Deep learning for undersampled MRI reconstruction
This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to captur...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2019-05 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Chang, Min Hyun Kim, Hwa Pyung Lee, Sung Min Lee, Sungchul Seo, Jin Keun |
| description | This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data. |
| doi_str_mv | 10.48550/arxiv.1709.02576 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1709_02576</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2076623699</sourcerecordid><originalsourceid>FETCH-LOGICAL-a529-2afb8e31f845f6aee59eb23b4bdea15dcdecc29fb45cd2d9a98fe87e0d68116c3</originalsourceid><addsrcrecordid>eNotj11LwzAYRoMgbMz9gF1Z8Lo1edOkyaXMjw0mguy-pMkb6ejSmrSi_965efXcHB7OIWTFaFEqIei9id_tV8EqqgsKopJXZA6cs1yVADOyTOlAKQVZgRB8Ttgj4pB1aGJow0fm-5hNwWFM5jh06LLX920W0fYhjXGyY9uHG3LtTZdw-b8Lsn9-2q83-e7tZbt-2OVGgM7B-EYhZ16VwkuDKDQ2wJuycWiYcNahtaB9UwrrwGmjlUdVIXVSMSYtX5Dby-25px5iezTxp_7rqs9dJ-LuQgyx_5wwjfWhn2I4OdVAKymBS635Lwk1URE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2076623699</pqid></control><display><type>article</type><title>Deep learning for undersampled MRI reconstruction</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Chang, Min Hyun ; Kim, Hwa Pyung ; Lee, Sung Min ; Lee, Sungchul ; Seo, Jin Keun</creator><creatorcontrib>Chang, Min Hyun ; Kim, Hwa Pyung ; Lee, Sung Min ; Lee, Sungchul ; Seo, Jin Keun</creatorcontrib><description>This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1709.02576</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Learning ; Deep learning ; Folding ; Fourier transforms ; Image quality ; Image reconstruction ; Image resolution ; Magnetic resonance imaging ; NMR ; Nuclear magnetic resonance ; Physics - Medical Physics ; Statistics - Machine Learning</subject><ispartof>arXiv.org, 2019-05</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.1088/1361-6560/aac71a$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1709.02576$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chang, Min Hyun</creatorcontrib><creatorcontrib>Kim, Hwa Pyung</creatorcontrib><creatorcontrib>Lee, Sung Min</creatorcontrib><creatorcontrib>Lee, Sungchul</creatorcontrib><creatorcontrib>Seo, Jin Keun</creatorcontrib><title>Deep learning for undersampled MRI reconstruction</title><title>arXiv.org</title><description>This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data.</description><subject>Computer Science - Learning</subject><subject>Deep learning</subject><subject>Folding</subject><subject>Fourier transforms</subject><subject>Image quality</subject><subject>Image reconstruction</subject><subject>Image resolution</subject><subject>Magnetic resonance imaging</subject><subject>NMR</subject><subject>Nuclear magnetic resonance</subject><subject>Physics - Medical Physics</subject><subject>Statistics - Machine Learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj11LwzAYRoMgbMz9gF1Z8Lo1edOkyaXMjw0mguy-pMkb6ejSmrSi_965efXcHB7OIWTFaFEqIei9id_tV8EqqgsKopJXZA6cs1yVADOyTOlAKQVZgRB8Ttgj4pB1aGJow0fm-5hNwWFM5jh06LLX920W0fYhjXGyY9uHG3LtTZdw-b8Lsn9-2q83-e7tZbt-2OVGgM7B-EYhZ16VwkuDKDQ2wJuycWiYcNahtaB9UwrrwGmjlUdVIXVSMSYtX5Dby-25px5iezTxp_7rqs9dJ-LuQgyx_5wwjfWhn2I4OdVAKymBS635Lwk1URE</recordid><startdate>20190512</startdate><enddate>20190512</enddate><creator>Chang, Min Hyun</creator><creator>Kim, Hwa Pyung</creator><creator>Lee, Sung Min</creator><creator>Lee, Sungchul</creator><creator>Seo, Jin Keun</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190512</creationdate><title>Deep learning for undersampled MRI reconstruction</title><author>Chang, Min Hyun ; Kim, Hwa Pyung ; Lee, Sung Min ; Lee, Sungchul ; Seo, Jin Keun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a529-2afb8e31f845f6aee59eb23b4bdea15dcdecc29fb45cd2d9a98fe87e0d68116c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Learning</topic><topic>Deep learning</topic><topic>Folding</topic><topic>Fourier transforms</topic><topic>Image quality</topic><topic>Image reconstruction</topic><topic>Image resolution</topic><topic>Magnetic resonance imaging</topic><topic>NMR</topic><topic>Nuclear magnetic resonance</topic><topic>Physics - Medical Physics</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Chang, Min Hyun</creatorcontrib><creatorcontrib>Kim, Hwa Pyung</creatorcontrib><creatorcontrib>Lee, Sung Min</creatorcontrib><creatorcontrib>Lee, Sungchul</creatorcontrib><creatorcontrib>Seo, Jin Keun</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chang, Min Hyun</au><au>Kim, Hwa Pyung</au><au>Lee, Sung Min</au><au>Lee, Sungchul</au><au>Seo, Jin Keun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep learning for undersampled MRI reconstruction</atitle><jtitle>arXiv.org</jtitle><date>2019-05-12</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>This paper presents a deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and provides a rationale for why the proposed approach works well. Uniform subsampling is used in the time-consuming phase-encoding direction to capture high-resolution image information, while permitting the image-folding problem dictated by the Poisson summation formula. To deal with the localization uncertainty due to image folding, very few low-frequency k-space data are added. Training the deep learning net involves input and output images that are pairs of Fourier transforms of the subsampled and fully sampled k-space data. Numerous experiments show the remarkable performance of the proposed method; only 29% of k-space data can generate images of high quality as effectively as standard MRI reconstruction with fully sampled data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1709.02576</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2019-05 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_arxiv_primary_1709_02576 |
| source | arXiv.org; Free E- Journals |
| subjects | Computer Science - Learning Deep learning Folding Fourier transforms Image quality Image reconstruction Image resolution Magnetic resonance imaging NMR Nuclear magnetic resonance Physics - Medical Physics Statistics - Machine Learning |
| title | Deep learning for undersampled MRI reconstruction |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T01%3A16%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20learning%20for%20undersampled%20MRI%20reconstruction&rft.jtitle=arXiv.org&rft.au=Chang,%20Min%20Hyun&rft.date=2019-05-12&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1709.02576&rft_dat=%3Cproquest_arxiv%3E2076623699%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2076623699&rft_id=info:pmid/&rfr_iscdi=true |