Loading…

Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms

Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and met...

Full description

Saved in:
Bibliographic Details
Published in:Curēus (Palo Alto, CA) CA), 2024-05, Vol.16 (5), p.e60550
Main Authors: Yavuz, Muhammet Burak, Sali, Nichal, Kurt Bayrakdar, Sevda, Ekşi, Cemre, İmamoğlu, Büşra Seda, Bayrakdar, İbrahim Şevki, Çelik, Özer, Orhan, Kaan
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c300t-6844e086ab9da434a05c1ec5036c943d72b6916239f0a04e4ed7807bcd4f5ea13
container_end_page
container_issue 5
container_start_page e60550
container_title Curēus (Palo Alto, CA)
container_volume 16
creator Yavuz, Muhammet Burak
Sali, Nichal
Kurt Bayrakdar, Sevda
Ekşi, Cemre
İmamoğlu, Büşra Seda
Bayrakdar, İbrahim Şevki
Çelik, Özer
Orhan, Kaan
description Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and methods The sample of the study consisted of 1120 periapical radiographs (560 periodontally healthy, 560 periodontally unhealthy) and 1498 bitewing radiographs (749 periodontally healthy, 749 periodontally ill). From the main datasets of both radiography types, three sub-datasets were randomly created: a training set (80%), a validation set (10%), and a test set (10%). Using these sub-datasets, a deep learning algorithm was developed with the YOLOv8-cls model (Ultralytics, Los Angeles, California, United States) and trained over 300 epochs. The success of the developed algorithm was evaluated using the confusion matrix method. Results The AI algorithm achieved classification accuracies of 75% or higher for both radiograph types. For bitewing radiographs, the sensitivity, specificity, precision, accuracy, and F1 score values were 0.8243, 0.7162, 0.7439, 0.7703, and 0.7821, respectively. For periapical radiographs, the sensitivity, specificity, precision, accuracy, and F1 score were 0.7500, 0.7500, 0.7500, 0.7500, and 0.7500, respectively. Conclusion The AI models developed in this study demonstrated considerable success in classifying periodontal disease. Future applications may involve employing AI algorithms for assessing periodontal status across various types of radiography images and for automated disease detection.
doi_str_mv 10.7759/cureus.60550
format article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11181894</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3073831690</sourcerecordid><originalsourceid>FETCH-LOGICAL-c300t-6844e086ab9da434a05c1ec5036c943d72b6916239f0a04e4ed7807bcd4f5ea13</originalsourceid><addsrcrecordid>eNpdkU1vEzEQhi0EolXojTOyxIUDKeN4P7wnVNKWIkUCIThbs_Zs4sqxF3u3KP-e3aZUhdOMZh698_Ey9lrAeV2XzQczJhrzeQVlCc_Y6UpUaqmEKp4_yU_YWc63ACCgXkENL9mJVErVUspTdrf2mLPrnMHBxcBjx79RcthPBc8xWP7JDfTbhS3_jtbFbcJ-lznmeyzaGAb0_sBvCP2wO_CY-KXLhJksbw_8kqjnG8IUZoULv43JDbt9fsVedOgznT3EBft5ffVjfbPcfP38ZX2xWRoJMCwrVRQEqsK2sVjIAqE0gkwJsjJNIW29aqtGVCvZdIBQUEG2VlC3xhZdSSjkgn086vZjuydrKAwJve6T22M66IhO_9sJbqe38U4LIabfTTMW7N2DQoq_RsqD3rtsyHsMFMes5fTRupFKzsPe_ofexjGF6b6ZmpGqgYl6f6RMijkn6h63EaBnU_XRVH1v6oS_eXrBI_zXQvkHzFCf3w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3073831690</pqid></control><display><type>article</type><title>Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms</title><source>Publicly Available Content (ProQuest)</source><source>PubMed Central</source><creator>Yavuz, Muhammet Burak ; Sali, Nichal ; Kurt Bayrakdar, Sevda ; Ekşi, Cemre ; İmamoğlu, Büşra Seda ; Bayrakdar, İbrahim Şevki ; Çelik, Özer ; Orhan, Kaan</creator><creatorcontrib>Yavuz, Muhammet Burak ; Sali, Nichal ; Kurt Bayrakdar, Sevda ; Ekşi, Cemre ; İmamoğlu, Büşra Seda ; Bayrakdar, İbrahim Şevki ; Çelik, Özer ; Orhan, Kaan</creatorcontrib><description>Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and methods The sample of the study consisted of 1120 periapical radiographs (560 periodontally healthy, 560 periodontally unhealthy) and 1498 bitewing radiographs (749 periodontally healthy, 749 periodontally ill). From the main datasets of both radiography types, three sub-datasets were randomly created: a training set (80%), a validation set (10%), and a test set (10%). Using these sub-datasets, a deep learning algorithm was developed with the YOLOv8-cls model (Ultralytics, Los Angeles, California, United States) and trained over 300 epochs. The success of the developed algorithm was evaluated using the confusion matrix method. Results The AI algorithm achieved classification accuracies of 75% or higher for both radiograph types. For bitewing radiographs, the sensitivity, specificity, precision, accuracy, and F1 score values were 0.8243, 0.7162, 0.7439, 0.7703, and 0.7821, respectively. For periapical radiographs, the sensitivity, specificity, precision, accuracy, and F1 score were 0.7500, 0.7500, 0.7500, 0.7500, and 0.7500, respectively. Conclusion The AI models developed in this study demonstrated considerable success in classifying periodontal disease. Future applications may involve employing AI algorithms for assessing periodontal status across various types of radiography images and for automated disease detection.</description><identifier>ISSN: 2168-8184</identifier><identifier>EISSN: 2168-8184</identifier><identifier>DOI: 10.7759/cureus.60550</identifier><identifier>PMID: 38887333</identifier><language>eng</language><publisher>United States: Cureus Inc</publisher><subject>Accuracy ; Algorithms ; Artificial intelligence ; Classification ; Datasets ; Dental enamel ; Dentistry ; Gum disease ; Neural networks ; Performance evaluation ; Teeth</subject><ispartof>Curēus (Palo Alto, CA), 2024-05, Vol.16 (5), p.e60550</ispartof><rights>Copyright © 2024, Yavuz et al.</rights><rights>Copyright © 2024, Yavuz et al. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>Copyright © 2024, Yavuz et al. 2024 Yavuz et al.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c300t-6844e086ab9da434a05c1ec5036c943d72b6916239f0a04e4ed7807bcd4f5ea13</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/3073831690/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/3073831690?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>230,314,727,780,784,885,25753,27924,27925,37012,37013,44590,53791,53793,75126</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38887333$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yavuz, Muhammet Burak</creatorcontrib><creatorcontrib>Sali, Nichal</creatorcontrib><creatorcontrib>Kurt Bayrakdar, Sevda</creatorcontrib><creatorcontrib>Ekşi, Cemre</creatorcontrib><creatorcontrib>İmamoğlu, Büşra Seda</creatorcontrib><creatorcontrib>Bayrakdar, İbrahim Şevki</creatorcontrib><creatorcontrib>Çelik, Özer</creatorcontrib><creatorcontrib>Orhan, Kaan</creatorcontrib><title>Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms</title><title>Curēus (Palo Alto, CA)</title><addtitle>Cureus</addtitle><description>Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and methods The sample of the study consisted of 1120 periapical radiographs (560 periodontally healthy, 560 periodontally unhealthy) and 1498 bitewing radiographs (749 periodontally healthy, 749 periodontally ill). From the main datasets of both radiography types, three sub-datasets were randomly created: a training set (80%), a validation set (10%), and a test set (10%). Using these sub-datasets, a deep learning algorithm was developed with the YOLOv8-cls model (Ultralytics, Los Angeles, California, United States) and trained over 300 epochs. The success of the developed algorithm was evaluated using the confusion matrix method. Results The AI algorithm achieved classification accuracies of 75% or higher for both radiograph types. For bitewing radiographs, the sensitivity, specificity, precision, accuracy, and F1 score values were 0.8243, 0.7162, 0.7439, 0.7703, and 0.7821, respectively. For periapical radiographs, the sensitivity, specificity, precision, accuracy, and F1 score were 0.7500, 0.7500, 0.7500, 0.7500, and 0.7500, respectively. Conclusion The AI models developed in this study demonstrated considerable success in classifying periodontal disease. Future applications may involve employing AI algorithms for assessing periodontal status across various types of radiography images and for automated disease detection.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Classification</subject><subject>Datasets</subject><subject>Dental enamel</subject><subject>Dentistry</subject><subject>Gum disease</subject><subject>Neural networks</subject><subject>Performance evaluation</subject><subject>Teeth</subject><issn>2168-8184</issn><issn>2168-8184</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpdkU1vEzEQhi0EolXojTOyxIUDKeN4P7wnVNKWIkUCIThbs_Zs4sqxF3u3KP-e3aZUhdOMZh698_Ey9lrAeV2XzQczJhrzeQVlCc_Y6UpUaqmEKp4_yU_YWc63ACCgXkENL9mJVErVUspTdrf2mLPrnMHBxcBjx79RcthPBc8xWP7JDfTbhS3_jtbFbcJ-lznmeyzaGAb0_sBvCP2wO_CY-KXLhJksbw_8kqjnG8IUZoULv43JDbt9fsVedOgznT3EBft5ffVjfbPcfP38ZX2xWRoJMCwrVRQEqsK2sVjIAqE0gkwJsjJNIW29aqtGVCvZdIBQUEG2VlC3xhZdSSjkgn086vZjuydrKAwJve6T22M66IhO_9sJbqe38U4LIabfTTMW7N2DQoq_RsqD3rtsyHsMFMes5fTRupFKzsPe_ofexjGF6b6ZmpGqgYl6f6RMijkn6h63EaBnU_XRVH1v6oS_eXrBI_zXQvkHzFCf3w</recordid><startdate>20240518</startdate><enddate>20240518</enddate><creator>Yavuz, Muhammet Burak</creator><creator>Sali, Nichal</creator><creator>Kurt Bayrakdar, Sevda</creator><creator>Ekşi, Cemre</creator><creator>İmamoğlu, Büşra Seda</creator><creator>Bayrakdar, İbrahim Şevki</creator><creator>Çelik, Özer</creator><creator>Orhan, Kaan</creator><general>Cureus Inc</general><general>Cureus</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20240518</creationdate><title>Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms</title><author>Yavuz, Muhammet Burak ; Sali, Nichal ; Kurt Bayrakdar, Sevda ; Ekşi, Cemre ; İmamoğlu, Büşra Seda ; Bayrakdar, İbrahim Şevki ; Çelik, Özer ; Orhan, Kaan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c300t-6844e086ab9da434a05c1ec5036c943d72b6916239f0a04e4ed7807bcd4f5ea13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Classification</topic><topic>Datasets</topic><topic>Dental enamel</topic><topic>Dentistry</topic><topic>Gum disease</topic><topic>Neural networks</topic><topic>Performance evaluation</topic><topic>Teeth</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yavuz, Muhammet Burak</creatorcontrib><creatorcontrib>Sali, Nichal</creatorcontrib><creatorcontrib>Kurt Bayrakdar, Sevda</creatorcontrib><creatorcontrib>Ekşi, Cemre</creatorcontrib><creatorcontrib>İmamoğlu, Büşra Seda</creatorcontrib><creatorcontrib>Bayrakdar, İbrahim Şevki</creatorcontrib><creatorcontrib>Çelik, Özer</creatorcontrib><creatorcontrib>Orhan, Kaan</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Health and Medical</collection><collection>ProQuest Central (purchase pre-March 2016)</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)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>Publicly Available Content (ProQuest)</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>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Curēus (Palo Alto, CA)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yavuz, Muhammet Burak</au><au>Sali, Nichal</au><au>Kurt Bayrakdar, Sevda</au><au>Ekşi, Cemre</au><au>İmamoğlu, Büşra Seda</au><au>Bayrakdar, İbrahim Şevki</au><au>Çelik, Özer</au><au>Orhan, Kaan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms</atitle><jtitle>Curēus (Palo Alto, CA)</jtitle><addtitle>Cureus</addtitle><date>2024-05-18</date><risdate>2024</risdate><volume>16</volume><issue>5</issue><spage>e60550</spage><pages>e60550-</pages><issn>2168-8184</issn><eissn>2168-8184</eissn><abstract>Objectives The aim of this artificial intelligence (AI) study was to develop a deep learning algorithm capable of automatically classifying periapical and bitewing radiography images as either periodontally healthy or unhealthy and to assess the algorithm's diagnostic success. Materials and methods The sample of the study consisted of 1120 periapical radiographs (560 periodontally healthy, 560 periodontally unhealthy) and 1498 bitewing radiographs (749 periodontally healthy, 749 periodontally ill). From the main datasets of both radiography types, three sub-datasets were randomly created: a training set (80%), a validation set (10%), and a test set (10%). Using these sub-datasets, a deep learning algorithm was developed with the YOLOv8-cls model (Ultralytics, Los Angeles, California, United States) and trained over 300 epochs. The success of the developed algorithm was evaluated using the confusion matrix method. Results The AI algorithm achieved classification accuracies of 75% or higher for both radiograph types. For bitewing radiographs, the sensitivity, specificity, precision, accuracy, and F1 score values were 0.8243, 0.7162, 0.7439, 0.7703, and 0.7821, respectively. For periapical radiographs, the sensitivity, specificity, precision, accuracy, and F1 score were 0.7500, 0.7500, 0.7500, 0.7500, and 0.7500, respectively. Conclusion The AI models developed in this study demonstrated considerable success in classifying periodontal disease. Future applications may involve employing AI algorithms for assessing periodontal status across various types of radiography images and for automated disease detection.</abstract><cop>United States</cop><pub>Cureus Inc</pub><pmid>38887333</pmid><doi>10.7759/cureus.60550</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2168-8184
ispartof Curēus (Palo Alto, CA), 2024-05, Vol.16 (5), p.e60550
issn 2168-8184
2168-8184
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_11181894
source Publicly Available Content (ProQuest); PubMed Central
subjects Accuracy
Algorithms
Artificial intelligence
Classification
Datasets
Dental enamel
Dentistry
Gum disease
Neural networks
Performance evaluation
Teeth
title Classification of Periapical and Bitewing Radiographs as Periodontally Healthy or Diseased by Deep Learning Algorithms
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A22%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Classification%20of%20Periapical%20and%20Bitewing%20Radiographs%20as%20Periodontally%20Healthy%20or%20Diseased%20by%20Deep%20Learning%20Algorithms&rft.jtitle=Cur%C4%93us%20(Palo%20Alto,%20CA)&rft.au=Yavuz,%20Muhammet%20Burak&rft.date=2024-05-18&rft.volume=16&rft.issue=5&rft.spage=e60550&rft.pages=e60550-&rft.issn=2168-8184&rft.eissn=2168-8184&rft_id=info:doi/10.7759/cureus.60550&rft_dat=%3Cproquest_pubme%3E3073831690%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c300t-6844e086ab9da434a05c1ec5036c943d72b6916239f0a04e4ed7807bcd4f5ea13%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3073831690&rft_id=info:pmid/38887333&rfr_iscdi=true