Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI
Background Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor‐intensive lung segmentation. Purpose To evaluate a...
Saved in:
| Published in: | Journal of magnetic resonance imaging Vol. 50; no. 4; pp. 1169 - 1181 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Hoboken, USA
John Wiley & Sons, Inc
01.10.2019
Wiley Subscription Services, Inc |
| Subjects: | |
| ISSN: | 1053-1807, 1522-2586, 1522-2586 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Background
Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor‐intensive lung segmentation.
Purpose
To evaluate a deep learning (DL) approach for automated lung segmentation to extract image‐based biomarkers from functional lung imaging using 3D radial UTE oxygen‐enhanced (OE) MRI.
Study Type
Retrospective study aimed to evaluate a technical development.
Population
Forty‐five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.
Field Strength/Sequence
1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.
Assessment
Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O2) and hyperoxic (100% O2) conditions. Automated segmentation of the lungs using 2D convolutional encoder‐decoder based DL method, and the subsequent functional quantification via adaptive K‐means were compared with the results obtained from the reference method, supervised region growing.
Statistical Tests
Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two‐sided Wilcoxon signed‐rank test for computation time, and Bland–Altman analysis on the functional measure derived from the OE images.
Results
The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland–Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs.
Data Conclusion
DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.
Level of Evidence: 2
Technical Efficacy: Stage 1
J. Magn. Reson. Imaging 2019;50:1169–1181. |
|---|---|
| AbstractList | BackgroundUltrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor‐intensive lung segmentation.PurposeTo evaluate a deep learning (DL) approach for automated lung segmentation to extract image‐based biomarkers from functional lung imaging using 3D radial UTE oxygen‐enhanced (OE) MRI.Study TypeRetrospective study aimed to evaluate a technical development.PopulationForty‐five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.Field Strength/Sequence1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.AssessmentTwo 3D radial UTE volumes were acquired sequentially under normoxic (21% O2) and hyperoxic (100% O2) conditions. Automated segmentation of the lungs using 2D convolutional encoder‐decoder based DL method, and the subsequent functional quantification via adaptive K‐means were compared with the results obtained from the reference method, supervised region growing.Statistical TestsRelative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two‐sided Wilcoxon signed‐rank test for computation time, and Bland–Altman analysis on the functional measure derived from the OE images.ResultsThe DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland–Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs.Data ConclusionDL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.Level of Evidence: 2Technical Efficacy: Stage 1J. Magn. Reson. Imaging 2019;50:1169–1181. Background Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor‐intensive lung segmentation. Purpose To evaluate a deep learning (DL) approach for automated lung segmentation to extract image‐based biomarkers from functional lung imaging using 3D radial UTE oxygen‐enhanced (OE) MRI. Study Type Retrospective study aimed to evaluate a technical development. Population Forty‐five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis. Field Strength/Sequence 1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence. Assessment Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O2) and hyperoxic (100% O2) conditions. Automated segmentation of the lungs using 2D convolutional encoder‐decoder based DL method, and the subsequent functional quantification via adaptive K‐means were compared with the results obtained from the reference method, supervised region growing. Statistical Tests Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two‐sided Wilcoxon signed‐rank test for computation time, and Bland–Altman analysis on the functional measure derived from the OE images. Results The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland–Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs. Data Conclusion DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI. Level of Evidence: 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1169–1181. Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor-intensive lung segmentation. To evaluate a deep learning (DL) approach for automated lung segmentation to extract image-based biomarkers from functional lung imaging using 3D radial UTE oxygen-enhanced (OE) MRI. Retrospective study aimed to evaluate a technical development. Forty-five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis. 1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence. Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O ) and hyperoxic (100% O ) conditions. Automated segmentation of the lungs using 2D convolutional encoder-decoder based DL method, and the subsequent functional quantification via adaptive K-means were compared with the results obtained from the reference method, supervised region growing. Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two-sided Wilcoxon signed-rank test for computation time, and Bland-Altman analysis on the functional measure derived from the OE images. The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland-Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs. DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI. 2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1169-1181. Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor-intensive lung segmentation.BACKGROUNDUltrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid biomarker extraction and regional quantification has lagged behind due to labor-intensive lung segmentation.To evaluate a deep learning (DL) approach for automated lung segmentation to extract image-based biomarkers from functional lung imaging using 3D radial UTE oxygen-enhanced (OE) MRI.PURPOSETo evaluate a deep learning (DL) approach for automated lung segmentation to extract image-based biomarkers from functional lung imaging using 3D radial UTE oxygen-enhanced (OE) MRI.Retrospective study aimed to evaluate a technical development.STUDY TYPERetrospective study aimed to evaluate a technical development.Forty-five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.POPULATIONForty-five human subjects, including 16 healthy volunteers, 5 asthma, and 24 patients with cystic fibrosis.1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.FIELD STRENGTH/SEQUENCE1.5T MRI, 3D radial UTE (TE = 0.08 msec) sequence.Two 3D radial UTE volumes were acquired sequentially under normoxic (21% O2 ) and hyperoxic (100% O2 ) conditions. Automated segmentation of the lungs using 2D convolutional encoder-decoder based DL method, and the subsequent functional quantification via adaptive K-means were compared with the results obtained from the reference method, supervised region growing.ASSESSMENTTwo 3D radial UTE volumes were acquired sequentially under normoxic (21% O2 ) and hyperoxic (100% O2 ) conditions. Automated segmentation of the lungs using 2D convolutional encoder-decoder based DL method, and the subsequent functional quantification via adaptive K-means were compared with the results obtained from the reference method, supervised region growing.Relative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two-sided Wilcoxon signed-rank test for computation time, and Bland-Altman analysis on the functional measure derived from the OE images.STATISTICAL TESTSRelative to the reference method, the performance of DL on volumetric quantification was assessed using Dice coefficient with 95% confidence interval (CI) for accuracy, two-sided Wilcoxon signed-rank test for computation time, and Bland-Altman analysis on the functional measure derived from the OE images.The DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland-Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs.RESULTSThe DL method produced strong agreement with supervised region growing for the right (Dice: 0.97; 95% CI = [0.96, 0.97]; P < 0.001) and left lungs (Dice: 0.96; 95% CI = [0.96, 0.97]; P < 0.001). The DL method averaged 46 seconds to generate the automatic segmentations in contrast to 1.93 hours using the reference method (P < 0.001). Bland-Altman analysis showed nonsignificant intermethod differences of volumetric (P ≥ 0.12) and functional measurements (P ≥ 0.34) in the left and right lungs.DL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.DATA CONCLUSIONDL provides rapid, automated, and robust lung segmentation for quantification of regional lung function using UTE proton MRI.2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1169-1181.LEVEL OF EVIDENCE2 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2019;50:1169-1181. |
| Author | Fain, Sean B. Schiebler, Mark L. Nagle, Scott K. Liu, Fang Zha, Wei Evans, Michael D. |
| Author_xml | – sequence: 1 givenname: Wei orcidid: 0000-0002-6914-8092 surname: Zha fullname: Zha, Wei email: lynnzha@gmail.com organization: University of Wisconsin‐Madison – sequence: 2 givenname: Sean B. surname: Fain fullname: Fain, Sean B. organization: University of Wisconsin‐Madison – sequence: 3 givenname: Mark L. surname: Schiebler fullname: Schiebler, Mark L. organization: University of Wisconsin‐Madison – sequence: 4 givenname: Michael D. surname: Evans fullname: Evans, Michael D. organization: University of Minnesota Twin Cities – sequence: 5 givenname: Scott K. surname: Nagle fullname: Nagle, Scott K. organization: University of Wisconsin‐Madison – sequence: 6 givenname: Fang orcidid: 0000-0001-8032-6681 surname: Liu fullname: Liu, Fang organization: University of Wisconsin‐Madison |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30945385$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kU1rFTEYhYNU7Idu_AEScCOFqW8mM5PJUmqrlYog7TpkchPNNZPc5sNL8c87ubfdFHH1vgnPOSHnHKMDH7xG6DWBMwLQvl_P0Z61A6PdM3RE-rZt2n4cDpYdetqQEdghOk5pDQCcd_0LdEhhmXTsj9Cfj1pvsAr-d3Al2-Clw16XuBt5G-KvhLc2_8RzcdlunPS60kn7VBJ2ctLO-h_YhIhdqUvxqtrguyJ9tsYquTuWVLHbmwu8iSEvF1-_X71Ez410Sb96mCfo9vLi5vxzc_3t09X5h-tGUU67hk8dJ6CnwXQrmIyCCXSnBsbkCKPhWknVd9AyDmNPmV4Ro5jkZhqBrvpBM3qC3u19l6fvik5ZzDYp7epnQkmibYESOgxQ0bdP0HUocQmlUpyQnnFKF-rNA1WmWa_EJtpZxnvxGOsCwB5QMaQUtRHK5l0QOUrrBAFRmxO1ObFrbpGcPpE8uv4TJnt4a52-_w8pviw57zV_AcMBqyA |
| CitedBy_id | crossref_primary_10_1002_jmri_28519 crossref_primary_10_1148_radiol_2021210020 crossref_primary_10_1016_j_patrec_2021_09_011 crossref_primary_10_1002_ppul_24931 crossref_primary_10_1016_j_mri_2023_07_001 crossref_primary_10_1002_jmri_28643 crossref_primary_10_1186_s12880_021_00608_1 crossref_primary_10_1002_mrm_29184 crossref_primary_10_1259_bjr_20210527 crossref_primary_10_3389_fmed_2024_1401473 crossref_primary_10_1016_j_ejro_2022_100442 crossref_primary_10_1016_j_acra_2024_10_029 crossref_primary_10_1016_j_mri_2022_06_016 crossref_primary_10_3390_ijerph19031417 crossref_primary_10_1002_jmri_28520 crossref_primary_10_1148_ryai_220239 crossref_primary_10_1259_bjr_20201107 crossref_primary_10_1016_j_jcf_2021_11_006 crossref_primary_10_1080_17476348_2023_2241355 crossref_primary_10_1183_13993003_00844_2021 crossref_primary_10_1002_mrm_27827 |
| Cites_doi | 10.1007/s00330-016-4218-5 10.1148/radiol.2017170591 10.1002/nbm.3158 10.1109/TPAMI.2016.2644615 10.1109/TMI.2016.2535302 10.1161/CIRCULATIONAHA.111.073239 10.1002/mrm.26841 10.1002/mrm.24570 10.1002/mrm.25158 10.1378/chest.12-2597 10.1002/nbm.3165 10.1148/radiol.2018181148 10.1513/AnnalsATS.201603-203OC 10.1080/21681163.2015.1124249 10.1007/174_2017_49 10.1109/TMI.2016.2528821 10.1038/nm1196-1236 10.1002/jmri.24680 10.1109/TMI.2010.2046908 10.1002/mrm.25824 10.1148/radiol.2018172322 10.1016/j.ejrad.2014.10.021 10.1136/thoraxjnl-2016-208948 10.1148/radiol.2017162326 10.1148/radiol.14132660 10.1016/j.acra.2007.10.019 10.1109/TMI.2016.2536809 10.1002/jmri.25877 10.1002/mrm.27229 10.1080/00220973.1974.10806305 10.1109/TMI.2016.2535865 10.1002/mrm.20128 10.3389/fcvm.2015.00008 10.1164/rccm.201107-1317PP 10.1109/TMI.2016.2528162 10.1002/jmri.24692 10.1016/j.acra.2016.04.005 10.1007/s11548-014-1090-0 10.1002/jmri.20290 10.1016/j.neuroimage.2018.03.065 10.1148/radiol.2017170700 |
| ContentType | Journal Article |
| Copyright | 2019 International Society for Magnetic Resonance in Medicine 2019 International Society for Magnetic Resonance in Medicine. |
| Copyright_xml | – notice: 2019 International Society for Magnetic Resonance in Medicine – notice: 2019 International Society for Magnetic Resonance in Medicine. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 K9. P64 7X8 |
| DOI | 10.1002/jmri.26734 |
| 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 |
| 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: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1522-2586 |
| EndPage | 1181 |
| ExternalDocumentID | 30945385 10_1002_jmri_26734 JMRI26734 |
| Genre | article Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: National Heart, Lung, and Blood Institute funderid: R01 HL126771; U10 HL109168 – fundername: National Center for Advancing Translational Sciences funderid: UL1TR002373 – fundername: National Institutes of Health funderid: S10 OD016394 – fundername: National Institute of Arthritis and Musculoskeletal and Skin Diseases funderid: R01 AR068373‐01 – fundername: NHLBI NIH HHS grantid: R01 HL126771 – fundername: NCATS NIH HHS grantid: UL1 TR000427 – fundername: NHLBI NIH HHS grantid: U10 HL109168 – fundername: NIH HHS grantid: S10 OD016394 – fundername: NCATS NIH HHS grantid: UL1 TR002373 |
| 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 AAMMB AAYXX AEFGJ AEYWJ AGHNM AGQPQ AGXDD AGYGG AIDQK AIDYY AIQQE CITATION O8X CGR CUY CVF ECM EIF NPM 7QO 7TK 8FD FR3 K9. P64 7X8 |
| ID | FETCH-LOGICAL-c3934-9b4910eb6f4d0bfc0b0e4c677a808f9ecac54027908537ed1fc7a9fb803d56e73 |
| IEDL.DBID | WIN |
| ISICitedReferencesCount | 23 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000486307100016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1053-1807 1522-2586 |
| IngestDate | Sun Nov 09 12:53:43 EST 2025 Sat Nov 29 14:28:25 EST 2025 Mon Jul 21 05:59:57 EDT 2025 Sat Nov 29 06:08:28 EST 2025 Tue Nov 18 21:19:28 EST 2025 Wed Jan 22 16:41:14 EST 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | lung deep learning magnetic resonance imaging asthma hyperoxia cystic fibrosis |
| Language | English |
| License | 2019 International Society for Magnetic Resonance in Medicine. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c3934-9b4910eb6f4d0bfc0b0e4c677a808f9ecac54027908537ed1fc7a9fb803d56e73 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-6914-8092 0000-0001-8032-6681 |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/7039686 |
| PMID | 30945385 |
| PQID | 2291157933 |
| PQPubID | 1006400 |
| PageCount | 13 |
| ParticipantIDs | proquest_miscellaneous_2203136607 proquest_journals_2291157933 pubmed_primary_30945385 crossref_citationtrail_10_1002_jmri_26734 crossref_primary_10_1002_jmri_26734 wiley_primary_10_1002_jmri_26734_JMRI26734 |
| PublicationCentury | 2000 |
| PublicationDate | October 2019 2019-10-00 20191001 |
| PublicationDateYYYYMMDD | 2019-10-01 |
| PublicationDate_xml | – month: 10 year: 2019 text: October 2019 |
| PublicationDecade | 2010 |
| 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 | 2019 |
| Publisher | John Wiley & Sons, Inc Wiley Subscription Services, Inc |
| Publisher_xml | – name: John Wiley & Sons, Inc – name: Wiley Subscription Services, Inc |
| References | 2015; 2 2018; 286 2019; 290 2012 2015; 73 2015; 07‐12 2018; 288 2015; 10 2014; 27 2008; 15 2013; 144 2005; 21 2013; 70 2012; 125 2014; 273 2016; 13 2016; 35 2018; 47 2016; 78 2018; 175 2018; 6 2004; 52 1974; 43 2013; 16 2015; 84 2010; 29 2015; 41 2017; 35 2018 2017 2016 2017; 284 1996; 2 2016; 26 2016; 23 2018; 79 e_1_2_6_32_1 e_1_2_6_10_1 e_1_2_6_31_1 e_1_2_6_30_1 Long J (e_1_2_6_43_1) 2015; 07 e_1_2_6_19_1 e_1_2_6_13_1 e_1_2_6_36_1 e_1_2_6_14_1 e_1_2_6_35_1 Prasoon A (e_1_2_6_40_1) 2013; 16 e_1_2_6_11_1 e_1_2_6_34_1 e_1_2_6_12_1 e_1_2_6_33_1 e_1_2_6_17_1 e_1_2_6_18_1 e_1_2_6_39_1 e_1_2_6_15_1 e_1_2_6_38_1 e_1_2_6_16_1 e_1_2_6_42_1 e_1_2_6_21_1 e_1_2_6_20_1 e_1_2_6_41_1 Pike D (e_1_2_6_8_1) 2016 e_1_2_6_9_1 e_1_2_6_5_1 e_1_2_6_4_1 e_1_2_6_7_1 e_1_2_6_6_1 e_1_2_6_25_1 e_1_2_6_48_1 e_1_2_6_24_1 e_1_2_6_3_1 e_1_2_6_23_1 e_1_2_6_2_1 e_1_2_6_22_1 e_1_2_6_29_1 e_1_2_6_44_1 e_1_2_6_28_1 e_1_2_6_45_1 e_1_2_6_27_1 Liu F (e_1_2_6_37_1) 2018 e_1_2_6_46_1 e_1_2_6_26_1 e_1_2_6_47_1 |
| References_xml | – year: 2017 article-title: SegNet: A deep convolutional encoder‐decoder architecture for scene segmentation publication-title: IEEE Trans Pattern Anal Mach Intell – volume: 16 start-page: 246 issue: Pt 2 year: 2013 end-page: 253 article-title: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network publication-title: Med Image Comput Comput Assist Interv – volume: 70 start-page: 1241 year: 2013 end-page: 1250 article-title: Optimized 3D ultrashort echo time pulmonary MRI publication-title: Magn Reson Med – volume: 15 start-page: 753 year: 2008 end-page: 762 article-title: Evaluation of structure‐function relationships in asthma using multidetector CT and hyperpolarized He‐3 MRI publication-title: Acad Radiol – start-page: 1 year: 2016 end-page: 9 article-title: Regional heterogeneity of chronic obstructive pulmonary disease phenotypes: Pulmonary 3He magnetic resonance imaging and computed tomography publication-title: COPD – volume: 35 start-page: 1207 year: 2016 end-page: 1216 article-title: Lung pattern classification for interstitial lung diseases using a deep convolutional neural network publication-title: IEEE Trans Med Imaging – volume: 35 start-page: 1285 year: 2016 end-page: 1298 article-title: Deep convolutional neural networks for computer‐aided detection: CNN architectures, dataset characteristics and transfer learning publication-title: IEEE Trans Med Imaging – volume: 2 year: 2015 article-title: Improved right ventricular performance with increased tricuspid annular excursion in athlete's heart publication-title: Front Cardiovasc Med – year: 2018 article-title: Deep convolutional neural network for segmentation of knee joint anatomy publication-title: Magn Reson Med – volume: 290 start-page: 229 year: 2019 end-page: 37 article-title: Three‐dimensional isotropic functional imaging of cystic fibrosis using oxygen‐enhanced MRI: Comparison with hyperpolarized (3)He MRI publication-title: Radiology – volume: 07‐12 start-page: 3431 year: 2015 end-page: 3440 article-title: Fully convolutional networks for semantic segmentation publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit – volume: 73 start-page: 555 year: 2015 end-page: 564 article-title: Three‐dimensional pulmonary perfusion MRI with radial ultrashort echo time and spatial‐temporal constrained reconstruction publication-title: Magn Reson Med – volume: 23 start-page: 1104 year: 2016 end-page: 1114 article-title: Semiautomated ventilation defect quantification in exercise‐induced bronchoconstriction using hyperpolarized helium‐3 magnetic resonance imaging: A repeatability study publication-title: Acad Radiol – start-page: 172986 year: 2018 article-title: Deep learning approach for evaluating knee MR images: Achieving high diagnostic performance for cartilage lesion detection publication-title: Radiology – volume: 144 start-page: 1300 year: 2013 end-page: 1310 article-title: Perfluoropropane gas as a magnetic resonance lung imaging contrast agent in humans publication-title: Chest – volume: 52 start-page: 197 year: 2004 end-page: 203 article-title: Fast isotropic volumetric coronary MR angiography using free‐breathing 3D radial balanced FFE acquisition publication-title: Magn Reson Med – volume: 273 start-page: 907 year: 2014 end-page: 916 article-title: Asthma: Comparison of dynamic oxygen‐enhanced MR imaging and quantitative thin‐section CT for evaluation of clinical treatment publication-title: Radiology – volume: 43 start-page: 61 year: 1974 end-page: 69 article-title: Robustness of the analysis of variance, the welch procedure and a box procedure to heterogeneous variances publication-title: J Exp Educ – volume: 13 start-page: 1923 year: 2016 end-page: 1931 article-title: Ultrashort echo‐time magnetic resonance imaging is a sensitive method for the evaluation of early cystic fibrosis lung disease publication-title: Ann Am Thorac Soc – start-page: 1 year: 2017 end-page: 15 – volume: 10 start-page: 403 year: 2015 end-page: 417 article-title: Automatic lung segmentation method for MRI‐based lung perfusion studies of patients with chronic obstructive pulmonary disease publication-title: Int J Comput Assist Radiol Surg – volume: 27 start-page: 1525 year: 2014 end-page: 1534 article-title: Inert fluorinated gas MRI: A new pulmonary imaging modality publication-title: NMR Biomed – volume: 26 start-page: 3811 year: 2016 end-page: 3820 article-title: Lung morphology assessment of cystic fibrosis using MRI with ultra‐short echo time at submillimeter spatial resolution publication-title: Eur Radiol – volume: 288 start-page: 177 year: 2018 end-page: 185 article-title: Use of 2D U‐Net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry publication-title: Radiology – volume: 286 start-page: 1040 year: 2018 end-page: 1051 article-title: Free‐breathing dynamic (19)F gas MR imaging for mapping of regional lung ventilation in patients with COPD publication-title: Radiology – start-page: 356 year: 2012 end-page: 362 article-title: Severe asthma: Lessons learned from the National Heart, Lung, and Blood Institute Severe Asthma Research Program publication-title: Am J Respir Crit Care Med – start-page: 760 year: 2017 end-page: 762 article-title: Detection of early subclinical lung disease in children with cystic fibrosis by lung ventilation imaging with hyperpolarised gas MRI publication-title: Thorax – volume: 84 start-page: 318 year: 2015 end-page: 326 article-title: Dynamic oxygen‐enhanced magnetic resonance imaging of the lung in asthma — Initial experience publication-title: Eur J Radiol – volume: 79 start-page: 2379 year: 2018 end-page: 2391 article-title: Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging publication-title: Magn Reson Med – volume: 175 start-page: 32 year: 2018 end-page: 44 article-title: Bayesian convolutional neural network based MRI brain extraction on nonhuman primates publication-title: Neuroimage – volume: 27 start-page: 1535 year: 2014 end-page: 1541 article-title: Oxygen‐enhanced 3D radial ultrashort echo time magnetic resonance imaging in the healthy human lung publication-title: NMR Biomed – volume: 35 start-page: 1229 year: 2016 end-page: 1239 article-title: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation publication-title: IEEE Trans Med Imaging – volume: 29 start-page: 1310 year: 2010 end-page: 1320 article-title: N4ITK: Improved N3 bias correction publication-title: IEEE Trans Med Imaging – volume: 284 start-page: 574 year: 2017 end-page: 582 article-title: Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks publication-title: Radiology – volume: 47 start-page: 1287 year: 2018 end-page: 1297 article-title: Pulmonary ventilation imaging in asthma and cystic fibrosis using oxygen‐enhanced 3D radial ultrashort echo time MRI publication-title: J Magn Reson Imaging – volume: 6 start-page: 1 year: 2018 end-page: 6 article-title: Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks publication-title: Comput Methods Biomech Biomed Eng Imaging Vis – volume: 41 start-page: 1465 year: 2015 end-page: 1474 article-title: Ultra‐short echo‐time pulmonary MRI: Evaluation and reproducibility in COPD subjects with and without bronchiectasis publication-title: J Magn Reson Imaging – volume: 2 start-page: 1236 year: 1996 end-page: 1239 article-title: Noninvasive assessment of regional ventilation in the human lung using oxygen‐enhanced magnetic resonance imaging publication-title: Nat Med – volume: 125 start-page: 2334 year: 2012 end-page: 2342 article-title: Magnetic resonance imaging with 3‐dimensional analysis of left ventricular remodeling in isolated mitral regurgitation: Implications beyond dimensions publication-title: Circulation – volume: 35 start-page: 1160 year: 2016 end-page: 1169 article-title: Pulmonary nodule detection in CT images: False positive reduction using multi‐view convolutional networks publication-title: IEEE Trans Med Imaging – volume: 286 start-page: 676 year: 2018 end-page: 684 article-title: Deep learning MR imaging‐based attenuation correction for PET/MR imaging publication-title: Radiology – volume: 78 start-page: 315 year: 2016 end-page: 320 article-title: Atlas‐based estimation of lung and lobar anatomy in proton MRI publication-title: Magn Reson Med – volume: 21 start-page: 365 year: 2005 end-page: 369 article-title: Combined helium‐3/proton magnetic resonance imaging measurement of ventilated lung volumes in smokers compared to never‐smokers publication-title: J Magn Reson Imaging – volume: 35 start-page: 1299 year: 2017 end-page: 1312 – volume: 41 start-page: 1708 year: 2015 end-page: 1714 article-title: Oxygen enhanced lung MRI by simultaneous measurement of T1 and T2* during free breathing using ultrashort TE publication-title: J Magn Reson Imaging – ident: e_1_2_6_15_1 doi: 10.1007/s00330-016-4218-5 – ident: e_1_2_6_12_1 doi: 10.1148/radiol.2017170591 – ident: e_1_2_6_31_1 doi: 10.1002/nbm.3158 – ident: e_1_2_6_35_1 doi: 10.1109/TPAMI.2016.2644615 – start-page: 1 year: 2016 ident: e_1_2_6_8_1 article-title: Regional heterogeneity of chronic obstructive pulmonary disease phenotypes: Pulmonary 3He magnetic resonance imaging and computed tomography publication-title: COPD – ident: e_1_2_6_42_1 doi: 10.1109/TMI.2016.2535302 – ident: e_1_2_6_45_1 doi: 10.1161/CIRCULATIONAHA.111.073239 – ident: e_1_2_6_24_1 doi: 10.1002/mrm.26841 – volume: 07 start-page: 3431 year: 2015 ident: e_1_2_6_43_1 article-title: Fully convolutional networks for semantic segmentation publication-title: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit – ident: e_1_2_6_30_1 doi: 10.1002/mrm.24570 – ident: e_1_2_6_48_1 doi: 10.1002/mrm.25158 – ident: e_1_2_6_10_1 doi: 10.1378/chest.12-2597 – ident: e_1_2_6_11_1 doi: 10.1002/nbm.3165 – ident: e_1_2_6_29_1 doi: 10.1148/radiol.2018181148 – ident: e_1_2_6_14_1 doi: 10.1513/AnnalsATS.201603-203OC – volume: 16 start-page: 246 issue: 2 year: 2013 ident: e_1_2_6_40_1 article-title: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network publication-title: Med Image Comput Comput Assist Interv – ident: e_1_2_6_21_1 doi: 10.1080/21681163.2015.1124249 – ident: e_1_2_6_17_1 doi: 10.1007/174_2017_49 – ident: e_1_2_6_39_1 – ident: e_1_2_6_38_1 doi: 10.1109/TMI.2016.2528821 – ident: e_1_2_6_2_1 doi: 10.1038/nm1196-1236 – ident: e_1_2_6_13_1 doi: 10.1002/jmri.24680 – ident: e_1_2_6_33_1 doi: 10.1109/TMI.2010.2046908 – ident: e_1_2_6_19_1 doi: 10.1002/mrm.25824 – ident: e_1_2_6_26_1 doi: 10.1148/radiol.2018172322 – ident: e_1_2_6_4_1 doi: 10.1016/j.ejrad.2014.10.021 – ident: e_1_2_6_9_1 doi: 10.1136/thoraxjnl-2016-208948 – ident: e_1_2_6_23_1 doi: 10.1148/radiol.2017162326 – ident: e_1_2_6_3_1 doi: 10.1148/radiol.14132660 – ident: e_1_2_6_7_1 doi: 10.1016/j.acra.2007.10.019 – ident: e_1_2_6_22_1 doi: 10.1109/TMI.2016.2536809 – ident: e_1_2_6_5_1 doi: 10.1002/jmri.25877 – ident: e_1_2_6_25_1 doi: 10.1002/mrm.27229 – ident: e_1_2_6_16_1 – start-page: 172986 year: 2018 ident: e_1_2_6_37_1 article-title: Deep learning approach for evaluating knee MR images: Achieving high diagnostic performance for cartilage lesion detection publication-title: Radiology – ident: e_1_2_6_44_1 doi: 10.1080/00220973.1974.10806305 – ident: e_1_2_6_20_1 doi: 10.1109/TMI.2016.2535865 – ident: e_1_2_6_32_1 doi: 10.1002/mrm.20128 – ident: e_1_2_6_46_1 doi: 10.3389/fcvm.2015.00008 – ident: e_1_2_6_28_1 doi: 10.1164/rccm.201107-1317PP – ident: e_1_2_6_41_1 doi: 10.1109/TMI.2016.2528162 – ident: e_1_2_6_47_1 doi: 10.1002/jmri.24692 – ident: e_1_2_6_34_1 doi: 10.1016/j.acra.2016.04.005 – ident: e_1_2_6_18_1 doi: 10.1007/s11548-014-1090-0 – ident: e_1_2_6_6_1 doi: 10.1002/jmri.20290 – ident: e_1_2_6_27_1 doi: 10.1016/j.neuroimage.2018.03.065 – ident: e_1_2_6_36_1 doi: 10.1148/radiol.2017170700 |
| SSID | ssj0009945 |
| Score | 2.4197798 |
| Snippet | Background
Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development... Ultrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development of rapid... BackgroundUltrashort echo time (UTE) proton MRI has gained popularity for assessing lung structure and function in pulmonary imaging; however, the development... |
| SourceID | proquest pubmed crossref wiley |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1169 |
| SubjectTerms | Adult Artificial neural networks Asthma Asthma - diagnostic imaging Asthma - physiopathology Automation Biomarkers Coders Confidence intervals Cystic fibrosis Cystic Fibrosis - diagnostic imaging Cystic Fibrosis - physiopathology deep learning Female Field strength Humans hyperoxia Image Interpretation, Computer-Assisted - methods Image processing Image segmentation Imaging, Three-Dimensional - methods lung Lung - diagnostic imaging Lung - physiopathology Lungs Machine learning Magnetic resonance imaging Magnetic Resonance Imaging - methods Male Medical imaging Neural networks Neural Networks, Computer Protons Rank tests Regional development Respiratory function Retrospective Studies Statistical analysis Statistical tests Structure-function relationships |
| Title | Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fjmri.26734 https://www.ncbi.nlm.nih.gov/pubmed/30945385 https://www.proquest.com/docview/2291157933 https://www.proquest.com/docview/2203136607 |
| Volume | 50 |
| WOSCitedRecordID | wos000486307100016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVWIB databaseName: Wiley Online Library Free Content customDbUrl: eissn: 1522-2586 dateEnd: 20201212 omitProxy: false ssIdentifier: ssj0009945 issn: 1053-1807 databaseCode: WIN dateStart: 19990101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1522-2586 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0009945 issn: 1053-1807 databaseCode: DRFUL dateStart: 19990101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwED6NgdBexm_IGJURvICUzbEdO5Z4QWwVQ1uFplX0LbJdGw1t3WjWveyfx-ekqSYQEuIpVnKJI99d7ot9_g7grSqcF1bQ3EgsYeZpmRumypw6y7kKaAVJ04dqNKomE_11DT4s98K0_BD9hBt6Rvpeo4Mb2-yuSEN_nM9Pd5hUHMlAC5G88tvBaMW4q1OF4ogfeF5UVPXcpGx3devtaPQbxLyNWFPIGT74v5d9CJsd1CQfW9t4BGt-9hjuH3WL6U_gZs_7S4Jp5535RWGkt0yHlBzeEJymJV3SoZl5lG6wOEZDovWkrewkol5ytsBGDJH4GPJzYdoUpKR1gqn138n4ZJ8gKUQ8cXR88BTGw_2TT5_zrhZD7rjmItdWRGDhrQxiSm1w1FIvnFTKVLQK2jvjIvZjSkcIx5WfFsEpo4OtKJ-W0iv-DNZnFzP_AogIXAfPSsukEYFxXVghvVYxbhbWsSqDd0ud1K4jKsd6GWd1S7HMahzNOo1mBm962cuWnuOPUttL1dadizY1YxqJhjTnGbzuL0fnwhWTOKIXC5RBakspqcrgeWsSfTc8_hjHaFFm8D5p_i_911_iwKbW1r8Iv4SNCM90mzq4DetX84V_Bffc9dVpMx_AHTWpBnB373g4Phwk2_8FU_kGPQ |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED9Bh4AXvj8CA4zgBaRsju3Y8SNiqzZoKzS10t6i2LWnodGNZt3L_nl8jpdqAiEhnmIllzi6O-d-sc-_A3ivCuuEETRvJJYwc7TMG6bKnFrDufLoBdHSIzWZVIeH-lvKzcG9MB0_RD_hhiMjfq9xgOOE9PaaNfT7j-XxFpOKi5uwIYIflQPY2DkYzkZr1l0dqxQHDMHzoqKq5ydl2-u7r0ek32DmddQaw87w_n--8AO4l_Am-dQ5yEO44RaP4PY4rag_hssd584I5p4nHwzCyHEZDzFDvCU4V0tS5mGzcCjdYoWMlgQXivvZSYC-5GSFjRAn8THk56rp8pCi6Qnm1x-R2XSXIDNEODE-2H8Cs-Hu9PNengoy5JZrLnJtREAXzkgv5tR4Sw11wkqlmopWXjvb2AAAmdIBx3Hl5oW3qtHeVJTPS-kUfwqDxenCPQciPNfesdIw2QjPuC6MkE6rEDwLY1mVwYcro9Q2sZVj0YyTuuNZZjVqs47azOBdL3vWcXT8UWrzyrZ1GqdtzZhGtiHNeQZv-8thhOGySdDo6QplkN9SSqoyeNb5RN8ND3_HIWSUGXyMpv9L__WXoNjYevEvwm_gzt50PKpH-5OvL-FuwGu6yyXchMH5cuVewS17cX7cLl8n5_8FaisJAQ |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fb9MwED7Bhqa9MH6OsAFG8AJSmGM7dvw4rasYdNU0rdLeoti10dDoSrPywj-Pz_FSTSAkxFOs5BJHvrvcF_v8HcBbVVgnjKB5I7GEmaNl3jBV5tQazpVHK4iaHqnxuDo_1ycpNwf3wnT8EP2EG3pG_F6jg7v51O-tWEO_fltcfGBScXEX1kWpZfDL9cHpcDJase7qWKU4YAieFxVVPT8p21vdfTsi_QYzb6PWGHaGW__5wg_gfsKbZL8zkIdwx80ewcZxWlF_DD8Hzs0J5p4nGwzCyHEZDzFDvCU4V0tS5mEzcyjdYoWMlgQTivvZSYC-5HKJjRAn8THk-7Lp8pCi6gnm138hk7NDgswQ4cTx6dETmAwPzw4-5qkgQ2655iLXRgR04Yz0YkqNt9RQJ6xUqqlo5bWzjQ0AkCkdcBxXblp4qxrtTUX5tJRO8aewNruauWdAhOfaO1YaJhvhGdeFEdJpFYJnYSyrMnh3o5TaJrZyLJpxWXc8y6zG0azjaGbwppeddxwdf5TavdFtnfy0rRnTyDakOc_gdX85eBgum4QRvVqiDPJbSklVBtudTfTd8PB3HEJGmcH7qPq_9F9_CgMbW8__RfgVbJwMhvXoaPx5BzYDXNNdKuEurF0vlu4F3LM_ri_axctk-78A6SQIfA |
| 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+convolutional+neural+networks+with+multiplane+consensus+labeling+for+lung+function+quantification+using+UTE+proton+MRI&rft.jtitle=Journal+of+magnetic+resonance+imaging&rft.au=Zha%2C+Wei&rft.au=Fain%2C+Sean+B&rft.au=Schiebler%2C+Mark+L&rft.au=Evans%2C+Michael+D&rft.date=2019-10-01&rft.eissn=1522-2586&rft.volume=50&rft.issue=4&rft.spage=1169&rft_id=info:doi/10.1002%2Fjmri.26734&rft_id=info%3Apmid%2F30945385&rft.externalDocID=30945385 |
| 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 |