Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images
Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy d...
Gespeichert in:
Veröffentlicht in: | PloS one 2023-05, Vol.18 (5), p.e0285996-e0285996 |
---|---|
Hauptverfasser: | , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | e0285996 |
---|---|
container_issue | 5 |
container_start_page | e0285996 |
container_title | PloS one |
container_volume | 18 |
creator | Kurita, Yuki Meguro, Shiori Tsuyama, Naoko Kosugi, Isao Enomoto, Yasunori Kawasaki, Hideya Uemura, Takashi Kimura, Michio Iwashita, Toshihide |
description | Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology. |
doi_str_mv | 10.1371/journal.pone.0285996 |
format | Article |
fullrecord | <record><control><sourceid>gale_plos_</sourceid><recordid>TN_cdi_plos_journals_2815235975</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A749745165</galeid><doaj_id>oai_doaj_org_article_3f8d4c6456874d3288487eb1e9ff2ef1</doaj_id><sourcerecordid>A749745165</sourcerecordid><originalsourceid>FETCH-LOGICAL-c693t-ad6b4cb83c08a73e17f50e415763ff43c6c26b3d24fecd26defe10a5970cf8933</originalsourceid><addsrcrecordid>eNqNk99u0zAUxiMEYmPwBggsISG4aLFjx0muUDXxp9LEJAbcWq593Lpy7c5OBnsCXhtnzUaLdoFykWPn9332OTmnKJ4TPCW0Ju_WoY9euuk2eJjisqnalj8ojklLywkvMX24Fx8VT1JaY1zRhvPHxRGtS5wl5Lj4PVOqj7IDpAG2yIGM3vol2gQNDvVpiBNs7CT1W4hXNoH-C0mv0Zdg0zW66HoNvkMmRKQGTkmHlPQ5RklFgBveeuTCT7SRS29NRjobPLJ5Celp8chIl-DZ-D4pvn_88O308-Ts_NP8dHY2Ubyl3URqvmBq0VCFG1lTILWpMDBS1Zwaw6jiquQLqktmQOmSazBAsKzaGivTtJSeFC93vlsXkhhrmESuRVXSjFWZmO8IHeRabGO-X7wWQVpxsxHiUsjYWeVAUNNopjireFMzTcumYU0NCwKtMSUYkr3ej6f1iw1olUsUpTswPfzi7Uosw5UgmLSsqVh2eDM6xHDZQ-rExiYFzkkPob-5OM-5U9xm9NU_6P3pjdRS5gysNyEfrAZTMatZW7OK8IGa3kPlR-deULnjjM37B4K3B4LMdPCrW8o-JTG_-Pr_7PmPQ_b1HrsC6bpVCq4fWicdgmwHqhhSimDuqkywGAbmthpiGBgxDkyWvdj_Q3ei2wmhfwCIbxLp</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2815235975</pqid></control><display><type>article</type><title>Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images</title><source>Public Library of Science (PLoS) Journals Open Access</source><source>MEDLINE</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><source>Free Full-Text Journals in Chemistry</source><creator>Kurita, Yuki ; Meguro, Shiori ; Tsuyama, Naoko ; Kosugi, Isao ; Enomoto, Yasunori ; Kawasaki, Hideya ; Uemura, Takashi ; Kimura, Michio ; Iwashita, Toshihide</creator><contributor>Giannini, Andrea</contributor><creatorcontrib>Kurita, Yuki ; Meguro, Shiori ; Tsuyama, Naoko ; Kosugi, Isao ; Enomoto, Yasunori ; Kawasaki, Hideya ; Uemura, Takashi ; Kimura, Michio ; Iwashita, Toshihide ; Giannini, Andrea</creatorcontrib><description>Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology.</description><identifier>ISSN: 1932-6203</identifier><identifier>EISSN: 1932-6203</identifier><identifier>DOI: 10.1371/journal.pone.0285996</identifier><identifier>PMID: 37200281</identifier><language>eng</language><publisher>United States: Public Library of Science</publisher><subject>Analysis ; Biology and Life Sciences ; Cancer ; Cancer screening ; Cellular biology ; Cervical cancer ; Clinical medicine ; Computational linguistics ; Computer and Information Sciences ; Cytology ; Deep Learning ; Diagnosis ; Early Detection of Cancer ; Female ; Histopathology ; Humans ; Image classification ; Language processing ; Lesions ; Low income groups ; Machine learning ; Medical diagnosis ; Medical imaging ; Medical screening ; Medicine and Health Sciences ; Model accuracy ; Model testing ; Modelling ; Natural language interfaces ; People and Places ; Reproducibility of Results ; Research and Analysis Methods ; Semi-supervised learning ; Social Sciences ; Squamous Intraepithelial Lesions ; Students ; Supervised Machine Learning ; Technology application ; Uterine Cervical Neoplasms - diagnostic imaging ; Uterine Cervical Neoplasms - pathology</subject><ispartof>PloS one, 2023-05, Vol.18 (5), p.e0285996-e0285996</ispartof><rights>Copyright: © 2023 Kurita et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.</rights><rights>COPYRIGHT 2023 Public Library of Science</rights><rights>2023 Kurita et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2023 Kurita et al 2023 Kurita et al</rights><rights>2023 Kurita et al. This is an open access article distributed under the terms of the Creative Commons Attribution License: http://creativecommons.org/licenses/by/4.0/ (the “License”), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. 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><citedby>FETCH-LOGICAL-c693t-ad6b4cb83c08a73e17f50e415763ff43c6c26b3d24fecd26defe10a5970cf8933</citedby><cites>FETCH-LOGICAL-c693t-ad6b4cb83c08a73e17f50e415763ff43c6c26b3d24fecd26defe10a5970cf8933</cites><orcidid>0009-0007-1927-9450 ; 0000-0002-8718-4599 ; 0000-0003-1920-4268</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10194854/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC10194854/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,860,881,2096,2915,23847,27903,27904,53769,53771,79346,79347</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/37200281$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><contributor>Giannini, Andrea</contributor><creatorcontrib>Kurita, Yuki</creatorcontrib><creatorcontrib>Meguro, Shiori</creatorcontrib><creatorcontrib>Tsuyama, Naoko</creatorcontrib><creatorcontrib>Kosugi, Isao</creatorcontrib><creatorcontrib>Enomoto, Yasunori</creatorcontrib><creatorcontrib>Kawasaki, Hideya</creatorcontrib><creatorcontrib>Uemura, Takashi</creatorcontrib><creatorcontrib>Kimura, Michio</creatorcontrib><creatorcontrib>Iwashita, Toshihide</creatorcontrib><title>Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images</title><title>PloS one</title><addtitle>PLoS One</addtitle><description>Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology.</description><subject>Analysis</subject><subject>Biology and Life Sciences</subject><subject>Cancer</subject><subject>Cancer screening</subject><subject>Cellular biology</subject><subject>Cervical cancer</subject><subject>Clinical medicine</subject><subject>Computational linguistics</subject><subject>Computer and Information Sciences</subject><subject>Cytology</subject><subject>Deep Learning</subject><subject>Diagnosis</subject><subject>Early Detection of Cancer</subject><subject>Female</subject><subject>Histopathology</subject><subject>Humans</subject><subject>Image classification</subject><subject>Language processing</subject><subject>Lesions</subject><subject>Low income groups</subject><subject>Machine learning</subject><subject>Medical diagnosis</subject><subject>Medical imaging</subject><subject>Medical screening</subject><subject>Medicine and Health Sciences</subject><subject>Model accuracy</subject><subject>Model testing</subject><subject>Modelling</subject><subject>Natural language interfaces</subject><subject>People and Places</subject><subject>Reproducibility of Results</subject><subject>Research and Analysis Methods</subject><subject>Semi-supervised learning</subject><subject>Social Sciences</subject><subject>Squamous Intraepithelial Lesions</subject><subject>Students</subject><subject>Supervised Machine Learning</subject><subject>Technology application</subject><subject>Uterine Cervical Neoplasms - diagnostic imaging</subject><subject>Uterine Cervical Neoplasms - pathology</subject><issn>1932-6203</issn><issn>1932-6203</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>BENPR</sourceid><sourceid>DOA</sourceid><recordid>eNqNk99u0zAUxiMEYmPwBggsISG4aLFjx0muUDXxp9LEJAbcWq593Lpy7c5OBnsCXhtnzUaLdoFykWPn9332OTmnKJ4TPCW0Ju_WoY9euuk2eJjisqnalj8ojklLywkvMX24Fx8VT1JaY1zRhvPHxRGtS5wl5Lj4PVOqj7IDpAG2yIGM3vol2gQNDvVpiBNs7CT1W4hXNoH-C0mv0Zdg0zW66HoNvkMmRKQGTkmHlPQ5RklFgBveeuTCT7SRS29NRjobPLJ5Celp8chIl-DZ-D4pvn_88O308-Ts_NP8dHY2Ubyl3URqvmBq0VCFG1lTILWpMDBS1Zwaw6jiquQLqktmQOmSazBAsKzaGivTtJSeFC93vlsXkhhrmESuRVXSjFWZmO8IHeRabGO-X7wWQVpxsxHiUsjYWeVAUNNopjireFMzTcumYU0NCwKtMSUYkr3ej6f1iw1olUsUpTswPfzi7Uosw5UgmLSsqVh2eDM6xHDZQ-rExiYFzkkPob-5OM-5U9xm9NU_6P3pjdRS5gysNyEfrAZTMatZW7OK8IGa3kPlR-deULnjjM37B4K3B4LMdPCrW8o-JTG_-Pr_7PmPQ_b1HrsC6bpVCq4fWicdgmwHqhhSimDuqkywGAbmthpiGBgxDkyWvdj_Q3ei2wmhfwCIbxLp</recordid><startdate>20230518</startdate><enddate>20230518</enddate><creator>Kurita, Yuki</creator><creator>Meguro, Shiori</creator><creator>Tsuyama, Naoko</creator><creator>Kosugi, Isao</creator><creator>Enomoto, Yasunori</creator><creator>Kawasaki, Hideya</creator><creator>Uemura, Takashi</creator><creator>Kimura, Michio</creator><creator>Iwashita, Toshihide</creator><general>Public Library of Science</general><general>Public Library of Science (PLoS)</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>IOV</scope><scope>ISR</scope><scope>3V.</scope><scope>7QG</scope><scope>7QL</scope><scope>7QO</scope><scope>7RV</scope><scope>7SN</scope><scope>7SS</scope><scope>7T5</scope><scope>7TG</scope><scope>7TM</scope><scope>7U9</scope><scope>7X2</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8AO</scope><scope>8C1</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FH</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AEUYN</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>H94</scope><scope>HCIFZ</scope><scope>K9.</scope><scope>KB.</scope><scope>KB0</scope><scope>KL.</scope><scope>L6V</scope><scope>LK8</scope><scope>M0K</scope><scope>M0S</scope><scope>M1P</scope><scope>M7N</scope><scope>M7P</scope><scope>M7S</scope><scope>NAPCQ</scope><scope>P5Z</scope><scope>P62</scope><scope>P64</scope><scope>PATMY</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>PYCSY</scope><scope>RC3</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0009-0007-1927-9450</orcidid><orcidid>https://orcid.org/0000-0002-8718-4599</orcidid><orcidid>https://orcid.org/0000-0003-1920-4268</orcidid></search><sort><creationdate>20230518</creationdate><title>Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images</title><author>Kurita, Yuki ; Meguro, Shiori ; Tsuyama, Naoko ; Kosugi, Isao ; Enomoto, Yasunori ; Kawasaki, Hideya ; Uemura, Takashi ; Kimura, Michio ; Iwashita, Toshihide</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c693t-ad6b4cb83c08a73e17f50e415763ff43c6c26b3d24fecd26defe10a5970cf8933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Analysis</topic><topic>Biology and Life Sciences</topic><topic>Cancer</topic><topic>Cancer screening</topic><topic>Cellular biology</topic><topic>Cervical cancer</topic><topic>Clinical medicine</topic><topic>Computational linguistics</topic><topic>Computer and Information Sciences</topic><topic>Cytology</topic><topic>Deep Learning</topic><topic>Diagnosis</topic><topic>Early Detection of Cancer</topic><topic>Female</topic><topic>Histopathology</topic><topic>Humans</topic><topic>Image classification</topic><topic>Language processing</topic><topic>Lesions</topic><topic>Low income groups</topic><topic>Machine learning</topic><topic>Medical diagnosis</topic><topic>Medical imaging</topic><topic>Medical screening</topic><topic>Medicine and Health Sciences</topic><topic>Model accuracy</topic><topic>Model testing</topic><topic>Modelling</topic><topic>Natural language interfaces</topic><topic>People and Places</topic><topic>Reproducibility of Results</topic><topic>Research and Analysis Methods</topic><topic>Semi-supervised learning</topic><topic>Social Sciences</topic><topic>Squamous Intraepithelial Lesions</topic><topic>Students</topic><topic>Supervised Machine Learning</topic><topic>Technology application</topic><topic>Uterine Cervical Neoplasms - diagnostic imaging</topic><topic>Uterine Cervical Neoplasms - pathology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kurita, Yuki</creatorcontrib><creatorcontrib>Meguro, Shiori</creatorcontrib><creatorcontrib>Tsuyama, Naoko</creatorcontrib><creatorcontrib>Kosugi, Isao</creatorcontrib><creatorcontrib>Enomoto, Yasunori</creatorcontrib><creatorcontrib>Kawasaki, Hideya</creatorcontrib><creatorcontrib>Uemura, Takashi</creatorcontrib><creatorcontrib>Kimura, Michio</creatorcontrib><creatorcontrib>Iwashita, Toshihide</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Gale In Context: Opposing Viewpoints</collection><collection>Gale In Context: Science</collection><collection>ProQuest Central (Corporate)</collection><collection>Animal Behavior Abstracts</collection><collection>Bacteriology Abstracts (Microbiology B)</collection><collection>Biotechnology Research Abstracts</collection><collection>Nursing & Allied Health Database</collection><collection>Ecology Abstracts</collection><collection>Entomology Abstracts (Full archive)</collection><collection>Immunology Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Nucleic Acids Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>Agricultural Science Collection</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>Public Health Database</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>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest One Sustainability</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>Agricultural & Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</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>AIDS and Cancer Research Abstracts</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Materials Science Database</collection><collection>Nursing & Allied Health Database (Alumni Edition)</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Agricultural Science Database</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Algology Mycology and Protozoology Abstracts (Microbiology C)</collection><collection>Biological Science Database</collection><collection>Engineering 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>Environmental Science Database</collection><collection>Materials Science 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>Engineering Collection</collection><collection>Environmental Science Collection</collection><collection>Genetics Abstracts</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>PloS one</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kurita, Yuki</au><au>Meguro, Shiori</au><au>Tsuyama, Naoko</au><au>Kosugi, Isao</au><au>Enomoto, Yasunori</au><au>Kawasaki, Hideya</au><au>Uemura, Takashi</au><au>Kimura, Michio</au><au>Iwashita, Toshihide</au><au>Giannini, Andrea</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images</atitle><jtitle>PloS one</jtitle><addtitle>PLoS One</addtitle><date>2023-05-18</date><risdate>2023</risdate><volume>18</volume><issue>5</issue><spage>e0285996</spage><epage>e0285996</epage><pages>e0285996-e0285996</pages><issn>1932-6203</issn><eissn>1932-6203</eissn><abstract>Deep learning technology has been used in the medical field to produce devices for clinical practice. Deep learning methods in cytology offer the potential to enhance cancer screening while also providing quantitative, objective, and highly reproducible testing. However, constructing high-accuracy deep learning models necessitates a significant amount of manually labeled data, which takes time. To address this issue, we used the Noisy Student Training technique to create a binary classification deep learning model for cervical cytology screening, which reduces the quantity of labeled data necessary. We used 140 whole-slide images from liquid-based cytology specimens, 50 of which were low-grade squamous intraepithelial lesions, 50 were high-grade squamous intraepithelial lesions, and 40 were negative samples. We extracted 56,996 images from the slides and then used them to train and test the model. We trained the EfficientNet using 2,600 manually labeled images to generate additional pseudo labels for the unlabeled data and then self-trained it within a student-teacher framework. Based on the presence or absence of abnormal cells, the created model was used to classify the images as normal or abnormal. The Grad-CAM approach was used to visualize the image components that contributed to the classification. The model achieved an area under the curve of 0.908, accuracy of 0.873, and F1-score of 0.833 with our test data. We also explored the optimal confidence threshold score and optimal augmentation approaches for low-magnification images. Our model efficiently classified normal and abnormal images at low magnification with high reliability, making it a promising screening tool for cervical cytology.</abstract><cop>United States</cop><pub>Public Library of Science</pub><pmid>37200281</pmid><doi>10.1371/journal.pone.0285996</doi><tpages>e0285996</tpages><orcidid>https://orcid.org/0009-0007-1927-9450</orcidid><orcidid>https://orcid.org/0000-0002-8718-4599</orcidid><orcidid>https://orcid.org/0000-0003-1920-4268</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1932-6203 |
ispartof | PloS one, 2023-05, Vol.18 (5), p.e0285996-e0285996 |
issn | 1932-6203 1932-6203 |
language | eng |
recordid | cdi_plos_journals_2815235975 |
source | Public Library of Science (PLoS) Journals Open Access; MEDLINE; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals; PubMed Central; Free Full-Text Journals in Chemistry |
subjects | Analysis Biology and Life Sciences Cancer Cancer screening Cellular biology Cervical cancer Clinical medicine Computational linguistics Computer and Information Sciences Cytology Deep Learning Diagnosis Early Detection of Cancer Female Histopathology Humans Image classification Language processing Lesions Low income groups Machine learning Medical diagnosis Medical imaging Medical screening Medicine and Health Sciences Model accuracy Model testing Modelling Natural language interfaces People and Places Reproducibility of Results Research and Analysis Methods Semi-supervised learning Social Sciences Squamous Intraepithelial Lesions Students Supervised Machine Learning Technology application Uterine Cervical Neoplasms - diagnostic imaging Uterine Cervical Neoplasms - pathology |
title | Accurate deep learning model using semi-supervised learning and Noisy Student for cervical cancer screening in low magnification images |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T16%3A05%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_plos_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accurate%20deep%20learning%20model%20using%20semi-supervised%20learning%20and%20Noisy%20Student%20for%20cervical%20cancer%20screening%20in%20low%20magnification%20images&rft.jtitle=PloS%20one&rft.au=Kurita,%20Yuki&rft.date=2023-05-18&rft.volume=18&rft.issue=5&rft.spage=e0285996&rft.epage=e0285996&rft.pages=e0285996-e0285996&rft.issn=1932-6203&rft.eissn=1932-6203&rft_id=info:doi/10.1371/journal.pone.0285996&rft_dat=%3Cgale_plos_%3EA749745165%3C/gale_plos_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2815235975&rft_id=info:pmid/37200281&rft_galeid=A749745165&rft_doaj_id=oai_doaj_org_article_3f8d4c6456874d3288487eb1e9ff2ef1&rfr_iscdi=true |