Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding
Purpose This study aims to propose a novel algorithm for slab boundary artifact correction in both single‐band multislab imaging and simultaneous multislab (SMSlab) imaging. Theory and Methods In image domain, the formation of slab boundary artifacts can be regarded as modulating the artifact‐free i...
Gespeichert in:
| Veröffentlicht in: | Magnetic resonance in medicine 2022-03, Vol.87 (3), p.1546-1560 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1560 |
|---|---|
| container_issue | 3 |
| container_start_page | 1546 |
| container_title | Magnetic resonance in medicine |
| container_volume | 87 |
| creator | Zhang, Jieying Liu, Simin Dai, Erpeng Ye, Xinyu Shi, Diwei Wu, Yuhsuan Lu, Jie Guo, Hua |
| description | Purpose
This study aims to propose a novel algorithm for slab boundary artifact correction in both single‐band multislab imaging and simultaneous multislab (SMSlab) imaging.
Theory and Methods
In image domain, the formation of slab boundary artifacts can be regarded as modulating the artifact‐free images using the slab profiles and introducing aliasing along the slice direction. Slab boundary artifact correction is the inverse problem of this process. An iterative algorithm based on convolutional neural networks (CNNs) is proposed to solve the problem, termed CNN‐enabled inversion for slab profile encoding (CPEN). Diffusion‐weighted SMSlab images and reference images without slab boundary artifacts were acquired in 7 healthy subjects for training. Images of 5 healthy subjects were acquired for testing, including single‐band multislab and SMSlab images with 1.3‐mm or 1‐mm isotropic resolution. CNN‐enabled inversion for slab profile encoding was compared with a previously reported method (i.e., nonlinear inversion for slab profile encoding [NPEN]).
Results
CNN‐enabled inversion for slab profile encoding reduces the slab boundary artifacts in both single‐band multislab and SMSlab images. It also suppresses the slab boundary artifacts in the diffusion metric maps. Compared with NPEN, CPEN shows fewer residual artifacts in different acquisition protocols and more significant improvements in quantitative assessment, and it also accelerates the computation by more than 35 times.
Conclusion
CNN‐enabled inversion for slab profile encoding can reduce the slab boundary artifacts in multislab acquisitions. It shows better slab boundary artifact correction capacity, higher robustness, and computation efficiency when compared with NPEN. It has the potential to improve the accuracy of multislab acquisitions in high‐resolution DWI and functional MRI. |
| doi_str_mv | 10.1002/mrm.29047 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2582811212</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2621127181</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3537-425bca4160c5774958b4828f3e93e918df6d2e7efe7eb407f2564f98ad6c91073</originalsourceid><addsrcrecordid>eNp1kU1LBSEUhiWKun0s-gMx0KYWU-roOC4j-oIi6GM9OI7GlKOlY3F37dsE_cN-SU731iIIjkcXDw_H8wKwieAeghDv977fwxwStgAmiGKcY8rJIphARmBeIE5WwGoI9xBCzhlZBisFKSmFnE7A27URTda4aFvhp5nwQ6eFHDLpvFdy6JzNOpv10QxdGMmuF3edvctiGLt09tmZOGLCfL6-WxX9_DG8OP_w-fqhrGiMapPlWfkw-rTz2bfr0TvdGZUpK12bdOtgSQsT1Mb8XgO3x0c3h6f5-eXJ2eHBeS4LWrCcYNpIQVAJJWWMcFo1pMKVLhRPhapWly1WTOl0GgKZxrQkmleiLSVHkBVrYGfmTQM8RRWGuu-CVMYIq1wMNaZJhxBGOKHbf9B7F336bKJKnBiGKpSo3RklvQvBK10_-rQoP60RrMeE6pRQ_Z1QYrfmxtj0qv0lfyJJwP4MeEm7mf5vqi-uLmbKL3iloD8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2621127181</pqid></control><display><type>article</type><title>Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding</title><source>MEDLINE</source><source>Access via Wiley Online Library</source><creator>Zhang, Jieying ; Liu, Simin ; Dai, Erpeng ; Ye, Xinyu ; Shi, Diwei ; Wu, Yuhsuan ; Lu, Jie ; Guo, Hua</creator><creatorcontrib>Zhang, Jieying ; Liu, Simin ; Dai, Erpeng ; Ye, Xinyu ; Shi, Diwei ; Wu, Yuhsuan ; Lu, Jie ; Guo, Hua</creatorcontrib><description>Purpose
This study aims to propose a novel algorithm for slab boundary artifact correction in both single‐band multislab imaging and simultaneous multislab (SMSlab) imaging.
Theory and Methods
In image domain, the formation of slab boundary artifacts can be regarded as modulating the artifact‐free images using the slab profiles and introducing aliasing along the slice direction. Slab boundary artifact correction is the inverse problem of this process. An iterative algorithm based on convolutional neural networks (CNNs) is proposed to solve the problem, termed CNN‐enabled inversion for slab profile encoding (CPEN). Diffusion‐weighted SMSlab images and reference images without slab boundary artifacts were acquired in 7 healthy subjects for training. Images of 5 healthy subjects were acquired for testing, including single‐band multislab and SMSlab images with 1.3‐mm or 1‐mm isotropic resolution. CNN‐enabled inversion for slab profile encoding was compared with a previously reported method (i.e., nonlinear inversion for slab profile encoding [NPEN]).
Results
CNN‐enabled inversion for slab profile encoding reduces the slab boundary artifacts in both single‐band multislab and SMSlab images. It also suppresses the slab boundary artifacts in the diffusion metric maps. Compared with NPEN, CPEN shows fewer residual artifacts in different acquisition protocols and more significant improvements in quantitative assessment, and it also accelerates the computation by more than 35 times.
Conclusion
CNN‐enabled inversion for slab profile encoding can reduce the slab boundary artifacts in multislab acquisitions. It shows better slab boundary artifact correction capacity, higher robustness, and computation efficiency when compared with NPEN. It has the potential to improve the accuracy of multislab acquisitions in high‐resolution DWI and functional MRI.</description><identifier>ISSN: 0740-3194</identifier><identifier>EISSN: 1522-2594</identifier><identifier>DOI: 10.1002/mrm.29047</identifier><identifier>PMID: 34655095</identifier><language>eng</language><publisher>United States: Wiley Subscription Services, Inc</publisher><subject>3D multislab ; Algorithms ; Artificial neural networks ; Brain - diagnostic imaging ; deep learning ; Functional magnetic resonance imaging ; Humans ; Image acquisition ; Image Processing, Computer-Assisted ; Inverse problems ; Inversion ; Iterative algorithms ; Iterative methods ; Magnetic Resonance Imaging ; model‐based CNN ; Neural networks ; Neural Networks, Computer ; Robustness (mathematics) ; simultaneous multislab ; slab boundary artifacts</subject><ispartof>Magnetic resonance in medicine, 2022-03, Vol.87 (3), p.1546-1560</ispartof><rights>2021 International Society for Magnetic Resonance in Medicine</rights><rights>2021 International Society for Magnetic Resonance in Medicine.</rights><rights>2022 International Society for Magnetic Resonance in Medicine</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3537-425bca4160c5774958b4828f3e93e918df6d2e7efe7eb407f2564f98ad6c91073</citedby><cites>FETCH-LOGICAL-c3537-425bca4160c5774958b4828f3e93e918df6d2e7efe7eb407f2564f98ad6c91073</cites><orcidid>0000-0002-0482-1493 ; 0000-0002-1032-5883</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%2Fmrm.29047$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1002%2Fmrm.29047$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>315,781,785,1418,27926,27927,45576,45577</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34655095$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Jieying</creatorcontrib><creatorcontrib>Liu, Simin</creatorcontrib><creatorcontrib>Dai, Erpeng</creatorcontrib><creatorcontrib>Ye, Xinyu</creatorcontrib><creatorcontrib>Shi, Diwei</creatorcontrib><creatorcontrib>Wu, Yuhsuan</creatorcontrib><creatorcontrib>Lu, Jie</creatorcontrib><creatorcontrib>Guo, Hua</creatorcontrib><title>Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding</title><title>Magnetic resonance in medicine</title><addtitle>Magn Reson Med</addtitle><description>Purpose
This study aims to propose a novel algorithm for slab boundary artifact correction in both single‐band multislab imaging and simultaneous multislab (SMSlab) imaging.
Theory and Methods
In image domain, the formation of slab boundary artifacts can be regarded as modulating the artifact‐free images using the slab profiles and introducing aliasing along the slice direction. Slab boundary artifact correction is the inverse problem of this process. An iterative algorithm based on convolutional neural networks (CNNs) is proposed to solve the problem, termed CNN‐enabled inversion for slab profile encoding (CPEN). Diffusion‐weighted SMSlab images and reference images without slab boundary artifacts were acquired in 7 healthy subjects for training. Images of 5 healthy subjects were acquired for testing, including single‐band multislab and SMSlab images with 1.3‐mm or 1‐mm isotropic resolution. CNN‐enabled inversion for slab profile encoding was compared with a previously reported method (i.e., nonlinear inversion for slab profile encoding [NPEN]).
Results
CNN‐enabled inversion for slab profile encoding reduces the slab boundary artifacts in both single‐band multislab and SMSlab images. It also suppresses the slab boundary artifacts in the diffusion metric maps. Compared with NPEN, CPEN shows fewer residual artifacts in different acquisition protocols and more significant improvements in quantitative assessment, and it also accelerates the computation by more than 35 times.
Conclusion
CNN‐enabled inversion for slab profile encoding can reduce the slab boundary artifacts in multislab acquisitions. It shows better slab boundary artifact correction capacity, higher robustness, and computation efficiency when compared with NPEN. It has the potential to improve the accuracy of multislab acquisitions in high‐resolution DWI and functional MRI.</description><subject>3D multislab</subject><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Brain - diagnostic imaging</subject><subject>deep learning</subject><subject>Functional magnetic resonance imaging</subject><subject>Humans</subject><subject>Image acquisition</subject><subject>Image Processing, Computer-Assisted</subject><subject>Inverse problems</subject><subject>Inversion</subject><subject>Iterative algorithms</subject><subject>Iterative methods</subject><subject>Magnetic Resonance Imaging</subject><subject>model‐based CNN</subject><subject>Neural networks</subject><subject>Neural Networks, Computer</subject><subject>Robustness (mathematics)</subject><subject>simultaneous multislab</subject><subject>slab boundary artifacts</subject><issn>0740-3194</issn><issn>1522-2594</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp1kU1LBSEUhiWKun0s-gMx0KYWU-roOC4j-oIi6GM9OI7GlKOlY3F37dsE_cN-SU731iIIjkcXDw_H8wKwieAeghDv977fwxwStgAmiGKcY8rJIphARmBeIE5WwGoI9xBCzhlZBisFKSmFnE7A27URTda4aFvhp5nwQ6eFHDLpvFdy6JzNOpv10QxdGMmuF3edvctiGLt09tmZOGLCfL6-WxX9_DG8OP_w-fqhrGiMapPlWfkw-rTz2bfr0TvdGZUpK12bdOtgSQsT1Mb8XgO3x0c3h6f5-eXJ2eHBeS4LWrCcYNpIQVAJJWWMcFo1pMKVLhRPhapWly1WTOl0GgKZxrQkmleiLSVHkBVrYGfmTQM8RRWGuu-CVMYIq1wMNaZJhxBGOKHbf9B7F336bKJKnBiGKpSo3RklvQvBK10_-rQoP60RrMeE6pRQ_Z1QYrfmxtj0qv0lfyJJwP4MeEm7mf5vqi-uLmbKL3iloD8</recordid><startdate>202203</startdate><enddate>202203</enddate><creator>Zhang, Jieying</creator><creator>Liu, Simin</creator><creator>Dai, Erpeng</creator><creator>Ye, Xinyu</creator><creator>Shi, Diwei</creator><creator>Wu, Yuhsuan</creator><creator>Lu, Jie</creator><creator>Guo, Hua</creator><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>8FD</scope><scope>FR3</scope><scope>K9.</scope><scope>M7Z</scope><scope>P64</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-0482-1493</orcidid><orcidid>https://orcid.org/0000-0002-1032-5883</orcidid></search><sort><creationdate>202203</creationdate><title>Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding</title><author>Zhang, Jieying ; Liu, Simin ; Dai, Erpeng ; Ye, Xinyu ; Shi, Diwei ; Wu, Yuhsuan ; Lu, Jie ; Guo, Hua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3537-425bca4160c5774958b4828f3e93e918df6d2e7efe7eb407f2564f98ad6c91073</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>3D multislab</topic><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Brain - diagnostic imaging</topic><topic>deep learning</topic><topic>Functional magnetic resonance imaging</topic><topic>Humans</topic><topic>Image acquisition</topic><topic>Image Processing, Computer-Assisted</topic><topic>Inverse problems</topic><topic>Inversion</topic><topic>Iterative algorithms</topic><topic>Iterative methods</topic><topic>Magnetic Resonance Imaging</topic><topic>model‐based CNN</topic><topic>Neural networks</topic><topic>Neural Networks, Computer</topic><topic>Robustness (mathematics)</topic><topic>simultaneous multislab</topic><topic>slab boundary artifacts</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Jieying</creatorcontrib><creatorcontrib>Liu, Simin</creatorcontrib><creatorcontrib>Dai, Erpeng</creatorcontrib><creatorcontrib>Ye, Xinyu</creatorcontrib><creatorcontrib>Shi, Diwei</creatorcontrib><creatorcontrib>Wu, Yuhsuan</creatorcontrib><creatorcontrib>Lu, Jie</creatorcontrib><creatorcontrib>Guo, Hua</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Biochemistry Abstracts 1</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>MEDLINE - Academic</collection><jtitle>Magnetic resonance in medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhang, Jieying</au><au>Liu, Simin</au><au>Dai, Erpeng</au><au>Ye, Xinyu</au><au>Shi, Diwei</au><au>Wu, Yuhsuan</au><au>Lu, Jie</au><au>Guo, Hua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding</atitle><jtitle>Magnetic resonance in medicine</jtitle><addtitle>Magn Reson Med</addtitle><date>2022-03</date><risdate>2022</risdate><volume>87</volume><issue>3</issue><spage>1546</spage><epage>1560</epage><pages>1546-1560</pages><issn>0740-3194</issn><eissn>1522-2594</eissn><abstract>Purpose
This study aims to propose a novel algorithm for slab boundary artifact correction in both single‐band multislab imaging and simultaneous multislab (SMSlab) imaging.
Theory and Methods
In image domain, the formation of slab boundary artifacts can be regarded as modulating the artifact‐free images using the slab profiles and introducing aliasing along the slice direction. Slab boundary artifact correction is the inverse problem of this process. An iterative algorithm based on convolutional neural networks (CNNs) is proposed to solve the problem, termed CNN‐enabled inversion for slab profile encoding (CPEN). Diffusion‐weighted SMSlab images and reference images without slab boundary artifacts were acquired in 7 healthy subjects for training. Images of 5 healthy subjects were acquired for testing, including single‐band multislab and SMSlab images with 1.3‐mm or 1‐mm isotropic resolution. CNN‐enabled inversion for slab profile encoding was compared with a previously reported method (i.e., nonlinear inversion for slab profile encoding [NPEN]).
Results
CNN‐enabled inversion for slab profile encoding reduces the slab boundary artifacts in both single‐band multislab and SMSlab images. It also suppresses the slab boundary artifacts in the diffusion metric maps. Compared with NPEN, CPEN shows fewer residual artifacts in different acquisition protocols and more significant improvements in quantitative assessment, and it also accelerates the computation by more than 35 times.
Conclusion
CNN‐enabled inversion for slab profile encoding can reduce the slab boundary artifacts in multislab acquisitions. It shows better slab boundary artifact correction capacity, higher robustness, and computation efficiency when compared with NPEN. It has the potential to improve the accuracy of multislab acquisitions in high‐resolution DWI and functional MRI.</abstract><cop>United States</cop><pub>Wiley Subscription Services, Inc</pub><pmid>34655095</pmid><doi>10.1002/mrm.29047</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0002-0482-1493</orcidid><orcidid>https://orcid.org/0000-0002-1032-5883</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0740-3194 |
| ispartof | Magnetic resonance in medicine, 2022-03, Vol.87 (3), p.1546-1560 |
| issn | 0740-3194 1522-2594 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2582811212 |
| source | MEDLINE; Access via Wiley Online Library |
| subjects | 3D multislab Algorithms Artificial neural networks Brain - diagnostic imaging deep learning Functional magnetic resonance imaging Humans Image acquisition Image Processing, Computer-Assisted Inverse problems Inversion Iterative algorithms Iterative methods Magnetic Resonance Imaging model‐based CNN Neural networks Neural Networks, Computer Robustness (mathematics) simultaneous multislab slab boundary artifacts |
| title | Slab boundary artifact correction in multislab imaging using convolutional‐neural‐network–enabled inversion for slab profile encoding |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-18T06%3A21%3A35IST&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=Slab%20boundary%20artifact%20correction%20in%20multislab%20imaging%20using%20convolutional%E2%80%90neural%E2%80%90network%E2%80%93enabled%20inversion%20for%20slab%20profile%20encoding&rft.jtitle=Magnetic%20resonance%20in%20medicine&rft.au=Zhang,%20Jieying&rft.date=2022-03&rft.volume=87&rft.issue=3&rft.spage=1546&rft.epage=1560&rft.pages=1546-1560&rft.issn=0740-3194&rft.eissn=1522-2594&rft_id=info:doi/10.1002/mrm.29047&rft_dat=%3Cproquest_cross%3E2621127181%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=2621127181&rft_id=info:pmid/34655095&rfr_iscdi=true |