About the generalizability of deep learning based image quality assessment in mammography
One method of assessing the image quality of a mammography unit is to estimate a contrast-detail-curve (CDC) that is obtained from images of a technical phantom. It has been proposed to estimate this CDC by using an end-to-end neural network (NN) which only needs one image to determine the CDC. That...
Gespeichert in:
| Veröffentlicht in: | Machine learning: science and technology 2023-12, Vol.4 (4), p.45001 |
|---|---|
| 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 | 4 |
| container_start_page | 45001 |
| container_title | Machine learning: science and technology |
| container_volume | 4 |
| creator | Faller, Josua Amanova, Narbota van Engen, Ruben Martin, Jörg Elster, Clemens |
| description | One method of assessing the image quality of a mammography unit is to estimate a contrast-detail-curve (CDC) that is obtained from images of a technical phantom. It has been proposed to estimate this CDC by using an end-to-end neural network (NN) which only needs one image to determine the CDC. That approach, however, has been developed on the basis of images of one single mammography unit. In this work, we train NNs on synthetic images of contrast-detail phantoms for mammography and test the so-trained NNs on images that are obtained from real mammography units. The goal of this paper is to demonstrate that such a deep learning approach is capable to generalize to predict CDCs for various real mammography units. Our experiments cover various manufacturers and the proposed approach is shown to work across different NN architectures and preprocessing methods which highlights its generalizability. |
| doi_str_mv | 10.1088/2632-2153/acf914 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_iop_j</sourceid><recordid>TN_cdi_proquest_journals_2872962397</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_58929a26e8b7402e81e7ce41f5848f46</doaj_id><sourcerecordid>2872962397</sourcerecordid><originalsourceid>FETCH-LOGICAL-c331t-dba9b55594783ebdf75ff35687e3ca1d1fabe527748698aba31938629425a5903</originalsourceid><addsrcrecordid>eNp9kb9P3TAQxyNUJBCwM1piYOkr_hnbI0ItRULq0g6drHNyDn5K4mDnDa9_ffMIAoaquuFOp89976u7qrpk9AujxtzwWvANZ0rcQBMsk0fV6Vvr04f6pLooZUsp5YoJxelp9fvWp91M5ickHY6YoY9_wMc-znuSAmkRJ9Ij5DGOHfFQsCVxgA7J8w5eICgFSxlwnEkcyQDDkLoM09P-vDoO0Be8eM1n1a9vX3_efd88_rh_uLt93DRCsHnTerBeKWWlNgJ9G7QKQajaaBQNsJYF8Ki41tLU1oAHwawwNbeSK1CWirPqYdVtE2zdlBd7ee8SRPfSSLlzkOfY9OiUsdwCr9F4LSlHw1A3KFlQRpog60XratWacnreYZndNu3yuNh33Ghuay6sXii6Uk1OpWQMb1sZdYd_uMPB3eHgbv3HMvJ5HYlpetf8D379D3zoF0NyCSoVpcxNbRB_AZszmEA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2872962397</pqid></control><display><type>article</type><title>About the generalizability of deep learning based image quality assessment in mammography</title><source>IOP Publishing Free Content</source><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Faller, Josua ; Amanova, Narbota ; van Engen, Ruben ; Martin, Jörg ; Elster, Clemens</creator><creatorcontrib>Faller, Josua ; Amanova, Narbota ; van Engen, Ruben ; Martin, Jörg ; Elster, Clemens</creatorcontrib><description>One method of assessing the image quality of a mammography unit is to estimate a contrast-detail-curve (CDC) that is obtained from images of a technical phantom. It has been proposed to estimate this CDC by using an end-to-end neural network (NN) which only needs one image to determine the CDC. That approach, however, has been developed on the basis of images of one single mammography unit. In this work, we train NNs on synthetic images of contrast-detail phantoms for mammography and test the so-trained NNs on images that are obtained from real mammography units. The goal of this paper is to demonstrate that such a deep learning approach is capable to generalize to predict CDCs for various real mammography units. Our experiments cover various manufacturers and the proposed approach is shown to work across different NN architectures and preprocessing methods which highlights its generalizability.</description><identifier>ISSN: 2632-2153</identifier><identifier>EISSN: 2632-2153</identifier><identifier>DOI: 10.1088/2632-2153/acf914</identifier><identifier>CODEN: MLSTCK</identifier><language>eng</language><publisher>Bristol: IOP Publishing</publisher><subject>Deep learning ; Image contrast ; Image quality ; Machine learning ; mammography ; medical imaging ; MSLE approximation ; neural network ; Neural networks ; Quality assessment ; synthetic data</subject><ispartof>Machine learning: science and technology, 2023-12, Vol.4 (4), p.45001</ispartof><rights>2023 The Author(s). Published by IOP Publishing Ltd</rights><rights>2023 The Author(s). Published by IOP Publishing Ltd. This work 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><cites>FETCH-LOGICAL-c331t-dba9b55594783ebdf75ff35687e3ca1d1fabe527748698aba31938629425a5903</cites><orcidid>0000-0002-4193-8906 ; 0000-0001-5066-7661 ; 0000-0001-7006-1376 ; 0000-0003-0113-3713 ; 0000-0002-7780-7078</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.1088/2632-2153/acf914/pdf$$EPDF$$P50$$Giop$$Hfree_for_read</linktopdf><link.rule.ids>314,776,780,860,2096,27901,27902,38867,53842</link.rule.ids></links><search><creatorcontrib>Faller, Josua</creatorcontrib><creatorcontrib>Amanova, Narbota</creatorcontrib><creatorcontrib>van Engen, Ruben</creatorcontrib><creatorcontrib>Martin, Jörg</creatorcontrib><creatorcontrib>Elster, Clemens</creatorcontrib><title>About the generalizability of deep learning based image quality assessment in mammography</title><title>Machine learning: science and technology</title><addtitle>MLST</addtitle><addtitle>Mach. Learn.: Sci. Technol</addtitle><description>One method of assessing the image quality of a mammography unit is to estimate a contrast-detail-curve (CDC) that is obtained from images of a technical phantom. It has been proposed to estimate this CDC by using an end-to-end neural network (NN) which only needs one image to determine the CDC. That approach, however, has been developed on the basis of images of one single mammography unit. In this work, we train NNs on synthetic images of contrast-detail phantoms for mammography and test the so-trained NNs on images that are obtained from real mammography units. The goal of this paper is to demonstrate that such a deep learning approach is capable to generalize to predict CDCs for various real mammography units. Our experiments cover various manufacturers and the proposed approach is shown to work across different NN architectures and preprocessing methods which highlights its generalizability.</description><subject>Deep learning</subject><subject>Image contrast</subject><subject>Image quality</subject><subject>Machine learning</subject><subject>mammography</subject><subject>medical imaging</subject><subject>MSLE approximation</subject><subject>neural network</subject><subject>Neural networks</subject><subject>Quality assessment</subject><subject>synthetic data</subject><issn>2632-2153</issn><issn>2632-2153</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>O3W</sourceid><sourceid>BENPR</sourceid><sourceid>DOA</sourceid><recordid>eNp9kb9P3TAQxyNUJBCwM1piYOkr_hnbI0ItRULq0g6drHNyDn5K4mDnDa9_ffMIAoaquuFOp89976u7qrpk9AujxtzwWvANZ0rcQBMsk0fV6Vvr04f6pLooZUsp5YoJxelp9fvWp91M5ickHY6YoY9_wMc-znuSAmkRJ9Ij5DGOHfFQsCVxgA7J8w5eICgFSxlwnEkcyQDDkLoM09P-vDoO0Be8eM1n1a9vX3_efd88_rh_uLt93DRCsHnTerBeKWWlNgJ9G7QKQajaaBQNsJYF8Ki41tLU1oAHwawwNbeSK1CWirPqYdVtE2zdlBd7ee8SRPfSSLlzkOfY9OiUsdwCr9F4LSlHw1A3KFlQRpog60XratWacnreYZndNu3yuNh33Ghuay6sXii6Uk1OpWQMb1sZdYd_uMPB3eHgbv3HMvJ5HYlpetf8D379D3zoF0NyCSoVpcxNbRB_AZszmEA</recordid><startdate>20231201</startdate><enddate>20231201</enddate><creator>Faller, Josua</creator><creator>Amanova, Narbota</creator><creator>van Engen, Ruben</creator><creator>Martin, Jörg</creator><creator>Elster, Clemens</creator><general>IOP Publishing</general><scope>O3W</scope><scope>TSCCA</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7XB</scope><scope>88I</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>M2P</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-4193-8906</orcidid><orcidid>https://orcid.org/0000-0001-5066-7661</orcidid><orcidid>https://orcid.org/0000-0001-7006-1376</orcidid><orcidid>https://orcid.org/0000-0003-0113-3713</orcidid><orcidid>https://orcid.org/0000-0002-7780-7078</orcidid></search><sort><creationdate>20231201</creationdate><title>About the generalizability of deep learning based image quality assessment in mammography</title><author>Faller, Josua ; Amanova, Narbota ; van Engen, Ruben ; Martin, Jörg ; Elster, Clemens</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c331t-dba9b55594783ebdf75ff35687e3ca1d1fabe527748698aba31938629425a5903</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Deep learning</topic><topic>Image contrast</topic><topic>Image quality</topic><topic>Machine learning</topic><topic>mammography</topic><topic>medical imaging</topic><topic>MSLE approximation</topic><topic>neural network</topic><topic>Neural networks</topic><topic>Quality assessment</topic><topic>synthetic data</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Faller, Josua</creatorcontrib><creatorcontrib>Amanova, Narbota</creatorcontrib><creatorcontrib>van Engen, Ruben</creatorcontrib><creatorcontrib>Martin, Jörg</creatorcontrib><creatorcontrib>Elster, Clemens</creatorcontrib><collection>IOP Publishing Free Content</collection><collection>IOPscience (Open Access)</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Science Database (Alumni Edition)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Science Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</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>ProQuest Central Basic</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Machine learning: science and technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Faller, Josua</au><au>Amanova, Narbota</au><au>van Engen, Ruben</au><au>Martin, Jörg</au><au>Elster, Clemens</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>About the generalizability of deep learning based image quality assessment in mammography</atitle><jtitle>Machine learning: science and technology</jtitle><stitle>MLST</stitle><addtitle>Mach. Learn.: Sci. Technol</addtitle><date>2023-12-01</date><risdate>2023</risdate><volume>4</volume><issue>4</issue><spage>45001</spage><pages>45001-</pages><issn>2632-2153</issn><eissn>2632-2153</eissn><coden>MLSTCK</coden><abstract>One method of assessing the image quality of a mammography unit is to estimate a contrast-detail-curve (CDC) that is obtained from images of a technical phantom. It has been proposed to estimate this CDC by using an end-to-end neural network (NN) which only needs one image to determine the CDC. That approach, however, has been developed on the basis of images of one single mammography unit. In this work, we train NNs on synthetic images of contrast-detail phantoms for mammography and test the so-trained NNs on images that are obtained from real mammography units. The goal of this paper is to demonstrate that such a deep learning approach is capable to generalize to predict CDCs for various real mammography units. Our experiments cover various manufacturers and the proposed approach is shown to work across different NN architectures and preprocessing methods which highlights its generalizability.</abstract><cop>Bristol</cop><pub>IOP Publishing</pub><doi>10.1088/2632-2153/acf914</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-4193-8906</orcidid><orcidid>https://orcid.org/0000-0001-5066-7661</orcidid><orcidid>https://orcid.org/0000-0001-7006-1376</orcidid><orcidid>https://orcid.org/0000-0003-0113-3713</orcidid><orcidid>https://orcid.org/0000-0002-7780-7078</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2632-2153 |
| ispartof | Machine learning: science and technology, 2023-12, Vol.4 (4), p.45001 |
| issn | 2632-2153 2632-2153 |
| language | eng |
| recordid | cdi_proquest_journals_2872962397 |
| source | IOP Publishing Free Content; DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Deep learning Image contrast Image quality Machine learning mammography medical imaging MSLE approximation neural network Neural networks Quality assessment synthetic data |
| title | About the generalizability of deep learning based image quality assessment in mammography |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T05%3A55%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_iop_j&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=About%20the%20generalizability%20of%20deep%20learning%20based%20image%20quality%20assessment%20in%20mammography&rft.jtitle=Machine%20learning:%20science%20and%20technology&rft.au=Faller,%20Josua&rft.date=2023-12-01&rft.volume=4&rft.issue=4&rft.spage=45001&rft.pages=45001-&rft.issn=2632-2153&rft.eissn=2632-2153&rft.coden=MLSTCK&rft_id=info:doi/10.1088/2632-2153/acf914&rft_dat=%3Cproquest_iop_j%3E2872962397%3C/proquest_iop_j%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2872962397&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_58929a26e8b7402e81e7ce41f5848f46&rfr_iscdi=true |