Loading…
Deep‐Learning Detection of Cancer Metastases to the Brain on MRI
Background Approximately one‐fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at...
Saved in:
| Published in: | Journal of magnetic resonance imaging 2020-10, Vol.52 (4), p.1227-1236 |
|---|---|
| Main Authors: | , , , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743 |
| container_end_page | 1236 |
| container_issue | 4 |
| container_start_page | 1227 |
| container_title | Journal of magnetic resonance imaging |
| container_volume | 52 |
| creator | Zhang, Min Young, Geoffrey S. Chen, Huai Li, Jing Qin, Lei McFaline‐Figueroa, J. Ricardo Reardon, David A. Cao, Xinhua Wu, Xian Xu, Xiaoyin |
| description | Background
Approximately one‐fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Purpose
To develop a deep‐learning‐based approach for finding brain metastasis on MRI.
Study Type
Retrospective.
Sequence
Axial postcontrast 3D T1‐weighted imaging.
Field Strength
1.5T and 3T.
Population
A total of 361 scans of 121 patients were used to train and test the Faster region‐based convolutional neural network (Faster R‐CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R‐CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing.
Assessment
Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2‐step pipeline consisting of a Faster R‐CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false‐positive foci detected.
Statistical Tests
The performance of the algorithm was evaluated by using sensitivity, false‐positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per‐metastases and per‐slice.
Results
Testing on held‐out brain MRI data demonstrated 96% sensitivity and 20 false‐positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false‐positive metastases per slice. The area under the ROC curve was 0.79.
Conclusion
Our results showed that deep‐learning‐based computer‐aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity.
Level of Evidence
3
Technical Efficacy Stage
2 J. Magn. Reson. Imaging 2020;52:1227–1236. |
| doi_str_mv | 10.1002/jmri.27129 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7487020</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2442033368</sourcerecordid><originalsourceid>FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743</originalsourceid><addsrcrecordid>eNp9kd1KHDEUx4NU6ldv-gBloDcijE0ySc7MTUHX-sWKIO11yGTOapbZZE1mW7zzEXzGPolZV8X2QkhIID9-Oef8CfnM6D6jlH-bzqLb58B4s0Y2meS85LJWH_KdyqpkNYUNspXSlFLaNEJ-JBsVZwqU5Jvk8Ahx_vf-YYwmeueviyMc0A4u-CJMipHxFmNxgYNJeWEqhlAMN1gcRuMy4YuLq7Mdsj4xfcJPz-c2-XX84-fotBxfnpyNDsallUw0pVJd22GDAKydMC4YAJdgOwrQCjDG1NRKg9LWklpaiY4JrlqlTAvMWhDVNvm-8s4X7Qw7i36Iptfz6GYm3ulgnP73xbsbfR1-axA1UE6zYPdZEMPtAtOgZy5Z7HvjMSyS5hVAlbdY_vX1P3QaFtHn9jQXIruqStWZ2ltRNoaUIk5ei2FUL6PRy2j0UzQZ_vK2_Ff0JYsMsBXwx_V4945Kn-epr6SPmB2Y6g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2442033368</pqid></control><display><type>article</type><title>Deep‐Learning Detection of Cancer Metastases to the Brain on MRI</title><source>Wiley</source><creator>Zhang, Min ; Young, Geoffrey S. ; Chen, Huai ; Li, Jing ; Qin, Lei ; McFaline‐Figueroa, J. Ricardo ; Reardon, David A. ; Cao, Xinhua ; Wu, Xian ; Xu, Xiaoyin</creator><creatorcontrib>Zhang, Min ; Young, Geoffrey S. ; Chen, Huai ; Li, Jing ; Qin, Lei ; McFaline‐Figueroa, J. Ricardo ; Reardon, David A. ; Cao, Xinhua ; Wu, Xian ; Xu, Xiaoyin</creatorcontrib><description>Background
Approximately one‐fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Purpose
To develop a deep‐learning‐based approach for finding brain metastasis on MRI.
Study Type
Retrospective.
Sequence
Axial postcontrast 3D T1‐weighted imaging.
Field Strength
1.5T and 3T.
Population
A total of 361 scans of 121 patients were used to train and test the Faster region‐based convolutional neural network (Faster R‐CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R‐CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing.
Assessment
Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2‐step pipeline consisting of a Faster R‐CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false‐positive foci detected.
Statistical Tests
The performance of the algorithm was evaluated by using sensitivity, false‐positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per‐metastases and per‐slice.
Results
Testing on held‐out brain MRI data demonstrated 96% sensitivity and 20 false‐positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false‐positive metastases per slice. The area under the ROC curve was 0.79.
Conclusion
Our results showed that deep‐learning‐based computer‐aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity.
Level of Evidence
3
Technical Efficacy Stage
2 J. Magn. Reson. Imaging 2020;52:1227–1236.</description><identifier>ISSN: 1053-1807</identifier><identifier>EISSN: 1522-2586</identifier><identifier>DOI: 10.1002/jmri.27129</identifier><identifier>PMID: 32167652</identifier><language>eng</language><publisher>Hoboken, USA: John Wiley & Sons, Inc</publisher><subject>Algorithms ; Annotations ; Artificial neural networks ; Brain ; Brain - diagnostic imaging ; Brain cancer ; brain metastases ; Brain slice preparation ; Cancer ; Deep Learning ; Faster R‐CNN ; Field strength ; Ground truth ; Humans ; Lesions ; Magnetic Resonance Imaging ; Medical imaging ; Metastases ; Metastasis ; Neoplasms ; Neural networks ; Neuroimaging ; Radiation therapy ; Retrospective Studies ; RUSBoost ; Sensitivity analysis ; Sensitivity and Specificity ; Statistical analysis ; Statistical tests ; Training</subject><ispartof>Journal of magnetic resonance imaging, 2020-10, Vol.52 (4), p.1227-1236</ispartof><rights>2020 International Society for Magnetic Resonance in Medicine</rights><rights>2020 International Society for Magnetic Resonance in Medicine.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743</citedby><cites>FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743</cites><orcidid>0000-0003-0813-7979</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.27129$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fjmri.27129$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>230,315,786,790,891,27957,27958,50923,51032</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/32167652$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Min</creatorcontrib><creatorcontrib>Young, Geoffrey S.</creatorcontrib><creatorcontrib>Chen, Huai</creatorcontrib><creatorcontrib>Li, Jing</creatorcontrib><creatorcontrib>Qin, Lei</creatorcontrib><creatorcontrib>McFaline‐Figueroa, J. Ricardo</creatorcontrib><creatorcontrib>Reardon, David A.</creatorcontrib><creatorcontrib>Cao, Xinhua</creatorcontrib><creatorcontrib>Wu, Xian</creatorcontrib><creatorcontrib>Xu, Xiaoyin</creatorcontrib><title>Deep‐Learning Detection of Cancer Metastases to the Brain on MRI</title><title>Journal of magnetic resonance imaging</title><addtitle>J Magn Reson Imaging</addtitle><description>Background
Approximately one‐fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Purpose
To develop a deep‐learning‐based approach for finding brain metastasis on MRI.
Study Type
Retrospective.
Sequence
Axial postcontrast 3D T1‐weighted imaging.
Field Strength
1.5T and 3T.
Population
A total of 361 scans of 121 patients were used to train and test the Faster region‐based convolutional neural network (Faster R‐CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R‐CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing.
Assessment
Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2‐step pipeline consisting of a Faster R‐CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false‐positive foci detected.
Statistical Tests
The performance of the algorithm was evaluated by using sensitivity, false‐positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per‐metastases and per‐slice.
Results
Testing on held‐out brain MRI data demonstrated 96% sensitivity and 20 false‐positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false‐positive metastases per slice. The area under the ROC curve was 0.79.
Conclusion
Our results showed that deep‐learning‐based computer‐aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity.
Level of Evidence
3
Technical Efficacy Stage
2 J. Magn. Reson. Imaging 2020;52:1227–1236.</description><subject>Algorithms</subject><subject>Annotations</subject><subject>Artificial neural networks</subject><subject>Brain</subject><subject>Brain - diagnostic imaging</subject><subject>Brain cancer</subject><subject>brain metastases</subject><subject>Brain slice preparation</subject><subject>Cancer</subject><subject>Deep Learning</subject><subject>Faster R‐CNN</subject><subject>Field strength</subject><subject>Ground truth</subject><subject>Humans</subject><subject>Lesions</subject><subject>Magnetic Resonance Imaging</subject><subject>Medical imaging</subject><subject>Metastases</subject><subject>Metastasis</subject><subject>Neoplasms</subject><subject>Neural networks</subject><subject>Neuroimaging</subject><subject>Radiation therapy</subject><subject>Retrospective Studies</subject><subject>RUSBoost</subject><subject>Sensitivity analysis</subject><subject>Sensitivity and Specificity</subject><subject>Statistical analysis</subject><subject>Statistical tests</subject><subject>Training</subject><issn>1053-1807</issn><issn>1522-2586</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kd1KHDEUx4NU6ldv-gBloDcijE0ySc7MTUHX-sWKIO11yGTOapbZZE1mW7zzEXzGPolZV8X2QkhIID9-Oef8CfnM6D6jlH-bzqLb58B4s0Y2meS85LJWH_KdyqpkNYUNspXSlFLaNEJ-JBsVZwqU5Jvk8Ahx_vf-YYwmeueviyMc0A4u-CJMipHxFmNxgYNJeWEqhlAMN1gcRuMy4YuLq7Mdsj4xfcJPz-c2-XX84-fotBxfnpyNDsallUw0pVJd22GDAKydMC4YAJdgOwrQCjDG1NRKg9LWklpaiY4JrlqlTAvMWhDVNvm-8s4X7Qw7i36Iptfz6GYm3ulgnP73xbsbfR1-axA1UE6zYPdZEMPtAtOgZy5Z7HvjMSyS5hVAlbdY_vX1P3QaFtHn9jQXIruqStWZ2ltRNoaUIk5ei2FUL6PRy2j0UzQZ_vK2_Ff0JYsMsBXwx_V4945Kn-epr6SPmB2Y6g</recordid><startdate>202010</startdate><enddate>202010</enddate><creator>Zhang, Min</creator><creator>Young, Geoffrey S.</creator><creator>Chen, Huai</creator><creator>Li, Jing</creator><creator>Qin, Lei</creator><creator>McFaline‐Figueroa, J. Ricardo</creator><creator>Reardon, David A.</creator><creator>Cao, Xinhua</creator><creator>Wu, Xian</creator><creator>Xu, Xiaoyin</creator><general>John Wiley & Sons, Inc</general><general>Wiley Subscription Services, Inc</general><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><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-0813-7979</orcidid></search><sort><creationdate>202010</creationdate><title>Deep‐Learning Detection of Cancer Metastases to the Brain on MRI</title><author>Zhang, Min ; Young, Geoffrey S. ; Chen, Huai ; Li, Jing ; Qin, Lei ; McFaline‐Figueroa, J. Ricardo ; Reardon, David A. ; Cao, Xinhua ; Wu, Xian ; Xu, Xiaoyin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Annotations</topic><topic>Artificial neural networks</topic><topic>Brain</topic><topic>Brain - diagnostic imaging</topic><topic>Brain cancer</topic><topic>brain metastases</topic><topic>Brain slice preparation</topic><topic>Cancer</topic><topic>Deep Learning</topic><topic>Faster R‐CNN</topic><topic>Field strength</topic><topic>Ground truth</topic><topic>Humans</topic><topic>Lesions</topic><topic>Magnetic Resonance Imaging</topic><topic>Medical imaging</topic><topic>Metastases</topic><topic>Metastasis</topic><topic>Neoplasms</topic><topic>Neural networks</topic><topic>Neuroimaging</topic><topic>Radiation therapy</topic><topic>Retrospective Studies</topic><topic>RUSBoost</topic><topic>Sensitivity analysis</topic><topic>Sensitivity and Specificity</topic><topic>Statistical analysis</topic><topic>Statistical tests</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Min</creatorcontrib><creatorcontrib>Young, Geoffrey S.</creatorcontrib><creatorcontrib>Chen, Huai</creatorcontrib><creatorcontrib>Li, Jing</creatorcontrib><creatorcontrib>Qin, Lei</creatorcontrib><creatorcontrib>McFaline‐Figueroa, J. Ricardo</creatorcontrib><creatorcontrib>Reardon, David A.</creatorcontrib><creatorcontrib>Cao, Xinhua</creatorcontrib><creatorcontrib>Wu, Xian</creatorcontrib><creatorcontrib>Xu, Xiaoyin</creatorcontrib><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><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of magnetic resonance imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Min</au><au>Young, Geoffrey S.</au><au>Chen, Huai</au><au>Li, Jing</au><au>Qin, Lei</au><au>McFaline‐Figueroa, J. Ricardo</au><au>Reardon, David A.</au><au>Cao, Xinhua</au><au>Wu, Xian</au><au>Xu, Xiaoyin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep‐Learning Detection of Cancer Metastases to the Brain on MRI</atitle><jtitle>Journal of magnetic resonance imaging</jtitle><addtitle>J Magn Reson Imaging</addtitle><date>2020-10</date><risdate>2020</risdate><volume>52</volume><issue>4</issue><spage>1227</spage><epage>1236</epage><pages>1227-1236</pages><issn>1053-1807</issn><eissn>1522-2586</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><notes>Co-first authors.</notes><abstract>Background
Approximately one‐fourth of all cancer metastases are found in the brain. MRI is the primary technique for detection of brain metastasis, planning of radiotherapy, and the monitoring of treatment response. Progress in tumor treatment now requires detection of new or growing metastases at the small subcentimeter size, when these therapies are most effective.
Purpose
To develop a deep‐learning‐based approach for finding brain metastasis on MRI.
Study Type
Retrospective.
Sequence
Axial postcontrast 3D T1‐weighted imaging.
Field Strength
1.5T and 3T.
Population
A total of 361 scans of 121 patients were used to train and test the Faster region‐based convolutional neural network (Faster R‐CNN): 1565 lesions in 270 scans of 73 patients for training; 488 lesions in 91 scans of 48 patients for testing. From the 48 outputs of Faster R‐CNN, 212 lesions in 46 scans of 18 patients were used for training the RUSBoost algorithm (MatLab) and 276 lesions in 45 scans of 30 patients for testing.
Assessment
Two radiologists diagnosed and supervised annotation of metastases on brain MRI as ground truth. This data were used to produce a 2‐step pipeline consisting of a Faster R‐CNN for detecting abnormal hyperintensity that may represent brain metastasis and a RUSBoost classifier to reduce the number of false‐positive foci detected.
Statistical Tests
The performance of the algorithm was evaluated by using sensitivity, false‐positive rate, and receiver's operating characteristic (ROC) curves. The detection performance was assessed both per‐metastases and per‐slice.
Results
Testing on held‐out brain MRI data demonstrated 96% sensitivity and 20 false‐positive metastases per scan. The results showed an 87.1% sensitivity and 0.24 false‐positive metastases per slice. The area under the ROC curve was 0.79.
Conclusion
Our results showed that deep‐learning‐based computer‐aided detection (CAD) had the potential of detecting brain metastases with high sensitivity and reasonable specificity.
Level of Evidence
3
Technical Efficacy Stage
2 J. Magn. Reson. Imaging 2020;52:1227–1236.</abstract><cop>Hoboken, USA</cop><pub>John Wiley & Sons, Inc</pub><pmid>32167652</pmid><doi>10.1002/jmri.27129</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-0813-7979</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1053-1807 |
| ispartof | Journal of magnetic resonance imaging, 2020-10, Vol.52 (4), p.1227-1236 |
| issn | 1053-1807 1522-2586 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_7487020 |
| source | Wiley |
| subjects | Algorithms Annotations Artificial neural networks Brain Brain - diagnostic imaging Brain cancer brain metastases Brain slice preparation Cancer Deep Learning Faster R‐CNN Field strength Ground truth Humans Lesions Magnetic Resonance Imaging Medical imaging Metastases Metastasis Neoplasms Neural networks Neuroimaging Radiation therapy Retrospective Studies RUSBoost Sensitivity analysis Sensitivity and Specificity Statistical analysis Statistical tests Training |
| title | Deep‐Learning Detection of Cancer Metastases to the Brain on MRI |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T10%3A27%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%E2%80%90Learning%20Detection%20of%20Cancer%20Metastases%20to%20the%20Brain%20on%20MRI&rft.jtitle=Journal%20of%20magnetic%20resonance%20imaging&rft.au=Zhang,%20Min&rft.date=2020-10&rft.volume=52&rft.issue=4&rft.spage=1227&rft.epage=1236&rft.pages=1227-1236&rft.issn=1053-1807&rft.eissn=1522-2586&rft_id=info:doi/10.1002/jmri.27129&rft_dat=%3Cproquest_pubme%3E2442033368%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c5149-66dbde9e771bf124177257cd077b47aaa80c5ae5c850c034d1426b66ab71cc743%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2442033368&rft_id=info:pmid/32167652&rfr_iscdi=true |