Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks
To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images. After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed o...
Gespeichert in:
| Veröffentlicht in: | Journal of dentistry 2022-07, Vol.122, p.104139-104139, Article 104139 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 104139 |
|---|---|
| container_issue | |
| container_start_page | 104139 |
| container_title | Journal of dentistry |
| container_volume | 122 |
| creator | Gerhardt, Maurício do Nascimento Fontenele, Rocharles Cavalcante Leite, André Ferreira Lahoud, Pierre Van Gerven, Adriaan Willems, Holger Smolders, Andreas Beznik, Thomas Jacobs, Reinhilde |
| description | To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images.
After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed on a total of 46 CBCT scans selected for this purpose. Scans were split into fully dentate and partially dentate patients (small edentulous regions). The AI Driven tool (Virtual Patient Creator, Relu BV, Leuven, Belgium) automatically detected, segmented and labelled teeth and edentulous regions. Human performance served as clinical reference. Accuracy and speed of the AI-driven tool to detect and label teeth and edentulous regions in partially edentulous jaws were assessed. Automatic tooth segmentation was compared to manually refined segmentation and accuracy by means of Intersetion over Union (IoU) and 95% Hausdorff Distance served as a secondary outcome.
The AI-driven tool achieved a general accuracy of 99.7% and 99% for detection and labelling of teeth and missing teeth for both fully dentate and partially dentate patients, respectively. Automated detections took a median time of 1.5s, while the human operator median time was 98s (P |
| doi_str_mv | 10.1016/j.jdent.2022.104139 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_swepu</sourceid><recordid>TN_cdi_swepub_primary_oai_swepub_ki_se_453874</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0300571222001956</els_id><sourcerecordid>2672693326</sourcerecordid><originalsourceid>FETCH-LOGICAL-c470t-c098bc0aaf5de9e3fad1087f7addfb6923b58064967f5d3ac6b6bfa7b112f703</originalsourceid><addsrcrecordid>eNp9kctu1TAQhiMEoofCEyAhS2zY5OBLYicLFlVFC1IlNl2ws3yZnCZN4uBLq74DD41zcuiCBasZjb7_H3v-onhP8J5gwj8P-8HCHPcUU5onFWHti2JHGtGWRPCfL4sdZhiXtSD0rHgTwoAxrjBtXxdnrK44aUW1K35fpOgmFcEiCxFM7N2M1GzRqDSMYz8fkOtQBIh3x3GY1DgiWBen0aWAPByyJKAsM26GUoOacjctafXM3u7g1XL3hFJYzTLz4Ma0rlEjmiH5Y4mPzt-Ht8WrTo0B3p3qeXF79fX28lt58-P6--XFTWkqgWNpcNtog5XqagstsE5ZghvRCWVtp3lLma4bzKuWi0wwZbjmulNCE0I7gdl5UW624RGWpOXi-0n5J-lUL0-j-9yBrGrWiCrznzZ-8e5XghDl1AeTr6NmyCeQlNc1wTXmbUY__oMOLvn81ZUSNBOM8kyxjTLeheChe34CwXLNVg7ymK1cs5Vbtln14eSd9AT2WfM3zAx82QDIt3vowctgepgN2N7nZKV1_X8X_AE-crqL</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2672693326</pqid></control><display><type>article</type><title>Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks</title><source>Elsevier ScienceDirect Journals</source><source>SWEPUB Freely available online</source><creator>Gerhardt, Maurício do Nascimento ; Fontenele, Rocharles Cavalcante ; Leite, André Ferreira ; Lahoud, Pierre ; Van Gerven, Adriaan ; Willems, Holger ; Smolders, Andreas ; Beznik, Thomas ; Jacobs, Reinhilde</creator><creatorcontrib>Gerhardt, Maurício do Nascimento ; Fontenele, Rocharles Cavalcante ; Leite, André Ferreira ; Lahoud, Pierre ; Van Gerven, Adriaan ; Willems, Holger ; Smolders, Andreas ; Beznik, Thomas ; Jacobs, Reinhilde</creatorcontrib><description>To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images.
After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed on a total of 46 CBCT scans selected for this purpose. Scans were split into fully dentate and partially dentate patients (small edentulous regions). The AI Driven tool (Virtual Patient Creator, Relu BV, Leuven, Belgium) automatically detected, segmented and labelled teeth and edentulous regions. Human performance served as clinical reference. Accuracy and speed of the AI-driven tool to detect and label teeth and edentulous regions in partially edentulous jaws were assessed. Automatic tooth segmentation was compared to manually refined segmentation and accuracy by means of Intersetion over Union (IoU) and 95% Hausdorff Distance served as a secondary outcome.
The AI-driven tool achieved a general accuracy of 99.7% and 99% for detection and labelling of teeth and missing teeth for both fully dentate and partially dentate patients, respectively. Automated detections took a median time of 1.5s, while the human operator median time was 98s (P<0.0001). Segmentation accuracy measured by Intersection over Union was 0.96 and 0.97 for fully dentate and partially edentulous jaws respectively.
The AI-driven tool was accurate and fast for CBCT-based detection, segmentation and labelling of teeth and missing teeth in partial edentulism.
The use of AI may represent a promising time-saving tool serving radiological reporting, with a major step forward towards automated dental charting, as well as surgical and treatment planning.</description><identifier>ISSN: 0300-5712</identifier><identifier>EISSN: 1879-176X</identifier><identifier>DOI: 10.1016/j.jdent.2022.104139</identifier><identifier>PMID: 35461974</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Accuracy ; Artificial Intelligence ; Artificial neural networks ; Automation ; Big Data ; Classification ; Computed tomography ; Cone-Beam Computed Tomography ; Datasets ; Deep Learning ; Dentistry ; Digital Dentistry ; Digital imaging/radiology ; Edentulous ; Human error ; Human performance ; Image segmentation ; Labeling ; Metric space ; Neural networks ; Patients ; Teeth ; Three dimensional imaging ; Tomography ; Tooth Detection ; Training</subject><ispartof>Journal of dentistry, 2022-07, Vol.122, p.104139-104139, Article 104139</ispartof><rights>2022 Elsevier Ltd</rights><rights>Copyright © 2022 Elsevier Ltd. All rights reserved.</rights><rights>2022. Elsevier Ltd</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c470t-c098bc0aaf5de9e3fad1087f7addfb6923b58064967f5d3ac6b6bfa7b112f703</citedby><cites>FETCH-LOGICAL-c470t-c098bc0aaf5de9e3fad1087f7addfb6923b58064967f5d3ac6b6bfa7b112f703</cites><orcidid>0000-0002-7843-0022 ; 0000-0001-5195-7660 ; 0000-0002-7803-4740 ; 0000-0003-1683-2314 ; 0000-0003-2757-9123 ; 0000-0001-5555-2185</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0300571222001956$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,550,776,780,881,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35461974$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttp://kipublications.ki.se/Default.aspx?queryparsed=id:149761623$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Gerhardt, Maurício do Nascimento</creatorcontrib><creatorcontrib>Fontenele, Rocharles Cavalcante</creatorcontrib><creatorcontrib>Leite, André Ferreira</creatorcontrib><creatorcontrib>Lahoud, Pierre</creatorcontrib><creatorcontrib>Van Gerven, Adriaan</creatorcontrib><creatorcontrib>Willems, Holger</creatorcontrib><creatorcontrib>Smolders, Andreas</creatorcontrib><creatorcontrib>Beznik, Thomas</creatorcontrib><creatorcontrib>Jacobs, Reinhilde</creatorcontrib><title>Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks</title><title>Journal of dentistry</title><addtitle>J Dent</addtitle><description>To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images.
After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed on a total of 46 CBCT scans selected for this purpose. Scans were split into fully dentate and partially dentate patients (small edentulous regions). The AI Driven tool (Virtual Patient Creator, Relu BV, Leuven, Belgium) automatically detected, segmented and labelled teeth and edentulous regions. Human performance served as clinical reference. Accuracy and speed of the AI-driven tool to detect and label teeth and edentulous regions in partially edentulous jaws were assessed. Automatic tooth segmentation was compared to manually refined segmentation and accuracy by means of Intersetion over Union (IoU) and 95% Hausdorff Distance served as a secondary outcome.
The AI-driven tool achieved a general accuracy of 99.7% and 99% for detection and labelling of teeth and missing teeth for both fully dentate and partially dentate patients, respectively. Automated detections took a median time of 1.5s, while the human operator median time was 98s (P<0.0001). Segmentation accuracy measured by Intersection over Union was 0.96 and 0.97 for fully dentate and partially edentulous jaws respectively.
The AI-driven tool was accurate and fast for CBCT-based detection, segmentation and labelling of teeth and missing teeth in partial edentulism.
The use of AI may represent a promising time-saving tool serving radiological reporting, with a major step forward towards automated dental charting, as well as surgical and treatment planning.</description><subject>Accuracy</subject><subject>Artificial Intelligence</subject><subject>Artificial neural networks</subject><subject>Automation</subject><subject>Big Data</subject><subject>Classification</subject><subject>Computed tomography</subject><subject>Cone-Beam Computed Tomography</subject><subject>Datasets</subject><subject>Deep Learning</subject><subject>Dentistry</subject><subject>Digital Dentistry</subject><subject>Digital imaging/radiology</subject><subject>Edentulous</subject><subject>Human error</subject><subject>Human performance</subject><subject>Image segmentation</subject><subject>Labeling</subject><subject>Metric space</subject><subject>Neural networks</subject><subject>Patients</subject><subject>Teeth</subject><subject>Three dimensional imaging</subject><subject>Tomography</subject><subject>Tooth Detection</subject><subject>Training</subject><issn>0300-5712</issn><issn>1879-176X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>D8T</sourceid><recordid>eNp9kctu1TAQhiMEoofCEyAhS2zY5OBLYicLFlVFC1IlNl2ws3yZnCZN4uBLq74DD41zcuiCBasZjb7_H3v-onhP8J5gwj8P-8HCHPcUU5onFWHti2JHGtGWRPCfL4sdZhiXtSD0rHgTwoAxrjBtXxdnrK44aUW1K35fpOgmFcEiCxFM7N2M1GzRqDSMYz8fkOtQBIh3x3GY1DgiWBen0aWAPByyJKAsM26GUoOacjctafXM3u7g1XL3hFJYzTLz4Ma0rlEjmiH5Y4mPzt-Ht8WrTo0B3p3qeXF79fX28lt58-P6--XFTWkqgWNpcNtog5XqagstsE5ZghvRCWVtp3lLma4bzKuWi0wwZbjmulNCE0I7gdl5UW624RGWpOXi-0n5J-lUL0-j-9yBrGrWiCrznzZ-8e5XghDl1AeTr6NmyCeQlNc1wTXmbUY__oMOLvn81ZUSNBOM8kyxjTLeheChe34CwXLNVg7ymK1cs5Vbtln14eSd9AT2WfM3zAx82QDIt3vowctgepgN2N7nZKV1_X8X_AE-crqL</recordid><startdate>20220701</startdate><enddate>20220701</enddate><creator>Gerhardt, Maurício do Nascimento</creator><creator>Fontenele, Rocharles Cavalcante</creator><creator>Leite, André Ferreira</creator><creator>Lahoud, Pierre</creator><creator>Van Gerven, Adriaan</creator><creator>Willems, Holger</creator><creator>Smolders, Andreas</creator><creator>Beznik, Thomas</creator><creator>Jacobs, Reinhilde</creator><general>Elsevier Ltd</general><general>Elsevier Limited</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QF</scope><scope>7QP</scope><scope>7QQ</scope><scope>7SE</scope><scope>7SR</scope><scope>7TA</scope><scope>7TB</scope><scope>8BQ</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8G</scope><scope>JG9</scope><scope>K9.</scope><scope>7X8</scope><scope>ADTPV</scope><scope>AOWAS</scope><scope>D8T</scope><scope>ZZAVC</scope><orcidid>https://orcid.org/0000-0002-7843-0022</orcidid><orcidid>https://orcid.org/0000-0001-5195-7660</orcidid><orcidid>https://orcid.org/0000-0002-7803-4740</orcidid><orcidid>https://orcid.org/0000-0003-1683-2314</orcidid><orcidid>https://orcid.org/0000-0003-2757-9123</orcidid><orcidid>https://orcid.org/0000-0001-5555-2185</orcidid></search><sort><creationdate>20220701</creationdate><title>Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks</title><author>Gerhardt, Maurício do Nascimento ; Fontenele, Rocharles Cavalcante ; Leite, André Ferreira ; Lahoud, Pierre ; Van Gerven, Adriaan ; Willems, Holger ; Smolders, Andreas ; Beznik, Thomas ; Jacobs, Reinhilde</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c470t-c098bc0aaf5de9e3fad1087f7addfb6923b58064967f5d3ac6b6bfa7b112f703</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Accuracy</topic><topic>Artificial Intelligence</topic><topic>Artificial neural networks</topic><topic>Automation</topic><topic>Big Data</topic><topic>Classification</topic><topic>Computed tomography</topic><topic>Cone-Beam Computed Tomography</topic><topic>Datasets</topic><topic>Deep Learning</topic><topic>Dentistry</topic><topic>Digital Dentistry</topic><topic>Digital imaging/radiology</topic><topic>Edentulous</topic><topic>Human error</topic><topic>Human performance</topic><topic>Image segmentation</topic><topic>Labeling</topic><topic>Metric space</topic><topic>Neural networks</topic><topic>Patients</topic><topic>Teeth</topic><topic>Three dimensional imaging</topic><topic>Tomography</topic><topic>Tooth Detection</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gerhardt, Maurício do Nascimento</creatorcontrib><creatorcontrib>Fontenele, Rocharles Cavalcante</creatorcontrib><creatorcontrib>Leite, André Ferreira</creatorcontrib><creatorcontrib>Lahoud, Pierre</creatorcontrib><creatorcontrib>Van Gerven, Adriaan</creatorcontrib><creatorcontrib>Willems, Holger</creatorcontrib><creatorcontrib>Smolders, Andreas</creatorcontrib><creatorcontrib>Beznik, Thomas</creatorcontrib><creatorcontrib>Jacobs, Reinhilde</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Aluminium Industry Abstracts</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>Ceramic Abstracts</collection><collection>Corrosion Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>Materials Business File</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Copper Technical Reference Library</collection><collection>Materials Research Database</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>SwePub</collection><collection>SwePub Articles</collection><collection>SWEPUB Freely available online</collection><collection>SwePub Articles full text</collection><jtitle>Journal of dentistry</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Gerhardt, Maurício do Nascimento</au><au>Fontenele, Rocharles Cavalcante</au><au>Leite, André Ferreira</au><au>Lahoud, Pierre</au><au>Van Gerven, Adriaan</au><au>Willems, Holger</au><au>Smolders, Andreas</au><au>Beznik, Thomas</au><au>Jacobs, Reinhilde</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks</atitle><jtitle>Journal of dentistry</jtitle><addtitle>J Dent</addtitle><date>2022-07-01</date><risdate>2022</risdate><volume>122</volume><spage>104139</spage><epage>104139</epage><pages>104139-104139</pages><artnum>104139</artnum><issn>0300-5712</issn><eissn>1879-176X</eissn><abstract>To assess the accuracy of a novel Artificial Intelligence (AI)-driven tool for automated detection of teeth and small edentulous regions on Cone-Beam Computed Tomography (CBCT) images.
After AI training and testing with 175 CBCT scans (130 for training and 40 for testing), validation was performed on a total of 46 CBCT scans selected for this purpose. Scans were split into fully dentate and partially dentate patients (small edentulous regions). The AI Driven tool (Virtual Patient Creator, Relu BV, Leuven, Belgium) automatically detected, segmented and labelled teeth and edentulous regions. Human performance served as clinical reference. Accuracy and speed of the AI-driven tool to detect and label teeth and edentulous regions in partially edentulous jaws were assessed. Automatic tooth segmentation was compared to manually refined segmentation and accuracy by means of Intersetion over Union (IoU) and 95% Hausdorff Distance served as a secondary outcome.
The AI-driven tool achieved a general accuracy of 99.7% and 99% for detection and labelling of teeth and missing teeth for both fully dentate and partially dentate patients, respectively. Automated detections took a median time of 1.5s, while the human operator median time was 98s (P<0.0001). Segmentation accuracy measured by Intersection over Union was 0.96 and 0.97 for fully dentate and partially edentulous jaws respectively.
The AI-driven tool was accurate and fast for CBCT-based detection, segmentation and labelling of teeth and missing teeth in partial edentulism.
The use of AI may represent a promising time-saving tool serving radiological reporting, with a major step forward towards automated dental charting, as well as surgical and treatment planning.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>35461974</pmid><doi>10.1016/j.jdent.2022.104139</doi><tpages>1</tpages><orcidid>https://orcid.org/0000-0002-7843-0022</orcidid><orcidid>https://orcid.org/0000-0001-5195-7660</orcidid><orcidid>https://orcid.org/0000-0002-7803-4740</orcidid><orcidid>https://orcid.org/0000-0003-1683-2314</orcidid><orcidid>https://orcid.org/0000-0003-2757-9123</orcidid><orcidid>https://orcid.org/0000-0001-5555-2185</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0300-5712 |
| ispartof | Journal of dentistry, 2022-07, Vol.122, p.104139-104139, Article 104139 |
| issn | 0300-5712 1879-176X |
| language | eng |
| recordid | cdi_swepub_primary_oai_swepub_ki_se_453874 |
| source | Elsevier ScienceDirect Journals; SWEPUB Freely available online |
| subjects | Accuracy Artificial Intelligence Artificial neural networks Automation Big Data Classification Computed tomography Cone-Beam Computed Tomography Datasets Deep Learning Dentistry Digital Dentistry Digital imaging/radiology Edentulous Human error Human performance Image segmentation Labeling Metric space Neural networks Patients Teeth Three dimensional imaging Tomography Tooth Detection Training |
| title | Automated detection and labelling of teeth and small edentulous regions on cone-beam computed tomography using convolutional neural networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T16%3A53%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_swepu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20detection%20and%20labelling%20of%20teeth%20and%20small%20edentulous%20regions%20on%20cone-beam%20computed%20tomography%20using%20convolutional%20neural%20networks&rft.jtitle=Journal%20of%20dentistry&rft.au=Gerhardt,%20Maur%C3%ADcio%20do%20Nascimento&rft.date=2022-07-01&rft.volume=122&rft.spage=104139&rft.epage=104139&rft.pages=104139-104139&rft.artnum=104139&rft.issn=0300-5712&rft.eissn=1879-176X&rft_id=info:doi/10.1016/j.jdent.2022.104139&rft_dat=%3Cproquest_swepu%3E2672693326%3C/proquest_swepu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2672693326&rft_id=info:pmid/35461974&rft_els_id=S0300571222001956&rfr_iscdi=true |