https://m2.mtmt.hu/ hun 2026-09-21 17:23 JournalArticle 36153385 VALIDATED true 0 false 2026-09-13T20:26:24.615+0000 2025-06-17T07:36:04.769+0000 2025-05-20T19:16:31.067+0000 true 10018804 Szalóky-Siki Ágnes /api/admin/10018804 Admin true 10018804 2026-01-02T00:42:00.857+0000 2025-06-12T07:11:07.485+0000 true 10080205 Szalóky-Siki Ágnes /api/admin/10080205 Admin true true false true 24 24 /api/publicationtype/24 PublicationType 1 true 24 JournalArticle true 10000059 Article true 24 24 /api/publicationtype/24 PublicationType 1 true 24 JournalArticle /api/subtype/10000059 Szakcikk SubType 101 true 10000059 true 1 /api/category/1 Category true 1 Palkovics, Daniel Automatic deep learning segmentation of mandibular periodontal bone topography on cone-beam computed tomography images. true true /api/journal/2417 REVIEWED true false 2417 false 2417 true 0300-5712 1879-176X Journal FOREIGN 159 105813 105813 10 2025 This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis.Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region.The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p<0.0001), 0.9232 (p<0.0001), and 0.9598(p<0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p<0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method.Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region.This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis. true true 2025 true true true false true false NONE 2026-09-13 false 8 0 8 7 1 8 8 7 8 8 8 7 7 7 1 0 8 7 8 7 0 2 2 Folyóiratcikk Journal Article 24 7 Könyvrészlet Chapter in Book 25 1 Könyv Book 23 0 Egyéb konferenciaközlemény Conference paper 31 0 Egyéb konferenciakötet Conference proceedings 32 0 Oltalmi formák Protection forms 26 0 Disszertáció Thesis 28 0 Egyéb Miscellaneous 29 0 Alkotás Achievement 22 0 Kutatási adat Research data 33 0 Folyóiratcikk Journal Article 24 0 0 0 Könyvrészlet Chapter in Book 25 0 0 0 Könyv Book 23 0 0 0 Egyéb konferenciaközlemény Conference paper 31 0 0 0 Egyéb konferenciakötet Conference proceedings 32 0 0 0 Oltalmi formák Protection forms 26 0 0 0 Disszertáció Thesis 28 0 0 0 Egyéb Miscellaneous 29 0 0 0 Alkotás Achievement 22 0 0 0 Kutatási adat Research data 33 0 0 0 2025 0 2 2 2 2 2026 0 6 5 6 5 D1 false false false false 2025-06-11T07:11:07.156+0000 Parodontológiai Klinika (SE / FOK) 3 10 1 7 0 true Language 10002 /api/language/10002 Angol English true 2 true PersonAuthorship 126632010 /api/authorship/126632010 1 0.143 true false true Author 10069847 /api/author/10069847 Palkovics Dániel true true Palkovics Daniel true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632011 /api/authorship/126632011 2 0.143 false false false Author 10018886 /api/author/10018886 Molnár Bálint true 10018886 true Molnar Balint true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632012 /api/authorship/126632012 3 0.14285715 false false false Pinter Csaba true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632013 /api/authorship/126632013 4 0.14285715 false false false García-Mato David true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632014 /api/authorship/126632014 5 0.14285715 false false false Diaz-Pinto Andres true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632015 /api/authorship/126632015 6 0.143 false false false Author 10018888 /api/author/10018888 Windisch Péter true 10018888 true Windisch Peter true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PersonAuthorship 126632016 /api/authorship/126632016 7 0.14285715 false true false Ramseier Christoph A true false false AuthorshipType 1 /api/authorshiptype/1 0 true 0 true false true PublicationIdentifier 29399843 /api/publicationidentifier/29399843 PlainSource 6 /api/publicationsource/6 PublicationSourceType 10001 /api/publicationsourcetype/10001 true true true DOI DOI https://doi.org/@@@ true true 6 true IDENTICAL 10.1016/j.jdent.2025.105813 https://doi.org/10.1016/j.jdent.2025.105813 false true PublicationIdentifier 29490874 /api/publicationidentifier/29490874 PlainSource 1 /api/publicationsource/1 PublicationSourceType 10003 /api/publicationsourcetype/10003 false true true WoS WoS https://www.webofscience.com/wos/woscc/full-record/@@@ true true 1 true IDENTICAL 001504609100002 https://www.webofscience.com/wos/woscc/full-record/001504609100002 true true PublicationIdentifier 29471057 /api/publicationidentifier/29471057 PlainSource 3 /api/publicationsource/3 PublicationSourceType 10003 /api/publicationsourcetype/10003 false true true Scopus Scopus http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-@@@ true true 3 true IDENTICAL 105006973951 http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-105006973951 false true PublicationIdentifier 29399842 /api/publicationidentifier/29399842 PlainSource 17 /api/publicationsource/17 PublicationSourceType 10003 /api/publicationsourcetype/10003 false true true PubMed PubMed http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=@@@&dopt=Abstract true true 17 true IDENTICAL 40373868 http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=40373868&dopt=Abstract false true Classification 12276 /api/classification/12276 true true Keyword 3693 /api/keyword/3693 true 3693 true Keyword 1011155 /api/keyword/1011155 true 1011155 true Keyword 1027009 /api/keyword/1027009 true 1027009 true Keyword 1078670 /api/keyword/1078670 true 1078670 true Keyword 1427322 /api/keyword/1427322 true 1427322 true Keyword 1438011 /api/keyword/1438011 true 1438011 true SjrRating 11572341 /api/sjrrating/11572341 6 0.1 journal RatingType 10002 /api/ratingtype/10002 sjr true true ClassificationExternal 3501 /api/classificationexternal/3501 true 3501 true D1 DIRECT true true /api/publication/36153385 <div class="JournalArticle Publication long-list"> <div class="authors"> <img title="Forrásközlemény" style="float: left" src="/frontend/resources/grid/publication-core-icon.png"> <img title="Idézőközlemény" style="float: left" src="/frontend/resources/grid/publication-citation-icon.png"> <div class="autype autype0"> <span class="author-name" mtid="10069847"><a href="/gui2/?type=authors&mode=browse&sel=10069847" target="_blank">Palkovics Daniel ✉ (<span class="authorship-author-name">Palkovics Dániel</span> <span class="authorAux-mtmt"> Parodontológia</span>) </a> </span> <span class="author-affil"><span title="Semmelweis Egyetem">SE</span>/<span title="Fogorvostudományi Kar">FOK</span>/Parodontológiai Klinika</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" mtid="10018886"><a href="/gui2/?type=authors&mode=browse&sel=10018886" target="_blank">Molnar Balint (<span class="authorship-author-name">Molnár Bálint</span> <span class="authorAux-mtmt"> Parodontológia</span>) </a> </span> <span class="author-affil"><span title="Semmelweis Egyetem">SE</span>/<span title="Fogorvostudományi Kar">FOK</span>/Parodontológiai Klinika</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" >Pinter Csaba </span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" >García-Mato David </span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" >Diaz-Pinto Andres </span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" mtid="10018888"><a href="/gui2/?type=authors&mode=browse&sel=10018888" target="_blank">Windisch Peter (<span class="authorship-author-name">Windisch Péter</span> <span class="authorAux-mtmt"> Parodontológia</span>) </a> </span> <span class="author-affil"><span title="Semmelweis Egyetem">SE</span>/<span title="Fogorvostudományi Kar">FOK</span>/Parodontológiai Klinika</span> ;&nbsp;&nbsp;&nbsp; <span class="author-name" >Ramseier Christoph A </span> </div> </div> <div class="title"><a href="/gui2/?mode=browse&params=publication;36153385" target="_blank">Automatic deep learning segmentation of mandibular periodontal bone topography on cone-beam computed tomography images.</a></div> <div> <span class="journal-title">JOURNAL OF DENTISTRY</span> <span class="journal-issn">(<a target="_blank" href="https://portal.issn.org/resource/ISSN/0300-5712">0300-5712</a> <a target="_blank" href="https://portal.issn.org/resource/ISSN/1879-176X">1879-176X</a>)</span>: <span class="journal-volume">159</span> <span class="page"> Paper 105813. 10 p. </span> <span class="year">(2025)</span> </div> <div class="pub-footer"> <span class="language" xmlns="http://www.w3.org/1999/html">Nyelv: Angol | </span> <span class="identifiers"> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="10.1016/j.jdent.2025.105813" target="_blank" href="https://doi.org/10.1016/j.jdent.2025.105813"> DOI </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="001504609100002" target="_blank" href="https://www.webofscience.com/wos/woscc/full-record/001504609100002"> WoS </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="105006973951" target="_blank" href="http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-105006973951"> Scopus </a> </span> <span class="id identifier oa_none" title="none"> <a style="color:blue" title="40373868" target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=PubMed&list_uids=40373868&dopt=Abstract"> PubMed </a> </span> </span> <OnlyViewableByAuthor><div class="ratings"> <div class="journal-subject">Folyóirat szakterülete: Scopus - Dentistry (miscellaneous)&nbsp;&nbsp;&nbsp;SJR indikátor:&nbsp;D1</div> </div></OnlyViewableByAuthor> <div class="publication-citation" style="margin-left: 0.5cm;"> <span title="Nyilvános idézőközlemények összesen, említések nélkül" class="citingPub-count">Nyilvános idéző összesen: 8</span> | Független: 7 | Függő: 1 | Nem jelölt: 0 | WoS jelölt: 7 | Scopus jelölt:&nbsp;8 | WoS/Scopus jelölt:&nbsp;8 | DOI jelölt:&nbsp;8 </div> <div class="publication-citation"> <a target="_blank" href="/api/publication?cond=citations.related;eq;36153385&sort=publishedYear,desc&sort=title"> Idézett közlemények száma: 2 </a> </div> <div class="mtid"><span class="long-pub-mtid">Közlemény: 36153385</span> | <span class="status-data status-VALIDATED"> Egyeztetett </span> Forrás Idéző | <span class="type-subtype">Folyóiratcikk ( Szakcikk ) </span> | <span class="pub-category">Tudományos</span> | <span class="publication-sourceOfData">kézi felvitel</span> </div> <div class="lastModified">Utolsó módosítás: 2025.06.17. 09:36 Szalóky-Siki Ágnes (SE_KK_Admin5_SZSA, admin) </div> </div></div>