Classification of large-scale image database of various skin diseases using deep learning

Purpose The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in high...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal for computer assisted radiology and surgery 2021-11, Vol.16 (11), p.1875-1887
Hauptverfasser: Tanaka, Masaya, Saito, Atsushi, Shido, Kosuke, Fujisawa, Yasuhiro, Yamasaki, Kenshi, Fujimoto, Manabu, Murao, Kohei, Ninomiya, Youichirou, Satoh, Shin’ichi, Shimizu, Akinobu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1887
container_issue 11
container_start_page 1875
container_title International journal for computer assisted radiology and surgery
container_volume 16
creator Tanaka, Masaya
Saito, Atsushi
Shido, Kosuke
Fujisawa, Yasuhiro
Yamasaki, Kenshi
Fujimoto, Manabu
Murao, Kohei
Ninomiya, Youichirou
Satoh, Shin’ichi
Shimizu, Akinobu
description Purpose The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in highly diverse images in terms of the appearance of the diseases or photographic conditions. Methods ResNet-18 is used as a baseline model for classification and is reinforced by metric learning to boost generalization in classification by avoiding the overfitting of the training data and increasing the reliability of CADx for dermatologists. Patient-wise classification is performed by aggregating the inference vectors of all the input patient images. Results The experiment using 70,196 images of 13,038 patients demonstrated that classification accuracy was significantly improved by both metric learning and aggregation, resulting in patient accuracies of 0.579 for Top-1, 0.793 for Top-3, and 0.863 for Top-5. The McNemar test showed that the improvements achieved by the proposed method were statistically significant. Conclusion This study presents a deep learning-based classification of 59 skin diseases using multiple photographic images of a patient. The experimental results demonstrated that the proposed classification reinforced by metric learning and aggregation of multiple input images was effective in the classification of patients with diverse skin diseases and imaging conditions.
doi_str_mv 10.1007/s11548-021-02440-y
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2555346872</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2555346872</sourcerecordid><originalsourceid>FETCH-LOGICAL-c418t-57b2aa4ff6b4f78c83b93967cb13fae8ec171d079e821e2a7719c8b7bad3c7313</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhosouK7-AU8BL16qSZM26VEWv2DBix48hWk6LVm77Zpphf33Zl1R8OAhJDN53mF4kuRc8CvBub4mIXJlUp6JeJTi6fYgmQlTiLRQWXn48xb8ODkhWnGuci3zWfK66IDIN97B6IeeDQ3rILSYkoMOmV9Di6yGESog3P1-QPDDRIzefM9qTxj7xCbyfctqxA3rEEIfq9PkqIGO8Oz7nicvd7fPi4d0-XT_uLhZpk4JM6a5rjIA1TRFpRptnJFVKctCu0rIBtCgE1rUXJdoMoEZaC1KZypdQS2dlkLOk8v93E0Y3iek0a49Oew66DEuarM8z6UqjM4ievEHXQ1T6ON2kSqLMueqNJHK9pQLA1HAxm5C9BC2VnC7s233tm20bb9s220MyX2IIty3GH5H_5P6BBNJg0E</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2596950498</pqid></control><display><type>article</type><title>Classification of large-scale image database of various skin diseases using deep learning</title><source>SpringerNature Journals</source><creator>Tanaka, Masaya ; Saito, Atsushi ; Shido, Kosuke ; Fujisawa, Yasuhiro ; Yamasaki, Kenshi ; Fujimoto, Manabu ; Murao, Kohei ; Ninomiya, Youichirou ; Satoh, Shin’ichi ; Shimizu, Akinobu</creator><creatorcontrib>Tanaka, Masaya ; Saito, Atsushi ; Shido, Kosuke ; Fujisawa, Yasuhiro ; Yamasaki, Kenshi ; Fujimoto, Manabu ; Murao, Kohei ; Ninomiya, Youichirou ; Satoh, Shin’ichi ; Shimizu, Akinobu</creatorcontrib><description>Purpose The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in highly diverse images in terms of the appearance of the diseases or photographic conditions. Methods ResNet-18 is used as a baseline model for classification and is reinforced by metric learning to boost generalization in classification by avoiding the overfitting of the training data and increasing the reliability of CADx for dermatologists. Patient-wise classification is performed by aggregating the inference vectors of all the input patient images. Results The experiment using 70,196 images of 13,038 patients demonstrated that classification accuracy was significantly improved by both metric learning and aggregation, resulting in patient accuracies of 0.579 for Top-1, 0.793 for Top-3, and 0.863 for Top-5. The McNemar test showed that the improvements achieved by the proposed method were statistically significant. Conclusion This study presents a deep learning-based classification of 59 skin diseases using multiple photographic images of a patient. The experimental results demonstrated that the proposed classification reinforced by metric learning and aggregation of multiple input images was effective in the classification of patients with diverse skin diseases and imaging conditions.</description><identifier>ISSN: 1861-6410</identifier><identifier>EISSN: 1861-6429</identifier><identifier>DOI: 10.1007/s11548-021-02440-y</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Accuracy ; Agglomeration ; CAI ; Classification ; Computer assisted instruction ; Computer Imaging ; Computer Science ; Deep learning ; Health Informatics ; Image classification ; Imaging ; Machine learning ; Medical imaging ; Medicine ; Medicine &amp; Public Health ; Original Article ; Patients ; Pattern Recognition and Graphics ; Radiology ; Skin diseases ; Surgery ; Vision</subject><ispartof>International journal for computer assisted radiology and surgery, 2021-11, Vol.16 (11), p.1875-1887</ispartof><rights>CARS 2021. corrected publication 2021</rights><rights>CARS 2021. corrected publication 2021.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c418t-57b2aa4ff6b4f78c83b93967cb13fae8ec171d079e821e2a7719c8b7bad3c7313</citedby><cites>FETCH-LOGICAL-c418t-57b2aa4ff6b4f78c83b93967cb13fae8ec171d079e821e2a7719c8b7bad3c7313</cites><orcidid>0000-0002-2719-5923</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11548-021-02440-y$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11548-021-02440-y$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Tanaka, Masaya</creatorcontrib><creatorcontrib>Saito, Atsushi</creatorcontrib><creatorcontrib>Shido, Kosuke</creatorcontrib><creatorcontrib>Fujisawa, Yasuhiro</creatorcontrib><creatorcontrib>Yamasaki, Kenshi</creatorcontrib><creatorcontrib>Fujimoto, Manabu</creatorcontrib><creatorcontrib>Murao, Kohei</creatorcontrib><creatorcontrib>Ninomiya, Youichirou</creatorcontrib><creatorcontrib>Satoh, Shin’ichi</creatorcontrib><creatorcontrib>Shimizu, Akinobu</creatorcontrib><title>Classification of large-scale image database of various skin diseases using deep learning</title><title>International journal for computer assisted radiology and surgery</title><addtitle>Int J CARS</addtitle><description>Purpose The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in highly diverse images in terms of the appearance of the diseases or photographic conditions. Methods ResNet-18 is used as a baseline model for classification and is reinforced by metric learning to boost generalization in classification by avoiding the overfitting of the training data and increasing the reliability of CADx for dermatologists. Patient-wise classification is performed by aggregating the inference vectors of all the input patient images. Results The experiment using 70,196 images of 13,038 patients demonstrated that classification accuracy was significantly improved by both metric learning and aggregation, resulting in patient accuracies of 0.579 for Top-1, 0.793 for Top-3, and 0.863 for Top-5. The McNemar test showed that the improvements achieved by the proposed method were statistically significant. Conclusion This study presents a deep learning-based classification of 59 skin diseases using multiple photographic images of a patient. The experimental results demonstrated that the proposed classification reinforced by metric learning and aggregation of multiple input images was effective in the classification of patients with diverse skin diseases and imaging conditions.</description><subject>Accuracy</subject><subject>Agglomeration</subject><subject>CAI</subject><subject>Classification</subject><subject>Computer assisted instruction</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Deep learning</subject><subject>Health Informatics</subject><subject>Image classification</subject><subject>Imaging</subject><subject>Machine learning</subject><subject>Medical imaging</subject><subject>Medicine</subject><subject>Medicine &amp; Public Health</subject><subject>Original Article</subject><subject>Patients</subject><subject>Pattern Recognition and Graphics</subject><subject>Radiology</subject><subject>Skin diseases</subject><subject>Surgery</subject><subject>Vision</subject><issn>1861-6410</issn><issn>1861-6429</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LxDAQhosouK7-AU8BL16qSZM26VEWv2DBix48hWk6LVm77Zpphf33Zl1R8OAhJDN53mF4kuRc8CvBub4mIXJlUp6JeJTi6fYgmQlTiLRQWXn48xb8ODkhWnGuci3zWfK66IDIN97B6IeeDQ3rILSYkoMOmV9Di6yGESog3P1-QPDDRIzefM9qTxj7xCbyfctqxA3rEEIfq9PkqIGO8Oz7nicvd7fPi4d0-XT_uLhZpk4JM6a5rjIA1TRFpRptnJFVKctCu0rIBtCgE1rUXJdoMoEZaC1KZypdQS2dlkLOk8v93E0Y3iek0a49Oew66DEuarM8z6UqjM4ievEHXQ1T6ON2kSqLMueqNJHK9pQLA1HAxm5C9BC2VnC7s233tm20bb9s220MyX2IIty3GH5H_5P6BBNJg0E</recordid><startdate>20211101</startdate><enddate>20211101</enddate><creator>Tanaka, Masaya</creator><creator>Saito, Atsushi</creator><creator>Shido, Kosuke</creator><creator>Fujisawa, Yasuhiro</creator><creator>Yamasaki, Kenshi</creator><creator>Fujimoto, Manabu</creator><creator>Murao, Kohei</creator><creator>Ninomiya, Youichirou</creator><creator>Satoh, Shin’ichi</creator><creator>Shimizu, Akinobu</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-2719-5923</orcidid></search><sort><creationdate>20211101</creationdate><title>Classification of large-scale image database of various skin diseases using deep learning</title><author>Tanaka, Masaya ; Saito, Atsushi ; Shido, Kosuke ; Fujisawa, Yasuhiro ; Yamasaki, Kenshi ; Fujimoto, Manabu ; Murao, Kohei ; Ninomiya, Youichirou ; Satoh, Shin’ichi ; Shimizu, Akinobu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c418t-57b2aa4ff6b4f78c83b93967cb13fae8ec171d079e821e2a7719c8b7bad3c7313</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Agglomeration</topic><topic>CAI</topic><topic>Classification</topic><topic>Computer assisted instruction</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Deep learning</topic><topic>Health Informatics</topic><topic>Image classification</topic><topic>Imaging</topic><topic>Machine learning</topic><topic>Medical imaging</topic><topic>Medicine</topic><topic>Medicine &amp; Public Health</topic><topic>Original Article</topic><topic>Patients</topic><topic>Pattern Recognition and Graphics</topic><topic>Radiology</topic><topic>Skin diseases</topic><topic>Surgery</topic><topic>Vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tanaka, Masaya</creatorcontrib><creatorcontrib>Saito, Atsushi</creatorcontrib><creatorcontrib>Shido, Kosuke</creatorcontrib><creatorcontrib>Fujisawa, Yasuhiro</creatorcontrib><creatorcontrib>Yamasaki, Kenshi</creatorcontrib><creatorcontrib>Fujimoto, Manabu</creatorcontrib><creatorcontrib>Murao, Kohei</creatorcontrib><creatorcontrib>Ninomiya, Youichirou</creatorcontrib><creatorcontrib>Satoh, Shin’ichi</creatorcontrib><creatorcontrib>Shimizu, Akinobu</creatorcontrib><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>International journal for computer assisted radiology and surgery</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tanaka, Masaya</au><au>Saito, Atsushi</au><au>Shido, Kosuke</au><au>Fujisawa, Yasuhiro</au><au>Yamasaki, Kenshi</au><au>Fujimoto, Manabu</au><au>Murao, Kohei</au><au>Ninomiya, Youichirou</au><au>Satoh, Shin’ichi</au><au>Shimizu, Akinobu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classification of large-scale image database of various skin diseases using deep learning</atitle><jtitle>International journal for computer assisted radiology and surgery</jtitle><stitle>Int J CARS</stitle><date>2021-11-01</date><risdate>2021</risdate><volume>16</volume><issue>11</issue><spage>1875</spage><epage>1887</epage><pages>1875-1887</pages><issn>1861-6410</issn><eissn>1861-6429</eissn><abstract>Purpose The purpose of this study was to develop a deep learning-based computer-aided diagnosis system for skin disease classification using photographic images of patients. The targets are 59 skin diseases, including localized and diffuse diseases captured by photographic cameras, resulting in highly diverse images in terms of the appearance of the diseases or photographic conditions. Methods ResNet-18 is used as a baseline model for classification and is reinforced by metric learning to boost generalization in classification by avoiding the overfitting of the training data and increasing the reliability of CADx for dermatologists. Patient-wise classification is performed by aggregating the inference vectors of all the input patient images. Results The experiment using 70,196 images of 13,038 patients demonstrated that classification accuracy was significantly improved by both metric learning and aggregation, resulting in patient accuracies of 0.579 for Top-1, 0.793 for Top-3, and 0.863 for Top-5. The McNemar test showed that the improvements achieved by the proposed method were statistically significant. Conclusion This study presents a deep learning-based classification of 59 skin diseases using multiple photographic images of a patient. The experimental results demonstrated that the proposed classification reinforced by metric learning and aggregation of multiple input images was effective in the classification of patients with diverse skin diseases and imaging conditions.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><doi>10.1007/s11548-021-02440-y</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0002-2719-5923</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1861-6410
ispartof International journal for computer assisted radiology and surgery, 2021-11, Vol.16 (11), p.1875-1887
issn 1861-6410
1861-6429
language eng
recordid cdi_proquest_miscellaneous_2555346872
source SpringerNature Journals
subjects Accuracy
Agglomeration
CAI
Classification
Computer assisted instruction
Computer Imaging
Computer Science
Deep learning
Health Informatics
Image classification
Imaging
Machine learning
Medical imaging
Medicine
Medicine & Public Health
Original Article
Patients
Pattern Recognition and Graphics
Radiology
Skin diseases
Surgery
Vision
title Classification of large-scale image database of various skin diseases using deep learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T18%3A51%3A19IST&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=Classification%20of%20large-scale%20image%20database%20of%20various%20skin%20diseases%20using%20deep%20learning&rft.jtitle=International%20journal%20for%20computer%20assisted%20radiology%20and%20surgery&rft.au=Tanaka,%20Masaya&rft.date=2021-11-01&rft.volume=16&rft.issue=11&rft.spage=1875&rft.epage=1887&rft.pages=1875-1887&rft.issn=1861-6410&rft.eissn=1861-6429&rft_id=info:doi/10.1007/s11548-021-02440-y&rft_dat=%3Cproquest_cross%3E2555346872%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=2596950498&rft_id=info:pmid/&rfr_iscdi=true