Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography
Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We...
Gespeichert in:
| Veröffentlicht in: | Journal of digital imaging 2023-06, Vol.36 (3), p.1237-1247 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1247 |
|---|---|
| container_issue | 3 |
| container_start_page | 1237 |
| container_title | Journal of digital imaging |
| container_volume | 36 |
| creator | Yoon, Myeong Seong Kwon, Gitaek Oh, Jaehoon Ryu, Jongbin Lim, Jongwoo Kang, Bo-kyeong Lee, Juncheol Han, Dong-Kyoon |
| description | Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all
p
|
| doi_str_mv | 10.1007/s10278-022-00772-y |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2769994707</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2769994707</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-869997485d924c520f9b345bfab6022e8999b50aba1aeb83fa502d91f885e1013</originalsourceid><addsrcrecordid>eNp9kUFP3DAQha2qqFDgD_RQWeqFS4rtxLFzRAu0SCuBqiJxs5xknAQl9tZOWvbUv96hS0vVAyfbet-8N9Yj5B1nHzlj6jRxJpTOmBAZPpXItq_IAS-5zpRQd6__ue-TtyndM8aVVMUbsp-XZaVZLg_IzwvnoJlpcHQV_BxtmukavsNIrW_p1WQ7oJchThYRTy09B9ggYKMffEfPxi7EYe4n6kKkcw-oz2g3IIuONx6WKcx9iPaB_kCOrnrAgC-2HUIX7abfHpE9Z8cEx0_nIbm9vPi6-pytrz9drc7WWZOLcs50WVWVKrRsK1E0UjBX1Xkha2frEv8PGuVaMltbbqHWubOSibbiTmsJnPH8kJzsfDcxfFtwCTMNqYFxtB7CkoxQjwmFYgrRD_-h92GJHrczQgsthWKsQkrsqCaGlCI4s4nDZOPWcGYe6zG7egyuZ37XY7Y49P7JeqknaP-O_OkDgXwHJJR8B_E5-wXbX5_0myU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2828527009</pqid></control><display><type>article</type><title>Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography</title><source>MEDLINE</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><creator>Yoon, Myeong Seong ; Kwon, Gitaek ; Oh, Jaehoon ; Ryu, Jongbin ; Lim, Jongwoo ; Kang, Bo-kyeong ; Lee, Juncheol ; Han, Dong-Kyoon</creator><creatorcontrib>Yoon, Myeong Seong ; Kwon, Gitaek ; Oh, Jaehoon ; Ryu, Jongbin ; Lim, Jongwoo ; Kang, Bo-kyeong ; Lee, Juncheol ; Han, Dong-Kyoon</creatorcontrib><description>Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all
p
< 0.001) except between 125 and 150% in JPEG format (
p
= 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all
p
< 0.001) except 50% and 100% (
p
= 0.079 and
p
= 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance.</description><identifier>ISSN: 1618-727X</identifier><identifier>ISSN: 0897-1889</identifier><identifier>EISSN: 1618-727X</identifier><identifier>DOI: 10.1007/s10278-022-00772-y</identifier><identifier>PMID: 36698035</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Algorithms ; Chest ; Deep Learning ; Digital imaging ; Format ; Humans ; Image compression ; Image contrast ; Image processing ; Imaging ; Machine learning ; Medical imaging ; Medicine ; Medicine & Public Health ; Pneumothorax ; Pneumothorax - diagnostic imaging ; Radiography ; Radiography, Thoracic - methods ; Radiology ; Retrospective Studies ; ROC Curve ; Test sets</subject><ispartof>Journal of digital imaging, 2023-06, Vol.36 (3), p.1237-1247</ispartof><rights>The Author(s) under exclusive licence to Society for Imaging Informatics in Medicine 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2023. The Author(s) under exclusive licence to Society for Imaging Informatics in Medicine.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c326t-869997485d924c520f9b345bfab6022e8999b50aba1aeb83fa502d91f885e1013</cites><orcidid>0000-0001-5574-5358 ; 0000-0001-8055-1467</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36698035$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yoon, Myeong Seong</creatorcontrib><creatorcontrib>Kwon, Gitaek</creatorcontrib><creatorcontrib>Oh, Jaehoon</creatorcontrib><creatorcontrib>Ryu, Jongbin</creatorcontrib><creatorcontrib>Lim, Jongwoo</creatorcontrib><creatorcontrib>Kang, Bo-kyeong</creatorcontrib><creatorcontrib>Lee, Juncheol</creatorcontrib><creatorcontrib>Han, Dong-Kyoon</creatorcontrib><title>Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography</title><title>Journal of digital imaging</title><addtitle>J Digit Imaging</addtitle><addtitle>J Digit Imaging</addtitle><description>Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all
p
< 0.001) except between 125 and 150% in JPEG format (
p
= 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all
p
< 0.001) except 50% and 100% (
p
= 0.079 and
p
= 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance.</description><subject>Algorithms</subject><subject>Chest</subject><subject>Deep Learning</subject><subject>Digital imaging</subject><subject>Format</subject><subject>Humans</subject><subject>Image compression</subject><subject>Image contrast</subject><subject>Image processing</subject><subject>Imaging</subject><subject>Machine learning</subject><subject>Medical imaging</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Pneumothorax</subject><subject>Pneumothorax - diagnostic imaging</subject><subject>Radiography</subject><subject>Radiography, Thoracic - methods</subject><subject>Radiology</subject><subject>Retrospective Studies</subject><subject>ROC Curve</subject><subject>Test sets</subject><issn>1618-727X</issn><issn>0897-1889</issn><issn>1618-727X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>BENPR</sourceid><recordid>eNp9kUFP3DAQha2qqFDgD_RQWeqFS4rtxLFzRAu0SCuBqiJxs5xknAQl9tZOWvbUv96hS0vVAyfbet-8N9Yj5B1nHzlj6jRxJpTOmBAZPpXItq_IAS-5zpRQd6__ue-TtyndM8aVVMUbsp-XZaVZLg_IzwvnoJlpcHQV_BxtmukavsNIrW_p1WQ7oJchThYRTy09B9ggYKMffEfPxi7EYe4n6kKkcw-oz2g3IIuONx6WKcx9iPaB_kCOrnrAgC-2HUIX7abfHpE9Z8cEx0_nIbm9vPi6-pytrz9drc7WWZOLcs50WVWVKrRsK1E0UjBX1Xkha2frEv8PGuVaMltbbqHWubOSibbiTmsJnPH8kJzsfDcxfFtwCTMNqYFxtB7CkoxQjwmFYgrRD_-h92GJHrczQgsthWKsQkrsqCaGlCI4s4nDZOPWcGYe6zG7egyuZ37XY7Y49P7JeqknaP-O_OkDgXwHJJR8B_E5-wXbX5_0myU</recordid><startdate>20230601</startdate><enddate>20230601</enddate><creator>Yoon, Myeong Seong</creator><creator>Kwon, Gitaek</creator><creator>Oh, Jaehoon</creator><creator>Ryu, Jongbin</creator><creator>Lim, Jongwoo</creator><creator>Kang, Bo-kyeong</creator><creator>Lee, Juncheol</creator><creator>Han, Dong-Kyoon</creator><general>Springer International Publishing</general><general>Springer Nature B.V</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>3V.</scope><scope>7QO</scope><scope>7RV</scope><scope>7SC</scope><scope>7TK</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K9.</scope><scope>KB0</scope><scope>L7M</scope><scope>LK8</scope><scope>L~C</scope><scope>L~D</scope><scope>M0S</scope><scope>M1P</scope><scope>M7P</scope><scope>NAPCQ</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-5574-5358</orcidid><orcidid>https://orcid.org/0000-0001-8055-1467</orcidid></search><sort><creationdate>20230601</creationdate><title>Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography</title><author>Yoon, Myeong Seong ; Kwon, Gitaek ; Oh, Jaehoon ; Ryu, Jongbin ; Lim, Jongwoo ; Kang, Bo-kyeong ; Lee, Juncheol ; Han, Dong-Kyoon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-869997485d924c520f9b345bfab6022e8999b50aba1aeb83fa502d91f885e1013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Algorithms</topic><topic>Chest</topic><topic>Deep Learning</topic><topic>Digital imaging</topic><topic>Format</topic><topic>Humans</topic><topic>Image compression</topic><topic>Image contrast</topic><topic>Image processing</topic><topic>Imaging</topic><topic>Machine learning</topic><topic>Medical imaging</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Pneumothorax</topic><topic>Pneumothorax - diagnostic imaging</topic><topic>Radiography</topic><topic>Radiography, Thoracic - methods</topic><topic>Radiology</topic><topic>Retrospective Studies</topic><topic>ROC Curve</topic><topic>Test sets</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yoon, Myeong Seong</creatorcontrib><creatorcontrib>Kwon, Gitaek</creatorcontrib><creatorcontrib>Oh, Jaehoon</creatorcontrib><creatorcontrib>Ryu, Jongbin</creatorcontrib><creatorcontrib>Lim, Jongwoo</creatorcontrib><creatorcontrib>Kang, Bo-kyeong</creatorcontrib><creatorcontrib>Lee, Juncheol</creatorcontrib><creatorcontrib>Han, Dong-Kyoon</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Biotechnology Research Abstracts</collection><collection>Nursing & Allied Health Database</collection><collection>Computer and Information Systems Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</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>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>ProQuest Biological Science Collection</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Biological Science Database</collection><collection>Nursing & Allied Health Premium</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>MEDLINE - Academic</collection><jtitle>Journal of digital imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yoon, Myeong Seong</au><au>Kwon, Gitaek</au><au>Oh, Jaehoon</au><au>Ryu, Jongbin</au><au>Lim, Jongwoo</au><au>Kang, Bo-kyeong</au><au>Lee, Juncheol</au><au>Han, Dong-Kyoon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography</atitle><jtitle>Journal of digital imaging</jtitle><stitle>J Digit Imaging</stitle><addtitle>J Digit Imaging</addtitle><date>2023-06-01</date><risdate>2023</risdate><volume>36</volume><issue>3</issue><spage>1237</spage><epage>1247</epage><pages>1237-1247</pages><issn>1618-727X</issn><issn>0897-1889</issn><eissn>1618-727X</eissn><abstract>Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all
p
< 0.001) except between 125 and 150% in JPEG format (
p
= 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all
p
< 0.001) except 50% and 100% (
p
= 0.079 and
p
= 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><pmid>36698035</pmid><doi>10.1007/s10278-022-00772-y</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0001-5574-5358</orcidid><orcidid>https://orcid.org/0000-0001-8055-1467</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1618-727X |
| ispartof | Journal of digital imaging, 2023-06, Vol.36 (3), p.1237-1247 |
| issn | 1618-727X 0897-1889 1618-727X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_2769994707 |
| source | MEDLINE; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central |
| subjects | Algorithms Chest Deep Learning Digital imaging Format Humans Image compression Image contrast Image processing Imaging Machine learning Medical imaging Medicine Medicine & Public Health Pneumothorax Pneumothorax - diagnostic imaging Radiography Radiography, Thoracic - methods Radiology Retrospective Studies ROC Curve Test sets |
| title | Effect of Contrast Level and Image Format on a Deep Learning Algorithm for the Detection of Pneumothorax with Chest Radiography |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T00%3A07%3A24IST&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=Effect%20of%20Contrast%20Level%20and%20Image%20Format%20on%20a%20Deep%20Learning%20Algorithm%20for%20the%20Detection%20of%20Pneumothorax%20with%20Chest%20Radiography&rft.jtitle=Journal%20of%20digital%20imaging&rft.au=Yoon,%20Myeong%20Seong&rft.date=2023-06-01&rft.volume=36&rft.issue=3&rft.spage=1237&rft.epage=1247&rft.pages=1237-1247&rft.issn=1618-727X&rft.eissn=1618-727X&rft_id=info:doi/10.1007/s10278-022-00772-y&rft_dat=%3Cproquest_cross%3E2769994707%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=2828527009&rft_id=info:pmid/36698035&rfr_iscdi=true |