah, Ilya M. Resnick, Susan M. Singh, Ashish Albert, Marilyn S. Shou, Haochang Gur, Ruben C. Bülow, Robin Koutsouleris, Nikolaos Srinivasan, Dhivya Wolf, Daniel H. Zhuo, Chuanjun Masters, Colin L. Doshi, Jimit Fan, Yong Davatzikos, Christos Bashyam, Vishnu M. Habes, Mohamad Johnson, Sterling C. Morris, John C. Gur, Raquel E. Grabe, Hans J. Bryan, Nick R. Wittfeld, Katharina |
| AuthorAffiliation | 7 German Centre for Cardiovascular Research, Partner Site Greifswald, Germany 10 Department of Psychiatry and Psychotherapy, Ludwig Maximilian University of Munich 9 CSIRO Health and Biosecurity, Australian e-Health Research Centre CSIRO 13 Department of Neurology, Washington University in St. Louis 17 Laboratory of Behavioral Neuroscience, National Institute on Aging 11 Department of Psychiatry, University of Pennsylvania 1 Artificial Intelligence in Biomedical Imaging Lab, University of Pennsylvania, Philadelphia, PA, USA 2 Biggs Alzheimer’s Institute, University of Texas San Antonio Health Science Center, USA 3 Florey Institute of Neuroscience and Mental Health, University of Melbourne 19 Institute of Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Germany 4 Tianjin Mental Health Center, Nankai University Affiliated Tianjin Anding Hospital, Tianjin, China 8 Wisconsin Alzheimer’s Institute, University of Wisconsin School of Medicine and Public Health 6 Institute for Comm |
| AuthorAffiliation_xml | – name: 1 Artificial Intelligence in Biomedical Imaging Lab, University of Pennsylvania, Philadelphia, PA, USA – name: 2 Biggs Alzheimer’s Institute, University of Texas San Antonio Health Science Center, USA – name: 12 Department of Radiology, University of Pennsylvania – name: 18 Department of Diagnostic Medicine, University of Texas at Austin – name: 15 Department of Psychiatry and Psychotherapy, University Medicine Greifswald, Germany – name: 4 Tianjin Mental Health Center, Nankai University Affiliated Tianjin Anding Hospital, Tianjin, China – name: 9 CSIRO Health and Biosecurity, Australian e-Health Research Centre CSIRO – name: 13 Department of Neurology, Washington University in St. Louis – name: 7 German Centre for Cardiovascular Research, Partner Site Greifswald, Germany – name: 5 Department of Psychiatry, Tianjin Medical University, Tianjin, China – name: 6 Institute for Community Medicine, University Medicine Greifswald, Germany – name: 11 Department of Psychiatry, University of Pennsylvania – name: 10 Department of Psychiatry and Psychotherapy, Ludwig Maximilian University of Munich – name: 14 Department of Neurology, Johns Hopkins University School of Medicine – name: 16 German Center for Neurodegenerative Diseases (DZNE), Site Rostock/Greifswald, Germany – name: 20 Department of Neurology, University of Pennsylvania – name: 8 Wisconsin Alzheimer’s Institute, University of Wisconsin School of Medicine and Public Health – name: 17 Laboratory of Behavioral Neuroscience, National Institute on Aging – name: 21 Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania – name: 3 Florey Institute of Neuroscience and Mental Health, University of Melbourne – name: 19 Institute of Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Germany |
| Author_xml | – sequence: 1 givenname: Vishnu M. orcidid: 0000-0002-8460-4957 surname: Bashyam fullname: Bashyam, Vishnu M. email: vishnu.bashyam@pennmedicine.upenn.edu organization: University of Pennsylvania – sequence: 2 givenname: Jimit surname: Doshi fullname: Doshi, Jimit organization: University of Pennsylvania – sequence: 3 givenname: Guray surname: Erus fullname: Erus, Guray organization: University of Pennsylvania – sequence: 4 givenname: Dhivya surname: Srinivasan fullname: Srinivasan, Dhivya organization: University of Pennsylvania – sequence: 5 givenname: Ahmed surname: Abdulkadir fullname: Abdulkadir, Ahmed organization: University of Pennsylvania – sequence: 6 givenname: Ashish surname: Singh fullname: Singh, Ashish organization: University of Pennsylvania – sequence: 7 givenname: Mohamad surname: Habes fullname: Habes, Mohamad organization: University of Texas San Antonio Health Science Center – sequence: 8 givenname: Yong surname: Fan fullname: Fan, Yong organization: University of Pennsylvania – sequence: 9 givenname: Colin L. surname: Masters fullname: Masters, Colin L. organization: University of Melbourne – sequence: 10 givenname: Paul surname: Maruff fullname: Maruff, Paul organization: University of Melbourne – sequence: 11 givenname: Chuanjun surname: Zhuo fullname: Zhuo, Chuanjun organization: Tianjin Medical University – sequence: 12 givenname: Henry surname: Völzke fullname: Völzke, Henry organization: Partner Site Greifswald – sequence: 13 givenname: Sterling C. surname: Johnson fullname: Johnson, Sterling C. organization: University of Wisconsin School of Medicine and Public Health – sequence: 14 givenname: Jurgen surname: Fripp fullname: Fripp, Jurgen organization: Australian e‐Health Research Centre CSIRO – sequence: 15 givenname: Nikolaos surname: Koutsouleris fullname: Koutsouleris, Nikolaos organization: Ludwig Maximilian University of Munich – sequence: 16 givenname: Theodore D. surname: Satterthwaite fullname: Satterthwaite, Theodore D. organization: University of Pennsylvania – sequence: 17 givenname: Daniel H. surname: Wolf fullname: Wolf, Daniel H. organization: University of Pennsylvania – sequence: 18 givenname: Raquel E. surname: Gur fullname: Gur, Raquel E. organization: University of Pennsylvania – sequence: 19 givenname: Ruben C. surname: Gur fullname: Gur, Ruben C. organization: University of Pennsylvania – sequence: 20 givenname: John C. surname: Morris fullname: Morris, John C. organization: Washington University in St. Louis – sequence: 21 givenname: Marilyn S. surname: Albert fullname: Albert, Marilyn S. organization: Johns Hopkins University School of Medicine – sequence: 22 givenname: Hans J. surname: Grabe fullname: Grabe, Hans J. organization: Site Rostock/Greifswald – sequence: 23 givenname: Susan M. surname: Resnick fullname: Resnick, Susan M. organization: National Institute on Aging – sequence: 24 givenname: Nick R. surname: Bryan fullname: Bryan, Nick R. organization: University of Texas at Austin – sequence: 25 givenname: Katharina surname: Wittfeld fullname: Wittfeld, Katharina organization: Site Rostock/Greifswald – sequence: 26 givenname: Robin surname: Bülow fullname: Bülow, Robin organization: University Medicine Greifswald – sequence: 27 givenname: David A. surname: Wolk fullname: Wolk, David A. organization: University of Pennsylvania – sequence: 28 givenname: Haochang surname: Shou fullname: Shou, Haochang organization: University of Pennsylvania – sequence: 29 givenname: Ilya M. surname: Nasrallah fullname: Nasrallah, Ilya M. organization: University of Pennsylvania – sequence: 30 givenname: Christos surname: Davatzikos fullname: Davatzikos, Christos email: christos.davatzikos@pennmedicine.upenn.edu organization: University of Pennsylvania |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34564904$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kctuEzEUhq2qVW-w4QHQSGwQ0hSPb2NvKqEAbapUoBbWlus5CY5m7NSeBJUVj8Az8iR4krSCqmJly-c7n87xf4R2ffCA0IsKn1QYk7fzLroTUissd9BhxQkpCZdiN98xp2UlcX2AjlKaY4yVYnwfHVDGBVOYHaLb9wCL4gw8RNO7FRSX0Dhr2mLcmRkU5yZ2wbsfuRZ8MQ0xvy9iWDk_K0YxpPT7569r18PW0N6Tzhdr8QRM9AP8OQ7ePsT0DO1NTZvg-fY8Rl8_fvgyOi8nn87Go3eT0jImZVk3nCtsa6YoB0WYIcTyprHMAuVUAa4pECUN3GCDFROUiMZyTgmIWlph6TE63XgXy5sOGgu-zwPqRXSdiXc6GKf_rXj3Tc_CSkvJGKYyC15vBTHcLiH1unPJQtsaD2GZNOG1UJWQhGX01SN0HpbR5_U0EUQSWjExCF_-PdHDKPdpZODNBrDD10aYPiAV1kPUeohar6POMH4EW9evfz9v49qnW6pNy3fXwt1_5Pri8mq86fkDqiO9sA |
| CitedBy_id | crossref_primary_10_1002_acm2_13739 crossref_primary_10_1109_JAS_2023_123123 crossref_primary_10_1360_SSV_2023_0297 crossref_primary_10_1002_hbm_26422 crossref_primary_10_1002_mp_16850 crossref_primary_10_1002_jmri_28887 crossref_primary_10_1088_1361_6560_aca388 crossref_primary_10_1038_s44172_023_00140_w crossref_primary_10_3390_cancers15092573 crossref_primary_10_1016_j_media_2024_103388 crossref_primary_10_1155_2022_5690879 crossref_primary_10_1016_S1470_2045_24_00315_2 crossref_primary_10_1016_j_compbiomed_2023_106973 crossref_primary_10_1038_s41598_024_85032_5 crossref_primary_10_1186_s13014_025_02590_2 crossref_primary_10_1111_jon_13043 crossref_primary_10_1111_jcpp_13593 crossref_primary_10_1186_s12888_022_04509_7 crossref_primary_10_1186_s12938_024_01280_6 crossref_primary_10_1371_journal_pcbi_1010778 crossref_primary_10_1016_j_heliyon_2023_e22647 crossref_primary_10_1038_s41398_024_03024_5 crossref_primary_10_1016_j_neuroimage_2024_120665 crossref_primary_10_1016_j_neuroimage_2023_120125 crossref_primary_10_1016_j_ynirp_2024_100195 crossref_primary_10_1117_1_JMI_11_5_054502 crossref_primary_10_1109_TPAMI_2024_3434435 crossref_primary_10_1148_radiol_223170 crossref_primary_10_1016_j_neuroimage_2023_119898 crossref_primary_10_1016_j_neuroimage_2023_119911 crossref_primary_10_1093_jamia_ocad171 crossref_primary_10_1109_JBHI_2024_3352513 crossref_primary_10_1109_TBME_2023_3330087 crossref_primary_10_1002_mp_16965 crossref_primary_10_1016_j_mri_2022_06_004 crossref_primary_10_1109_JBHI_2024_3393870 crossref_primary_10_1007_s12149_024_01923_7 crossref_primary_10_37349_ent_2023_00034 crossref_primary_10_1016_j_media_2024_103135 crossref_primary_10_1016_j_nic_2024_12_003 crossref_primary_10_1038_s43588_024_00659_8 crossref_primary_10_3390_app13158923 |
| Cites_doi | 10.1016/j.mri.2019.05.041 10.1007/978-3-030-59728-3_70 10.1016/j.jalz.2010.03.009 10.1145/3446776 10.1016/j.acra.2013.09.010 10.1007/978-3-030-05831-9_16 10.1007/978-3-030-78191-0_27 10.1055/s-0028-1109510 10.3389/fneur.2019.00789 10.1002/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M 10.1371/journal.pmed.1001779 10.1038/s41467-019-13163-9 10.1007/978-3-030-00536-8_3 10.1109/TMI.2019.2894692 10.1109/ICCV.2017.244 10.1109/CVPR42600.2020.00821 10.1007/978-3-030-00928-1_60 10.1117/12.2513089 10.1016/B978-0-12-816176-0.00021-1 10.1016/j.neuroimage.2019.116450 10.1093/brain/awaa160 10.1371/journal.pmed.1002683 10.1016/j.media.2017.10.005 10.1016/j.media.2016.10.004 10.1006/nimg.2002.1132 10.1371/journal.pcbi.1006376 10.1002/jmri.22636 10.1016/j.media.2010.12.003 10.1109/CVPR.2016.90 10.2307/2532051 |
| ContentType | Journal Article |
| Copyright | 2021 International Society for Magnetic Resonance in Medicine. 2022 International Society for Magnetic Resonance in Medicine |
| Copyright_xml | – notice: 2021 International Society for Magnetic Resonance in Medicine. – notice: 2022 International Society for Magnetic Resonance in Medicine |
| CorporateAuthor | The iSTAGING and PHENOM consortia iSTAGING and PHENOM consortia |
| CorporateAuthor_xml | – name: The iSTAGING and PHENOM consortia – name: iSTAGING and PHENOM consortia |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 K9. P64 7X8 5PM |
| DOI | 10.1002/jmri.27908 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Biotechnology Research Abstracts Neurosciences Abstracts Technology Research Database Engineering Research Database ProQuest Health & Medical Complete (Alumni) Biotechnology and BioEngineering Abstracts MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) Engineering Research Database Biotechnology Research Abstracts Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitleList | ProQuest Health & Medical Complete (Alumni) MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1522-2586 |
| EndPage | 916 |
| ExternalDocumentID | PMC8844038 34564904 10_1002_jmri_27908 JMRI27908 |
| Genre | article Research Support, N.I.H., Intramural Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: Federal State of Mecklenburg‐West Pomerania – fundername: Swiss National Science Foundation funderid: 191026 – fundername: Federal Ministry of Education and Research funderid: 01ZZ0103; 01ZZ0403; 01ZZ9603 – fundername: Intramural Research Program – fundername: National Institute on Aging – fundername: Ministry of Cultural Affairs and the Social Ministry of the Federal State of Mecklenburg‐West Pomerania – fundername: National Institutes of Health (NIH) funderid: HHSN271201600059C; R01MH113565; R01EB022573; R01MH112070; R01MH120482; RF1AG054409 – fundername: Siemens Healthineers – fundername: NIA NIH HHS grantid: RF1 AG059869 – fundername: NIMH NIH HHS grantid: R01 MH120482 – fundername: NIA NIH HHS grantid: P30 AG072979 – fundername: NIA NIH HHS grantid: U19 AG033655 – fundername: NIA NIH HHS grantid: RF1 AG054409 – fundername: NIA NIH HHS grantid: U01 AG068057 – fundername: NIMH NIH HHS grantid: R01 MH112070 – fundername: NIH HHS grantid: S10 OD023495 – fundername: NIBIB NIH HHS grantid: R01 EB022573 – fundername: NIDA NIH HHS grantid: HHSN271201600059C |
| GroupedDBID | --- -DZ .3N .GA .GJ .Y3 05W 0R~ 10A 1L6 1OB 1OC 1ZS 24P 31~ 33P 3O- 3SF 3WU 4.4 4ZD 50Y 50Z 51W 51X 52M 52N 52O 52P 52R 52S 52T 52U 52V 52W 52X 53G 5GY 5RE 5VS 66C 702 7PT 8-0 8-1 8-3 8-4 8-5 8UM 930 A01 A03 AAESR AAEVG AAHHS AAHQN AAIPD AAMNL AANHP AANLZ AAONW AASGY AAWTL AAXRX AAYCA AAZKR ABCQN ABCUV ABEML ABIJN ABJNI ABLJU ABOCM ABPVW ABQWH ABXGK ACAHQ ACBWZ ACCFJ ACCZN ACGFO ACGFS ACGOF ACIWK ACMXC ACPOU ACPRK ACRPL ACSCC ACXBN ACXQS ACYXJ ADBBV ADBTR ADEOM ADIZJ ADKYN ADMGS ADNMO ADOZA ADXAS ADZMN AEEZP AEGXH AEIGN AEIMD AENEX AEQDE AEUQT AEUYR AFBPY AFFPM AFGKR AFPWT AFRAH AFWVQ AFZJQ AHBTC AHMBA AIACR AIAGR AITYG AIURR AIWBW AJBDE ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ASPBG ATUGU AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMXJE BROTX BRXPI BY8 C45 CS3 D-6 D-7 D-E D-F DCZOG DPXWK DR2 DRFUL DRMAN DRSTM DU5 EBD EBS EJD EMOBN F00 F01 F04 F5P FEDTE FUBAC G-S G.N GNP GODZA H.X HBH HDBZQ HF~ HGLYW HHY HHZ HVGLF HZ~ IX1 J0M JPC KBYEO KQQ LATKE LAW LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES M65 MEWTI MK4 MRFUL MRMAN MRSTM MSFUL MSMAN MSSTM MXFUL MXMAN MXSTM N04 N05 N9A NF~ NNB O66 O9- OIG OVD P2P P2W P2X P2Z P4B P4D PALCI PQQKQ Q.N Q11 QB0 QRW R.K RGB RIWAO RJQFR ROL RWI RX1 RYL SAMSI SUPJJ SV3 TEORI TWZ UB1 V2E V8K V9Y W8V W99 WBKPD WHWMO WIB WIH WIJ WIK WIN WJL WOHZO WQJ WRC WUP WVDHM WXI WXSBR XG1 XV2 ZXP ZZTAW ~IA ~WT AAYXX AEYWJ AGHNM AGQPQ AGYGG CITATION AAMMB AEFGJ AGXDD AIDQK AIDYY CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 K9. P64 7X8 5PM |
| ID | FETCH-LOGICAL-c4488-7d5590c74935e924a22c5ddc4ce3539e073e298aeb0a0946326dc5532e678c6c3 |
| IEDL.DBID | DR2 |
| ISSN | 1053-1807 1522-2586 |
| IngestDate | Thu Aug 21 18:38:50 EDT 2025 Fri Jul 11 05:34:08 EDT 2025 Fri Jul 25 09:21:37 EDT 2025 Mon Jul 21 05:45:29 EDT 2025 Thu Apr 24 23:08:29 EDT 2025 Tue Jul 01 03:56:51 EDT 2025 Wed Jan 22 16:26:07 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | StarGAN deep learning harmonization |
| Language | English |
| License | 2021 International Society for Magnetic Resonance in Medicine. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4488-7d5590c74935e924a22c5ddc4ce3539e073e298aeb0a0946326dc5532e678c6c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-8460-4957 |
| OpenAccessLink | https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/jmri.27908 |
| PMID | 34564904 |
| PQID | 2628231468 |
| PQPubID | 1006400 |
| PageCount | 9 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_8844038 proquest_miscellaneous_2576916824 proquest_journals_2628231468 pubmed_primary_34564904 crossref_primary_10_1002_jmri_27908 crossref_citationtrail_10_1002_jmri_27908 wiley_primary_10_1002_jmri_27908_JMRI27908 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | March 2022 |
| PublicationDateYYYYMMDD | 2022-03-01 |
| PublicationDate_xml | – month: 03 year: 2022 text: March 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | Hoboken, USA |
| PublicationPlace_xml | – name: Hoboken, USA – name: United States – name: Nashville |
| PublicationSubtitle | JMRI |
| PublicationTitle | Journal of magnetic resonance imaging |
| PublicationTitleAlternate | J Magn Reson Imaging |
| PublicationYear | 2022 |
| Publisher | John Wiley & Sons, Inc Wiley Subscription Services, Inc |
| Publisher_xml | – name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc |
| References | 2015; 12 2002; 17 2021; 64 1989; 45 2020; 143 2019; 10 2013; 20 2009 2019; 38 1999; 42 2011; 34 2011; 15 2018; 43 2020; 208 2019; 64 2017; 36 2021 2020 2019 2018 2017 1984 2015 2014 2018; 15 2010; 6 2018; 14 e_1_2_8_28_1 e_1_2_8_29_1 e_1_2_8_24_1 e_1_2_8_25_1 e_1_2_8_26_1 e_1_2_8_27_1 Modanwal G (e_1_2_8_15_1) 2020 e_1_2_8_3_1 e_1_2_8_2_1 e_1_2_8_5_1 Neyshabur B (e_1_2_8_8_1) 2017 e_1_2_8_4_1 e_1_2_8_7_1 e_1_2_8_6_1 e_1_2_8_9_1 e_1_2_8_20_1 e_1_2_8_21_1 e_1_2_8_22_1 e_1_2_8_23_1 e_1_2_8_40_1 e_1_2_8_17_1 e_1_2_8_18_1 e_1_2_8_39_1 e_1_2_8_19_1 e_1_2_8_13_1 e_1_2_8_36_1 e_1_2_8_14_1 e_1_2_8_35_1 e_1_2_8_38_1 e_1_2_8_16_1 e_1_2_8_37_1 e_1_2_8_32_1 e_1_2_8_10_1 e_1_2_8_31_1 e_1_2_8_11_1 e_1_2_8_34_1 e_1_2_8_12_1 e_1_2_8_33_1 e_1_2_8_30_1 |
| References_xml | – year: 2009 – year: 2020 article-title: MRI image harmonization using cycle‐consistent generative adversarial network publication-title: SPIE Medical Imaging – volume: 64 start-page: 160 year: 2019 end-page: 170 article-title: DeepHarmony: A deep learning approach to contrast harmonization across scanner changes publication-title: Magn Reson Imaging – volume: 12 issue: 3 year: 2015 article-title: UKbiobank: An open access resource for identifying the causes of a wide range of complex diseases of middle and old age publication-title: PLoS Med – volume: 15 start-page: 267 issue: 2 year: 2011 end-page: 282 article-title: Evaluating intensity normalization on MRIs of human brain with multiple sclerosis publication-title: Med Image Anal – volume: 10 start-page: 5409 issue: 1 year: 2019 article-title: Brain age prediction using deep learning uncovers associated sequence variants publication-title: Nat Commun – volume: 143 start-page: 2312 year: 2020 end-page: 2324 article-title: MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide publication-title: Brain – volume: 34 start-page: 438 issue: 2 year: 2011 end-page: 444 article-title: Effect of scanner in longitudinal studies of brain volume changes publication-title: J Magn Reson Imaging – start-page: 379 year: 2020 end-page: 399 article-title: Machine learning based imaging biomarkers in large scale population studies: A neuroimaging perspective publication-title: Handbook of Medical Image Computing and Computer Assisted Intervention – volume: 6 start-page: 291 issue: 3 year: 2010 end-page: 296 article-title: Addressing population aging and Alzheimer's disease through the Australian imaging biomarkers and lifestyle study: Collaboration with the Alzheimer's disease neuroimaging initiative publication-title: Alzheimers Dement – year: 2021 – volume: 43 start-page: 157 year: 2018 end-page: 168 article-title: Landmark‐based deep multi‐instance learning for brain disease diagnosis publication-title: Med Image Anal – volume: 10 start-page: 789 year: 2019 article-title: Ten years of BrainAGE as a neuroimaging biomarker of brain aging: What insights have we gained? publication-title: Front Neurol – volume: 208 year: 2020 article-title: Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan publication-title: Neuroimage – volume: 64 start-page: 107 issue: 3 year: 2021 end-page: 115 article-title: Understanding deep learning (still) requires rethinking generalization publication-title: Commun ACM – volume: 20 start-page: 1566 issue: 12 year: 2013 end-page: 1576 article-title: Multi‐atlas skull‐stripping publication-title: Acad Radiol – volume: 17 start-page: 825 issue: 2 year: 2002 end-page: 841 article-title: Improved optimization for the robust and accurate linear registration and motion correction of brain images publication-title: Neuroimage – volume: 36 start-page: 61 year: 2017 end-page: 78 article-title: Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation publication-title: Med Image Anal – year: 2018 – year: 2014 – volume: 42 start-page: 1072 issue: 6 year: 1999 end-page: 1081 article-title: On standardizing the MR image intensity scale publication-title: Magn Reson Med – year: 1984 – year: 2020 – volume: 45 start-page: 255 issue: 1 year: 1989 end-page: 268 article-title: A concordance correlation coefficient to evaluate reproducibility publication-title: Biometrics – start-page: 720 year: 2020 end-page: 729 – volume: 14 issue: 9 year: 2018 article-title: Modeling and prediction of clinical symptom trajectories in Alzheimer's disease using longitudinal data publication-title: PLoS Comput Biol – volume: 15 issue: 11 year: 2018 article-title: Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross‐sectional study publication-title: PLoS Med – year: 2017 – volume: 38 start-page: 2059 issue: 9 year: 2019 end-page: 2069 article-title: A universal intensity standardization method based on a many‐to‐one weak‐paired cycle generative adversarial network for magnetic resonance images publication-title: IEEE Trans Med Imaging – year: 2019 – year: 2017 article-title: Exploring generalization in deep learning publication-title: Advances in neural information processing systems – year: 2015 – ident: e_1_2_8_21_1 doi: 10.1016/j.mri.2019.05.041 – ident: e_1_2_8_18_1 doi: 10.1007/978-3-030-59728-3_70 – ident: e_1_2_8_11_1 – ident: e_1_2_8_25_1 doi: 10.1016/j.jalz.2010.03.009 – ident: e_1_2_8_6_1 doi: 10.1145/3446776 – ident: e_1_2_8_28_1 doi: 10.1016/j.acra.2013.09.010 – ident: e_1_2_8_22_1 doi: 10.1007/978-3-030-05831-9_16 – ident: e_1_2_8_33_1 – ident: e_1_2_8_19_1 doi: 10.1007/978-3-030-78191-0_27 – ident: e_1_2_8_23_1 doi: 10.1055/s-0028-1109510 – ident: e_1_2_8_39_1 doi: 10.3389/fneur.2019.00789 – ident: e_1_2_8_30_1 doi: 10.1002/(SICI)1522-2594(199912)42:6<1072::AID-MRM11>3.0.CO;2-M – ident: e_1_2_8_36_1 – ident: e_1_2_8_27_1 doi: 10.1371/journal.pmed.1001779 – ident: e_1_2_8_38_1 doi: 10.1038/s41467-019-13163-9 – ident: e_1_2_8_20_1 doi: 10.1007/978-3-030-00536-8_3 – ident: e_1_2_8_14_1 doi: 10.1109/TMI.2019.2894692 – ident: e_1_2_8_13_1 doi: 10.1109/ICCV.2017.244 – ident: e_1_2_8_17_1 doi: 10.1109/CVPR42600.2020.00821 – ident: e_1_2_8_40_1 doi: 10.1007/978-3-030-00928-1_60 – ident: e_1_2_8_10_1 – ident: e_1_2_8_32_1 doi: 10.1117/12.2513089 – ident: e_1_2_8_9_1 doi: 10.1016/B978-0-12-816176-0.00021-1 – ident: e_1_2_8_16_1 – ident: e_1_2_8_26_1 doi: 10.1016/j.neuroimage.2019.116450 – ident: e_1_2_8_24_1 – year: 2017 ident: e_1_2_8_8_1 article-title: Exploring generalization in deep learning publication-title: Advances in neural information processing systems – ident: e_1_2_8_34_1 doi: 10.1093/brain/awaa160 – ident: e_1_2_8_7_1 doi: 10.1371/journal.pmed.1002683 – ident: e_1_2_8_3_1 doi: 10.1016/j.media.2017.10.005 – ident: e_1_2_8_2_1 doi: 10.1016/j.media.2016.10.004 – ident: e_1_2_8_12_1 – ident: e_1_2_8_29_1 doi: 10.1006/nimg.2002.1132 – ident: e_1_2_8_4_1 doi: 10.1371/journal.pcbi.1006376 – ident: e_1_2_8_5_1 doi: 10.1002/jmri.22636 – year: 2020 ident: e_1_2_8_15_1 article-title: MRI image harmonization using cycle‐consistent generative adversarial network publication-title: SPIE Medical Imaging – ident: e_1_2_8_31_1 doi: 10.1016/j.media.2010.12.003 – ident: e_1_2_8_35_1 doi: 10.1109/CVPR.2016.90 – ident: e_1_2_8_37_1 doi: 10.2307/2532051 |
| SSID | ssj0009945 |
| Score | 2.559919 |
| Snippet | Background
In the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization... In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance... BackgroundIn the medical imaging domain, deep learning‐based methods have yet to see widespread clinical adoption, in part due to limited generalization... |
| SourceID | pubmedcentral proquest pubmed crossref wiley |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 908 |
| SubjectTerms | Adolescent Age Biomarkers Brain Brain - diagnostic imaging Deep Learning Domains Field strength Generative adversarial networks harmonization Histograms Humans Image Processing, Computer-Assisted - methods Magnetic resonance imaging Medical imaging Medical research Neuroimaging Population studies Prediction models Research Design Retrospective Studies StarGAN Statistical analysis Statistical tests |
| Title | Deep Generative Medical Image Harmonization for Improving Cross‐Site Generalization in Deep Learning Predictors |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjmri.27908 https://www.ncbi.nlm.nih.gov/pubmed/34564904 https://www.proquest.com/docview/2628231468 https://www.proquest.com/docview/2576916824 https://pubmed.ncbi.nlm.nih.gov/PMC8844038 |
| Volume | 55 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwELYQh6oXoJRnF-QKLiBl8fqVROoF0aIFaRHiIXFBUeLMwvII22X30lN_Qn8jv4Sx42S7BVWCWyRPHNuZGX9jez4TsilY3sqZ5kGcSghkpEyQRZoFuVFdnDAVy8Gud3SOdPtcHl6oiynyrcqFKfkh6gU3axnOX1sDT7PHnTFp6M39oNfkYewyfe1hLYuITsbcUXHsbihG_CCCVsTCmpuU74xfnZyNXkDMlycl_0awbgranyWXVePLkye3zdEwa5pf__A6vrd3c2TGY1O6WyrTJzIFxTz50PG775_Jz-8AfVoSVVsvSf0uDz24R69E2-kAddrndVIEw7ResaB7tvtPv_-cIsL1NdxVkr2Cuoo91esVPR7Yeu01QAvkfP_H2V478Fc2BAbjvCgIc4xQmAllLBRgaJdyblSeG2lAKBEDOhTgcZRCxlIMLDWCR9QKJTjgpGm0EYtkungoYJlQbTA454DxJ0OM1O1moHLdAgYtCNHtyBWyVf26xHg-c3utxl1SMjHzxI5h4sZwhWzUsv2SxeNVqUalAYm35MeEa253SqXG4q91Mdqg3VhJC3gYoQwGbQizI46NWioVpv6MsHw9McOScEKVagHL7z1ZUvSuHc93FEnJBH5322nKf1qeHHZODtzT6luEv5CP3GZzuCN1DTI9HIxgDTHWMFt3tvQMhiIlPw |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwELYQlWgvUOgLSqmr9tJKWbx-JTlWPLRLWVRRkLhFiTPbLoVAl90LJ35Cf2N_SWccb5YtVSV6i-SJHTsz42_8-Iaxd0qU7VJYGaW5hkgnxkVFYkVUOtPHCdOIEmi9o3dgO8d678SchLM5dBem5odoFtzIMry_JgOnBenNKWvo6flw0JJxSld9H1BKb0pgsH04ZY9KU5-jGBGEitqJiBt2Urk5fXd2ProDMu-elbyNYf0ktLtUZ1q98tyFdPbke2s8Klru-g9mx__u32O2GOAp_1jr0zKbg2qFLfTCBvwT9mMb4JLXXNXkKHnY6OHdc3RMvJMPUa3D1U6OeJg3ixZ8i_r_6-bnFwS5oYazieSg4r7iwPb6lX8eUr2UCegpO97dOdrqRCFrQ-Qw1EuiuMQgRbhYp8oARne5lM6UpdMOlFEpoE8BmSY5FCLH2NIifkTFMEoCzpvOOvWMzVcXFbxg3DqMzyVgCCoQJvX7BZjStkFAG2L0PHqVvZ_8u8wFSnPKrHGW1WTMMqMxzPwYrrK3jexlTeTxV6n1iQpkwZivMmklbZZqi8VvmmI0Q9pbySu4GKMMxm2ItBOJH_W81pimGUWUPanAknhGlxoBovieLakG3zzVd5JoLRS2-8Gryj--PNvrHXb909p9hF-zh52j3n623z349JI9knS5w5-wW2fzo-EYXiHkGhUb3rB-A64eKVk |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaqVqq4QCmPlr6M4AJStl6_kki9oLar3cJWVaFSLyhK7FlYaNPtdvfSEz-B38gvYew4WZYiJLhF8sSxnZnxNx77MyEvBbNtyzSP0lxCJBNloiLRLLJGDXDCVMyCW-_oH-vumTw6V-cLZK8-C1PxQzQLbs4yvL92Bj6yg90ZaeiXy_GwxePUnfRdkhqtxUGi0xl5VJr6K4oRQIionbC4ISflu7N356ejOxjz7lbJXyGsn4M6D8jHuvXV1pOvremkaJnb34gd_7d7K-R-AKf0TaVND8kClKtkuR_S74_I9QHAiFZM1c5N0pDmob1LdEu0m49RqcPBTopomDZLFnTfdf_Ht-_vEeKGGi5qyWFJfcWB6_UTPRm7et09QI_JWefww343Cnc2RAYDvSSKLYYozMQyFQowtss5N8paIw0IJVJAjwI8TXIoWI6RpUb0iGqhBAecNY024glZLK9KWCNUG4zOOWAAyhAkDQYFKKvbwKANMfoduU5e1b8uM4HQ3N2rcZFVVMw8c2OY-TFcJy8a2VFF4_FHqc1aA7JgyjcZ19ylSqXG4udNMRqhy6zkJVxNUQajNsTZCcdGPa0UpvmMcIQ9KcOSeE6VGgFH8D1fUg4_e6LvJJGSCfzua68pf2l5dtQ_7fmnZ_8ivEOWTw462bve8dsNco-7kx1-e90mWZyMp7CFeGtSbHuz-gk9fygR |
| 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=Deep+Generative+Medical+Image+Harmonization+for+Improving+Cross-Site+Generalization+in+Deep+Learning+Predictors&rft.jtitle=Journal+of+magnetic+resonance+imaging&rft.au=Bashyam%2C+Vishnu+M&rft.au=Doshi%2C+Jimit&rft.au=Erus%2C+Guray&rft.au=Srinivasan%2C+Dhivya&rft.date=2022-03-01&rft.issn=1522-2586&rft.eissn=1522-2586&rft.volume=55&rft.issue=3&rft.spage=908&rft_id=info:doi/10.1002%2Fjmri.27908&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-1807&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-1807&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-1807&client=summon |