Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint
Background Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could signifi...
Gespeichert in:
| Veröffentlicht in: | Journal of magnetic resonance imaging 2023-08, Vol.58 (2), p.559-568 |
|---|---|
| Hauptverfasser: | , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 568 |
|---|---|
| container_issue | 2 |
| container_start_page | 559 |
| container_title | Journal of magnetic resonance imaging |
| container_volume | 58 |
| creator | Nykänen, Olli Nevalainen, Mika Casula, Victor Isosalo, Antti Inkinen, Satu I. Nikki, Marko Lattanzi, Riccardo Cloos, Martijn A. Nissi, Mikko J. Nieminen, Miika T. |
| description | Background
Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.
Purpose
To improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations.
Study Type
Retrospective.
Population
Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).
Field Strength and Sequence
A 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS).
Assessment
Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.
Statistical Tests
Friedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P |
| doi_str_mv | 10.1002/jmri.28573 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2758110497</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2834859595</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3933-b1e5e47fa17087cfdd38ccdb1820375c663ccc6c904c2fdcde8f506235b2de6c3</originalsourceid><addsrcrecordid>eNp90EtOwzAQBmALgXgUNhwAWWKDkFL8iBNnCYVCSytQKWvLdSaQqnGKnQp1xxE4IyfBpcCCBZrFzOLTr9GP0CElbUoIO5tWrmwzKVK-gXapYCxiQiab4SaCR1SSdAfteT8lhGRZLLbRDk9EwgQhu2h8CTD_eHsfgHa2tE_hvNAectypbeO0b_DD0jbP4EuPu66u8HDUxffa6QoacHio5x6XFgeBby0A7telbfbRVqFnHg6-dws9dq_GnZtocHfd65wPIsMzzqMJBQFxWmiaEpmaIs-5NCafUMkIT4VJEm6MSUxGYsOK3OQgC0ESxsWE5ZAY3kIn69y5q18W4BtVld7AbKYt1AuvWCokpSTO0kCP_9BpvXA2fKeY5LEUWZigTtfKuNp7B4Wau7LSbqkoUauu1apr9dV1wEffkYtJBfkv_Sk3ALoGr-UMlv9Eqf5w1FuHfgKRy4pl</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2834859595</pqid></control><display><type>article</type><title>Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint</title><source>MEDLINE</source><source>Wiley Journals</source><creator>Nykänen, Olli ; Nevalainen, Mika ; Casula, Victor ; Isosalo, Antti ; Inkinen, Satu I. ; Nikki, Marko ; Lattanzi, Riccardo ; Cloos, Martijn A. ; Nissi, Mikko J. ; Nieminen, Miika T.</creator><creatorcontrib>Nykänen, Olli ; Nevalainen, Mika ; Casula, Victor ; Isosalo, Antti ; Inkinen, Satu I. ; Nikki, Marko ; Lattanzi, Riccardo ; Cloos, Martijn A. ; Nissi, Mikko J. ; Nieminen, Miika T.</creatorcontrib><description>Background
Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.
Purpose
To improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations.
Study Type
Retrospective.
Population
Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).
Field Strength and Sequence
A 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS).
Assessment
Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.
Statistical Tests
Friedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.
Results
The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5‐point scale). Qualitatively, the best synthetic images were produced with combination of L1‐ and perceptual loss functions and perceptual loss alone, while L1‐loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1‐loss.
Data Conclusion
Synthesizing high‐quality contrast‐weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.
Evidence Level
4.
Technical Efficacy
Stage 1.</description><identifier>ISSN: 1053-1807</identifier><identifier>ISSN: 1522-2586</identifier><identifier>EISSN: 1522-2586</identifier><identifier>DOI: 10.1002/jmri.28573</identifier><identifier>PMID: 36562500</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>Correlation coefficient ; Correlation coefficients ; Deep Learning ; Field strength ; Fingerprinting ; Humans ; Image contrast ; Image Processing, Computer-Assisted - methods ; Image quality ; Imaging, Three-Dimensional - methods ; Joints (anatomy) ; Knee ; Knee Joint ; Knee Joint - diagnostic imaging ; Magnetic Resonance Fingerprinting ; Magnetic resonance imaging ; Magnetic Resonance Imaging - methods ; Magnetic Resonance Spectroscopy ; Medical imaging ; Population studies ; Proton density (concentration) ; Rank tests ; Retrospective Studies ; Statistical analysis ; Statistical tests ; Synthetic data ; Synthetic MRI ; Training</subject><ispartof>Journal of magnetic resonance imaging, 2023-08, Vol.58 (2), p.559-568</ispartof><rights>2022 The Authors. published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.</rights><rights>2022 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.</rights><rights>2022. This article is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3933-b1e5e47fa17087cfdd38ccdb1820375c663ccc6c904c2fdcde8f506235b2de6c3</citedby><cites>FETCH-LOGICAL-c3933-b1e5e47fa17087cfdd38ccdb1820375c663ccc6c904c2fdcde8f506235b2de6c3</cites><orcidid>0000-0002-2300-2848 ; 0000-0002-0636-234X ; 0000-0001-7329-3463 ; 0000-0002-5678-0689 ; 0000-0002-9774-8925</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1002%2Fjmri.28573$$EPDF$$P50$$Gwiley$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fjmri.28573$$EHTML$$P50$$Gwiley$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,1417,27924,27925,45574,45575</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36562500$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Nykänen, Olli</creatorcontrib><creatorcontrib>Nevalainen, Mika</creatorcontrib><creatorcontrib>Casula, Victor</creatorcontrib><creatorcontrib>Isosalo, Antti</creatorcontrib><creatorcontrib>Inkinen, Satu I.</creatorcontrib><creatorcontrib>Nikki, Marko</creatorcontrib><creatorcontrib>Lattanzi, Riccardo</creatorcontrib><creatorcontrib>Cloos, Martijn A.</creatorcontrib><creatorcontrib>Nissi, Mikko J.</creatorcontrib><creatorcontrib>Nieminen, Miika T.</creatorcontrib><title>Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint</title><title>Journal of magnetic resonance imaging</title><addtitle>J Magn Reson Imaging</addtitle><description>Background
Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.
Purpose
To improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations.
Study Type
Retrospective.
Population
Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).
Field Strength and Sequence
A 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS).
Assessment
Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.
Statistical Tests
Friedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.
Results
The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5‐point scale). Qualitatively, the best synthetic images were produced with combination of L1‐ and perceptual loss functions and perceptual loss alone, while L1‐loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1‐loss.
Data Conclusion
Synthesizing high‐quality contrast‐weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.
Evidence Level
4.
Technical Efficacy
Stage 1.</description><subject>Correlation coefficient</subject><subject>Correlation coefficients</subject><subject>Deep Learning</subject><subject>Field strength</subject><subject>Fingerprinting</subject><subject>Humans</subject><subject>Image contrast</subject><subject>Image Processing, Computer-Assisted - methods</subject><subject>Image quality</subject><subject>Imaging, Three-Dimensional - methods</subject><subject>Joints (anatomy)</subject><subject>Knee</subject><subject>Knee Joint</subject><subject>Knee Joint - diagnostic imaging</subject><subject>Magnetic Resonance Fingerprinting</subject><subject>Magnetic resonance imaging</subject><subject>Magnetic Resonance Imaging - methods</subject><subject>Magnetic Resonance Spectroscopy</subject><subject>Medical imaging</subject><subject>Population studies</subject><subject>Proton density (concentration)</subject><subject>Rank tests</subject><subject>Retrospective Studies</subject><subject>Statistical analysis</subject><subject>Statistical tests</subject><subject>Synthetic data</subject><subject>Synthetic MRI</subject><subject>Training</subject><issn>1053-1807</issn><issn>1522-2586</issn><issn>1522-2586</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>24P</sourceid><sourceid>WIN</sourceid><sourceid>EIF</sourceid><recordid>eNp90EtOwzAQBmALgXgUNhwAWWKDkFL8iBNnCYVCSytQKWvLdSaQqnGKnQp1xxE4IyfBpcCCBZrFzOLTr9GP0CElbUoIO5tWrmwzKVK-gXapYCxiQiab4SaCR1SSdAfteT8lhGRZLLbRDk9EwgQhu2h8CTD_eHsfgHa2tE_hvNAectypbeO0b_DD0jbP4EuPu66u8HDUxffa6QoacHio5x6XFgeBby0A7telbfbRVqFnHg6-dws9dq_GnZtocHfd65wPIsMzzqMJBQFxWmiaEpmaIs-5NCafUMkIT4VJEm6MSUxGYsOK3OQgC0ESxsWE5ZAY3kIn69y5q18W4BtVld7AbKYt1AuvWCokpSTO0kCP_9BpvXA2fKeY5LEUWZigTtfKuNp7B4Wau7LSbqkoUauu1apr9dV1wEffkYtJBfkv_Sk3ALoGr-UMlv9Eqf5w1FuHfgKRy4pl</recordid><startdate>202308</startdate><enddate>202308</enddate><creator>Nykänen, Olli</creator><creator>Nevalainen, Mika</creator><creator>Casula, Victor</creator><creator>Isosalo, Antti</creator><creator>Inkinen, Satu I.</creator><creator>Nikki, Marko</creator><creator>Lattanzi, Riccardo</creator><creator>Cloos, Martijn A.</creator><creator>Nissi, Mikko J.</creator><creator>Nieminen, Miika T.</creator><general>John Wiley & Sons, Inc</general><general>Wiley Subscription Services, Inc</general><scope>24P</scope><scope>WIN</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>7TK</scope><scope>8FD</scope><scope>FR3</scope><scope>K9.</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2300-2848</orcidid><orcidid>https://orcid.org/0000-0002-0636-234X</orcidid><orcidid>https://orcid.org/0000-0001-7329-3463</orcidid><orcidid>https://orcid.org/0000-0002-5678-0689</orcidid><orcidid>https://orcid.org/0000-0002-9774-8925</orcidid></search><sort><creationdate>202308</creationdate><title>Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint</title><author>Nykänen, Olli ; Nevalainen, Mika ; Casula, Victor ; Isosalo, Antti ; Inkinen, Satu I. ; Nikki, Marko ; Lattanzi, Riccardo ; Cloos, Martijn A. ; Nissi, Mikko J. ; Nieminen, Miika T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3933-b1e5e47fa17087cfdd38ccdb1820375c663ccc6c904c2fdcde8f506235b2de6c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Correlation coefficient</topic><topic>Correlation coefficients</topic><topic>Deep Learning</topic><topic>Field strength</topic><topic>Fingerprinting</topic><topic>Humans</topic><topic>Image contrast</topic><topic>Image Processing, Computer-Assisted - methods</topic><topic>Image quality</topic><topic>Imaging, Three-Dimensional - methods</topic><topic>Joints (anatomy)</topic><topic>Knee</topic><topic>Knee Joint</topic><topic>Knee Joint - diagnostic imaging</topic><topic>Magnetic Resonance Fingerprinting</topic><topic>Magnetic resonance imaging</topic><topic>Magnetic Resonance Imaging - methods</topic><topic>Magnetic Resonance Spectroscopy</topic><topic>Medical imaging</topic><topic>Population studies</topic><topic>Proton density (concentration)</topic><topic>Rank tests</topic><topic>Retrospective Studies</topic><topic>Statistical analysis</topic><topic>Statistical tests</topic><topic>Synthetic data</topic><topic>Synthetic MRI</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nykänen, Olli</creatorcontrib><creatorcontrib>Nevalainen, Mika</creatorcontrib><creatorcontrib>Casula, Victor</creatorcontrib><creatorcontrib>Isosalo, Antti</creatorcontrib><creatorcontrib>Inkinen, Satu I.</creatorcontrib><creatorcontrib>Nikki, Marko</creatorcontrib><creatorcontrib>Lattanzi, Riccardo</creatorcontrib><creatorcontrib>Cloos, Martijn A.</creatorcontrib><creatorcontrib>Nissi, Mikko J.</creatorcontrib><creatorcontrib>Nieminen, Miika T.</creatorcontrib><collection>Wiley Online Library Open Access</collection><collection>Wiley Free Content</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of magnetic resonance imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nykänen, Olli</au><au>Nevalainen, Mika</au><au>Casula, Victor</au><au>Isosalo, Antti</au><au>Inkinen, Satu I.</au><au>Nikki, Marko</au><au>Lattanzi, Riccardo</au><au>Cloos, Martijn A.</au><au>Nissi, Mikko J.</au><au>Nieminen, Miika T.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint</atitle><jtitle>Journal of magnetic resonance imaging</jtitle><addtitle>J Magn Reson Imaging</addtitle><date>2023-08</date><risdate>2023</risdate><volume>58</volume><issue>2</issue><spage>559</spage><epage>568</epage><pages>559-568</pages><issn>1053-1807</issn><issn>1522-2586</issn><eissn>1522-2586</eissn><abstract>Background
Magnetic resonance fingerprinting (MRF) is a method to speed up acquisition of quantitative MRI data. However, MRF does not usually produce contrast‐weighted images that are required by radiologists, limiting reachable total scan time improvement. Contrast synthesis from MRF could significantly decrease the imaging time.
Purpose
To improve clinical utility of MRF by synthesizing contrast‐weighted MR images from the quantitative data provided by MRF, using U‐nets that were trained for the synthesis task utilizing L1‐ and perceptual loss functions, and their combinations.
Study Type
Retrospective.
Population
Knee joint MRI data from 184 subjects from Northern Finland 1986 Birth Cohort (ages 33–35, gender distribution not available).
Field Strength and Sequence
A 3 T, multislice‐MRF, proton density (PD)‐weighted 3D‐SPACE (sampling perfection with application optimized contrasts using different flip angle evolution), fat‐saturated T2‐weighted 3D‐space, water‐excited double echo steady state (DESS).
Assessment
Data were divided into training, validation, test, and radiologist's assessment sets in the following way: 136 subjects to training, 3 for validation, 3 for testing, and 42 for radiologist's assessment. The synthetic and target images were evaluated using 5‐point Likert scale by two musculoskeletal radiologists blinded and with quantitative error metrics.
Statistical Tests
Friedman's test accompanied with post hoc Wilcoxon signed‐rank test and intraclass correlation coefficient. The statistical cutoff P <0.05 adjusted by Bonferroni correction as necessary was utilized.
Results
The networks trained in the study could synthesize conventional images with high image quality (Likert scores 3–4 on a 5‐point scale). Qualitatively, the best synthetic images were produced with combination of L1‐ and perceptual loss functions and perceptual loss alone, while L1‐loss alone led to significantly poorer image quality (Likert scores below 3). The interreader and intrareader agreement were high (0.80 and 0.92, respectively) and significant. However, quantitative image quality metrics indicated best performance for the pure L1‐loss.
Data Conclusion
Synthesizing high‐quality contrast‐weighted images from MRF data using deep learning is feasible. However, more studies are needed to validate the diagnostic accuracy of these synthetic images.
Evidence Level
4.
Technical Efficacy
Stage 1.</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><pmid>36562500</pmid><doi>10.1002/jmri.28573</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0002-2300-2848</orcidid><orcidid>https://orcid.org/0000-0002-0636-234X</orcidid><orcidid>https://orcid.org/0000-0001-7329-3463</orcidid><orcidid>https://orcid.org/0000-0002-5678-0689</orcidid><orcidid>https://orcid.org/0000-0002-9774-8925</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1053-1807 |
| ispartof | Journal of magnetic resonance imaging, 2023-08, Vol.58 (2), p.559-568 |
| issn | 1053-1807 1522-2586 1522-2586 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2758110497 |
| source | MEDLINE; Wiley Journals |
| subjects | Correlation coefficient Correlation coefficients Deep Learning Field strength Fingerprinting Humans Image contrast Image Processing, Computer-Assisted - methods Image quality Imaging, Three-Dimensional - methods Joints (anatomy) Knee Knee Joint Knee Joint - diagnostic imaging Magnetic Resonance Fingerprinting Magnetic resonance imaging Magnetic Resonance Imaging - methods Magnetic Resonance Spectroscopy Medical imaging Population studies Proton density (concentration) Rank tests Retrospective Studies Statistical analysis Statistical tests Synthetic data Synthetic MRI Training |
| title | Deep‐Learning‐Based Contrast Synthesis From MRF Parameter Maps in the Knee Joint |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T13%3A27%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%E2%80%90Learning%E2%80%90Based%20Contrast%20Synthesis%20From%20MRF%20Parameter%20Maps%20in%20the%20Knee%20Joint&rft.jtitle=Journal%20of%20magnetic%20resonance%20imaging&rft.au=Nyk%C3%A4nen,%20Olli&rft.date=2023-08&rft.volume=58&rft.issue=2&rft.spage=559&rft.epage=568&rft.pages=559-568&rft.issn=1053-1807&rft.eissn=1522-2586&rft_id=info:doi/10.1002/jmri.28573&rft_dat=%3Cproquest_cross%3E2834859595%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2834859595&rft_id=info:pmid/36562500&rfr_iscdi=true |