Multi-Class Classification of Lung Diseases Using CNN Models

In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang U...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied sciences 2021-10, Vol.11 (19), p.9289
Hauptverfasser: Hong, Min, Rim, Beanbonyka, Lee, Hongchang, Jang, Hyeonung, Oh, Joonho, Choi, Seongjun
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 19
container_start_page 9289
container_title Applied sciences
container_volume 11
creator Hong, Min
Rim, Beanbonyka
Lee, Hongchang
Jang, Hyeonung
Oh, Joonho
Choi, Seongjun
description In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang University Hospital dataset including Tuberculosis were used. To improve performance, preprocessing was performed with Center Crop while maintaining the aspect ratio of 1:1. As a Noisy Student of EfficientNet B7, fine-tuning learning was performed using the weights learned from ImageNet, and the features of each layer were maximally utilized using the Multi GAP structure. As a result of the experiment, Benchmarks measured with the NIH dataset showed the highest performance among the tested models with an accuracy of 85.32%, and the four-class predictions measured with data from Soonchunhyang University Hospital in Cheonan had an average accuracy of 96.1%, an average sensitivity of 92.2%, an average specificity of 97.4%, and an average inference time of 0.2 s.
doi_str_mv 10.3390/app11199289
format Article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_crossref_primary_10_3390_app11199289</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_5592ace0c3134993b04f050ee74dc9bf</doaj_id><sourcerecordid>2580965305</sourcerecordid><originalsourceid>FETCH-LOGICAL-c364t-4e09ca74e7aeeb8658edbb733c0339d7345c2428bc216fba6033f31d62cc9563</originalsourceid><addsrcrecordid>eNpNUMtKw0AUHUTBUrvyBwIuJTrvZMCNxFchrZu6HiaTO2VK7MSZZOHfG1uR3sV9HA7nHg5C1wTfMabwvel7QohStFRnaEZxIXPGSXF-sl-iRUo7PJUirCR4hh5WYzf4vOpMStmhe-etGXzYZ8Fl9bjfZk8-gUmQso_kp7Nar7NVaKFLV-jCmS7B4m_O0ebleVO95fX767J6rHPLJB9yDlhZU3AoDEBTSlFC2zQFYxZPxtuCcWEpp2VjKZGuMXKCHSOtpNYqIdkcLY-ybTA73Uf_aeK3DsbrAxDiVps4eNuBFkJRYwFbRhhXijWYOywwQMFbqxo3ad0ctfoYvkZIg96FMe4n95qKEispGBYT6_bIsjGkFMH9fyVY_4atT8JmP0lJb14</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2580965305</pqid></control><display><type>article</type><title>Multi-Class Classification of Lung Diseases Using CNN Models</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Directory of Open Access Journals</source><source>EZB Electronic Journals Library</source><creator>Hong, Min ; Rim, Beanbonyka ; Lee, Hongchang ; Jang, Hyeonung ; Oh, Joonho ; Choi, Seongjun</creator><creatorcontrib>Hong, Min ; Rim, Beanbonyka ; Lee, Hongchang ; Jang, Hyeonung ; Oh, Joonho ; Choi, Seongjun</creatorcontrib><description>In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang University Hospital dataset including Tuberculosis were used. To improve performance, preprocessing was performed with Center Crop while maintaining the aspect ratio of 1:1. As a Noisy Student of EfficientNet B7, fine-tuning learning was performed using the weights learned from ImageNet, and the features of each layer were maximally utilized using the Multi GAP structure. As a result of the experiment, Benchmarks measured with the NIH dataset showed the highest performance among the tested models with an accuracy of 85.32%, and the four-class predictions measured with data from Soonchunhyang University Hospital in Cheonan had an average accuracy of 96.1%, an average sensitivity of 92.2%, an average specificity of 97.4%, and an average inference time of 0.2 s.</description><identifier>ISSN: 2076-3417</identifier><identifier>EISSN: 2076-3417</identifier><identifier>DOI: 10.3390/app11199289</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Bacterial infections ; Benchmarks ; Classification ; Coronaviruses ; COVID-19 ; Datasets ; Deep learning ; efficientnet ; Fever ; Image classification ; Learning ; Lung diseases ; Lungs ; Medical imaging ; multi-class classification ; Neural networks ; Pain ; Pneumonia ; Pneumothorax ; Tuberculosis</subject><ispartof>Applied sciences, 2021-10, Vol.11 (19), p.9289</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). 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-c364t-4e09ca74e7aeeb8658edbb733c0339d7345c2428bc216fba6033f31d62cc9563</citedby><cites>FETCH-LOGICAL-c364t-4e09ca74e7aeeb8658edbb733c0339d7345c2428bc216fba6033f31d62cc9563</cites><orcidid>0000-0001-9963-5521 ; 0000-0002-3517-6175 ; 0000-0003-1232-0610</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,864,2102,27924,27925</link.rule.ids></links><search><creatorcontrib>Hong, Min</creatorcontrib><creatorcontrib>Rim, Beanbonyka</creatorcontrib><creatorcontrib>Lee, Hongchang</creatorcontrib><creatorcontrib>Jang, Hyeonung</creatorcontrib><creatorcontrib>Oh, Joonho</creatorcontrib><creatorcontrib>Choi, Seongjun</creatorcontrib><title>Multi-Class Classification of Lung Diseases Using CNN Models</title><title>Applied sciences</title><description>In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang University Hospital dataset including Tuberculosis were used. To improve performance, preprocessing was performed with Center Crop while maintaining the aspect ratio of 1:1. As a Noisy Student of EfficientNet B7, fine-tuning learning was performed using the weights learned from ImageNet, and the features of each layer were maximally utilized using the Multi GAP structure. As a result of the experiment, Benchmarks measured with the NIH dataset showed the highest performance among the tested models with an accuracy of 85.32%, and the four-class predictions measured with data from Soonchunhyang University Hospital in Cheonan had an average accuracy of 96.1%, an average sensitivity of 92.2%, an average specificity of 97.4%, and an average inference time of 0.2 s.</description><subject>Accuracy</subject><subject>Bacterial infections</subject><subject>Benchmarks</subject><subject>Classification</subject><subject>Coronaviruses</subject><subject>COVID-19</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>efficientnet</subject><subject>Fever</subject><subject>Image classification</subject><subject>Learning</subject><subject>Lung diseases</subject><subject>Lungs</subject><subject>Medical imaging</subject><subject>multi-class classification</subject><subject>Neural networks</subject><subject>Pain</subject><subject>Pneumonia</subject><subject>Pneumothorax</subject><subject>Tuberculosis</subject><issn>2076-3417</issn><issn>2076-3417</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>DOA</sourceid><recordid>eNpNUMtKw0AUHUTBUrvyBwIuJTrvZMCNxFchrZu6HiaTO2VK7MSZZOHfG1uR3sV9HA7nHg5C1wTfMabwvel7QohStFRnaEZxIXPGSXF-sl-iRUo7PJUirCR4hh5WYzf4vOpMStmhe-etGXzYZ8Fl9bjfZk8-gUmQso_kp7Nar7NVaKFLV-jCmS7B4m_O0ebleVO95fX767J6rHPLJB9yDlhZU3AoDEBTSlFC2zQFYxZPxtuCcWEpp2VjKZGuMXKCHSOtpNYqIdkcLY-ybTA73Uf_aeK3DsbrAxDiVps4eNuBFkJRYwFbRhhXijWYOywwQMFbqxo3ad0ctfoYvkZIg96FMe4n95qKEispGBYT6_bIsjGkFMH9fyVY_4atT8JmP0lJb14</recordid><startdate>20211001</startdate><enddate>20211001</enddate><creator>Hong, Min</creator><creator>Rim, Beanbonyka</creator><creator>Lee, Hongchang</creator><creator>Jang, Hyeonung</creator><creator>Oh, Joonho</creator><creator>Choi, Seongjun</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>COVID</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0001-9963-5521</orcidid><orcidid>https://orcid.org/0000-0002-3517-6175</orcidid><orcidid>https://orcid.org/0000-0003-1232-0610</orcidid></search><sort><creationdate>20211001</creationdate><title>Multi-Class Classification of Lung Diseases Using CNN Models</title><author>Hong, Min ; Rim, Beanbonyka ; Lee, Hongchang ; Jang, Hyeonung ; Oh, Joonho ; Choi, Seongjun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c364t-4e09ca74e7aeeb8658edbb733c0339d7345c2428bc216fba6033f31d62cc9563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Bacterial infections</topic><topic>Benchmarks</topic><topic>Classification</topic><topic>Coronaviruses</topic><topic>COVID-19</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>efficientnet</topic><topic>Fever</topic><topic>Image classification</topic><topic>Learning</topic><topic>Lung diseases</topic><topic>Lungs</topic><topic>Medical imaging</topic><topic>multi-class classification</topic><topic>Neural networks</topic><topic>Pain</topic><topic>Pneumonia</topic><topic>Pneumothorax</topic><topic>Tuberculosis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Hong, Min</creatorcontrib><creatorcontrib>Rim, Beanbonyka</creatorcontrib><creatorcontrib>Lee, Hongchang</creatorcontrib><creatorcontrib>Jang, Hyeonung</creatorcontrib><creatorcontrib>Oh, Joonho</creatorcontrib><creatorcontrib>Choi, Seongjun</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>Coronavirus Research Database</collection><collection>ProQuest Central</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>Directory of Open Access Journals</collection><jtitle>Applied sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Hong, Min</au><au>Rim, Beanbonyka</au><au>Lee, Hongchang</au><au>Jang, Hyeonung</au><au>Oh, Joonho</au><au>Choi, Seongjun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-Class Classification of Lung Diseases Using CNN Models</atitle><jtitle>Applied sciences</jtitle><date>2021-10-01</date><risdate>2021</risdate><volume>11</volume><issue>19</issue><spage>9289</spage><pages>9289-</pages><issn>2076-3417</issn><eissn>2076-3417</eissn><abstract>In this study, we propose a multi-class classification method by learning lung disease images with Convolutional Neural Network (CNN). As the image data for learning, the U.S. National Institutes of Health (NIH) dataset divided into Normal, Pneumonia, and Pneumothorax and the Cheonan Soonchunhyang University Hospital dataset including Tuberculosis were used. To improve performance, preprocessing was performed with Center Crop while maintaining the aspect ratio of 1:1. As a Noisy Student of EfficientNet B7, fine-tuning learning was performed using the weights learned from ImageNet, and the features of each layer were maximally utilized using the Multi GAP structure. As a result of the experiment, Benchmarks measured with the NIH dataset showed the highest performance among the tested models with an accuracy of 85.32%, and the four-class predictions measured with data from Soonchunhyang University Hospital in Cheonan had an average accuracy of 96.1%, an average sensitivity of 92.2%, an average specificity of 97.4%, and an average inference time of 0.2 s.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/app11199289</doi><orcidid>https://orcid.org/0000-0001-9963-5521</orcidid><orcidid>https://orcid.org/0000-0002-3517-6175</orcidid><orcidid>https://orcid.org/0000-0003-1232-0610</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2076-3417
ispartof Applied sciences, 2021-10, Vol.11 (19), p.9289
issn 2076-3417
2076-3417
language eng
recordid cdi_crossref_primary_10_3390_app11199289
source MDPI - Multidisciplinary Digital Publishing Institute; Directory of Open Access Journals; EZB Electronic Journals Library
subjects Accuracy
Bacterial infections
Benchmarks
Classification
Coronaviruses
COVID-19
Datasets
Deep learning
efficientnet
Fever
Image classification
Learning
Lung diseases
Lungs
Medical imaging
multi-class classification
Neural networks
Pain
Pneumonia
Pneumothorax
Tuberculosis
title Multi-Class Classification of Lung Diseases Using CNN Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A10%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-Class%20Classification%20of%20Lung%20Diseases%20Using%20CNN%20Models&rft.jtitle=Applied%20sciences&rft.au=Hong,%20Min&rft.date=2021-10-01&rft.volume=11&rft.issue=19&rft.spage=9289&rft.pages=9289-&rft.issn=2076-3417&rft.eissn=2076-3417&rft_id=info:doi/10.3390/app11199289&rft_dat=%3Cproquest_doaj_%3E2580965305%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2580965305&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_5592ace0c3134993b04f050ee74dc9bf&rfr_iscdi=true