Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification
The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification tas...
Gespeichert in:
Veröffentlicht in: | International journal of image, graphics and signal processing graphics and signal processing, 2022-10, Vol.14 (5), p.1-9 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 9 |
---|---|
container_issue | 5 |
container_start_page | 1 |
container_title | International journal of image, graphics and signal processing |
container_volume | 14 |
creator | Xu, Jiashu Stirenko, Sergii |
description | The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works. |
doi_str_mv | 10.5815/ijigsp.2022.05.01 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2798551940</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2798551940</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1831-3cc459f72f11861d19fb82bba6b3d9be21d9e96f0a57f04b08c4ebf43f749e353</originalsourceid><addsrcrecordid>eNo9kF1LwzAUhoMoOOZ-gHcBr1tz8tE2l7OoEzYEN69DkiaSWduarAP_vR0Tz8154H05Bx6EboHkogJxH_bhIw05JZTmROQELtCMkpJnklT08p9Lfo0WKe3JNIUAVvIZetu61mdpHFw8huQavOkb1-IHfeK-wxudPidajofedXbKYsLL5qg763C9w1uru4TrVqcUfLD6EPruBl153Sa3-Ntz9P70uKtX2fr1-aVerjMLFYOMWcuF9CX1AFUBDUhvKmqMLgxrpHEUGulk4YkWpSfckMpyZzxnvuTSMcHm6O58d4j99-jSQe37MXbTS0VLWQkBkpOpBeeWjX1K0Xk1xPCl448Cok721NmeOtlTRCgC7Ber5WOT</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2798551940</pqid></control><display><type>article</type><title>Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification</title><source>EZB-FREE-00999 freely available EZB journals</source><creator>Xu, Jiashu ; Stirenko, Sergii</creator><creatorcontrib>Xu, Jiashu ; Stirenko, Sergii ; National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, 03056, Ukraine</creatorcontrib><description>The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works.</description><identifier>ISSN: 2074-9074</identifier><identifier>EISSN: 2074-9082</identifier><identifier>DOI: 10.5815/ijigsp.2022.05.01</identifier><language>eng</language><publisher>Hong Kong: Modern Education and Computer Science Press</publisher><subject>Ablation ; Algorithms ; Classification ; Computed tomography ; Datasets ; Deep learning ; Machine learning ; Medical imaging ; Self-supervised learning ; Severe acute respiratory syndrome coronavirus 2 ; Viral diseases</subject><ispartof>International journal of image, graphics and signal processing, 2022-10, Vol.14 (5), p.1-9</ispartof><rights>2022. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at http://www.mecs-press.org/ijcnis/terms.html</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>314,776,780,27903,27904</link.rule.ids></links><search><creatorcontrib>Xu, Jiashu</creatorcontrib><creatorcontrib>Stirenko, Sergii</creatorcontrib><creatorcontrib>National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, 03056, Ukraine</creatorcontrib><title>Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification</title><title>International journal of image, graphics and signal processing</title><description>The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works.</description><subject>Ablation</subject><subject>Algorithms</subject><subject>Classification</subject><subject>Computed tomography</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Machine learning</subject><subject>Medical imaging</subject><subject>Self-supervised learning</subject><subject>Severe acute respiratory syndrome coronavirus 2</subject><subject>Viral diseases</subject><issn>2074-9074</issn><issn>2074-9082</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNo9kF1LwzAUhoMoOOZ-gHcBr1tz8tE2l7OoEzYEN69DkiaSWduarAP_vR0Tz8154H05Bx6EboHkogJxH_bhIw05JZTmROQELtCMkpJnklT08p9Lfo0WKe3JNIUAVvIZetu61mdpHFw8huQavOkb1-IHfeK-wxudPidajofedXbKYsLL5qg763C9w1uru4TrVqcUfLD6EPruBl153Sa3-Ntz9P70uKtX2fr1-aVerjMLFYOMWcuF9CX1AFUBDUhvKmqMLgxrpHEUGulk4YkWpSfckMpyZzxnvuTSMcHm6O58d4j99-jSQe37MXbTS0VLWQkBkpOpBeeWjX1K0Xk1xPCl448Cok721NmeOtlTRCgC7Ber5WOT</recordid><startdate>20221001</startdate><enddate>20221001</enddate><creator>Xu, Jiashu</creator><creator>Stirenko, Sergii</creator><general>Modern Education and Computer Science Press</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7XB</scope><scope>8AL</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>BVBZV</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>M0N</scope><scope>P5Z</scope><scope>P62</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope></search><sort><creationdate>20221001</creationdate><title>Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification</title><author>Xu, Jiashu ; Stirenko, Sergii</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1831-3cc459f72f11861d19fb82bba6b3d9be21d9e96f0a57f04b08c4ebf43f749e353</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Ablation</topic><topic>Algorithms</topic><topic>Classification</topic><topic>Computed tomography</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Machine learning</topic><topic>Medical imaging</topic><topic>Self-supervised learning</topic><topic>Severe acute respiratory syndrome coronavirus 2</topic><topic>Viral diseases</topic><toplevel>online_resources</toplevel><creatorcontrib>Xu, Jiashu</creatorcontrib><creatorcontrib>Stirenko, Sergii</creatorcontrib><creatorcontrib>National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, 03056, Ukraine</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Computing 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</collection><collection>East & South Asia Database</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</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>Computing Database</collection><collection>Advanced Technologies & Aerospace 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><jtitle>International journal of image, graphics and signal processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xu, Jiashu</au><au>Stirenko, Sergii</au><aucorp>National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Kyiv, 03056, Ukraine</aucorp><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification</atitle><jtitle>International journal of image, graphics and signal processing</jtitle><date>2022-10-01</date><risdate>2022</risdate><volume>14</volume><issue>5</issue><spage>1</spage><epage>9</epage><pages>1-9</pages><issn>2074-9074</issn><eissn>2074-9082</eissn><abstract>The coronavirus pandemic has been going on since the year 2019, and the trend is still not abating. Therefore, it is particularly important to classify medical CT scans to assist in medical diagnosis. At present, Supervised Deep Learning algorithms have made a great success in the classification task of medical CT scans, but medical image datasets often require professional image annotation, and many research datasets are not publicly available. To solve this problem, this paper is inspired by the self-supervised learning algorithm MAE and uses the MAE model pre-trained on ImageNet to perform transfer learning on CT Scans dataset. This method improves the generalization performance of the model and avoids the risk of overfitting on small datasets. Through extensive experiments on the COVID-CT dataset and the SARS-CoV-2 dataset, we compare the SSL-based method in this paper with other state-of-the-art supervised learning-based pretraining methods. Experimental results show that our method improves the generalization performance of the model more effectively and avoids the risk of overfitting on small datasets. The model achieved almost the same accuracy as supervised learning on both test datasets. Finally, ablation experiments aim to fully demonstrate the effectiveness of our method and how it works.</abstract><cop>Hong Kong</cop><pub>Modern Education and Computer Science Press</pub><doi>10.5815/ijigsp.2022.05.01</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2074-9074 |
ispartof | International journal of image, graphics and signal processing, 2022-10, Vol.14 (5), p.1-9 |
issn | 2074-9074 2074-9082 |
language | eng |
recordid | cdi_proquest_journals_2798551940 |
source | EZB-FREE-00999 freely available EZB journals |
subjects | Ablation Algorithms Classification Computed tomography Datasets Deep learning Machine learning Medical imaging Self-supervised learning Severe acute respiratory syndrome coronavirus 2 Viral diseases |
title | Self-supervised Model Based on Masked Autoencoders Advance CT Scans Classification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-22T04%3A45%3A31IST&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=Self-supervised%20Model%20Based%20on%20Masked%20Autoencoders%20Advance%20CT%20Scans%20Classification&rft.jtitle=International%20journal%20of%20image,%20graphics%20and%20signal%20processing&rft.au=Xu,%20Jiashu&rft.aucorp=National%20Technical%20University%20of%20Ukraine%20%E2%80%9CIgor%20Sikorsky%20Kyiv%20Polytechnic%20Institute%E2%80%9D,%20Kyiv,%2003056,%20Ukraine&rft.date=2022-10-01&rft.volume=14&rft.issue=5&rft.spage=1&rft.epage=9&rft.pages=1-9&rft.issn=2074-9074&rft.eissn=2074-9082&rft_id=info:doi/10.5815/ijigsp.2022.05.01&rft_dat=%3Cproquest_cross%3E2798551940%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=2798551940&rft_id=info:pmid/&rfr_iscdi=true |