Loading…
Automated landmarking for palatal shape analysis using geometric deep learning
Objectives To develop and evaluate a geometric deep‐learning network to automatically place seven palatal landmarks on digitized maxillary dental casts. Settings and Sample Population The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manua...
Saved in:
| Published in: | Orthodontics & craniofacial research 2021-12, Vol.24 (S2), p.144-152 |
|---|---|
| Main Authors: | , , , , , , , , , , , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93 |
| container_end_page | 152 |
| container_issue | S2 |
| container_start_page | 144 |
| container_title | Orthodontics & craniofacial research |
| container_volume | 24 |
| creator | Croquet, Balder Matthews, Harold Mertens, Jules Fan, Yi Nauwelaers, Nele Mahdi, Soha Hoskens, Hanne El Sergani, Ahmed Xu, Tianmin Vandermeulen, Dirk Bronstein, Michael Marazita, Mary Weinberg, Seth Claes, Peter |
| description | Objectives
To develop and evaluate a geometric deep‐learning network to automatically place seven palatal landmarks on digitized maxillary dental casts.
Settings and Sample Population
The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts.
Materials and Methods
A geometric deep‐learning network was developed to hierarchically learn features from point‐clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks.
Results
Repeat‐measurement reliability was |
| doi_str_mv | 10.1111/ocr.12513 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8818261</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2545594887</sourcerecordid><originalsourceid>FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93</originalsourceid><addsrcrecordid>eNp1kV1LwzAUhoMobk4v_ANS8EYv5vLVNL0RZPgFoiB6HbLmdHamTU1aZf_e6HSoYG4STh4ezjkvQvsEn5B4Jq7wJ4SmhG2gIRGYjAXjbHP9ZukA7YSwwJhiSsU2GjBORC54OkS3Z33nat2BSaxuTK39c9XMk9L5pNVWd9om4Um3kOhG22WoQtKHD2AOrobOV0ViANrEgvZNrO-irVLbAHtf9wg9Xpw_TK_GN3eX19Ozm3HBOWNjXkpucmOIhoxQBiajktJZaQQQI3CWciMZoQQwJxhziXVWzISOLBU5h5yN0OnK2_azGkwBTee1Va2v4gRL5XSlfv801ZOau1clJZFUkCg4-hJ499JD6FRdhQJsXAK4Piia8jTNuZRZRA__oAvX-7iOSIloo0zEoUboeEUV3oXgoVw3Q7D6SEnFlNRnSpE9-Nn9mvyOJQKTFfBWWVj-b1J30_uV8h2PXJvI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2618223644</pqid></control><display><type>article</type><title>Automated landmarking for palatal shape analysis using geometric deep learning</title><source>Wiley</source><creator>Croquet, Balder ; Matthews, Harold ; Mertens, Jules ; Fan, Yi ; Nauwelaers, Nele ; Mahdi, Soha ; Hoskens, Hanne ; El Sergani, Ahmed ; Xu, Tianmin ; Vandermeulen, Dirk ; Bronstein, Michael ; Marazita, Mary ; Weinberg, Seth ; Claes, Peter</creator><creatorcontrib>Croquet, Balder ; Matthews, Harold ; Mertens, Jules ; Fan, Yi ; Nauwelaers, Nele ; Mahdi, Soha ; Hoskens, Hanne ; El Sergani, Ahmed ; Xu, Tianmin ; Vandermeulen, Dirk ; Bronstein, Michael ; Marazita, Mary ; Weinberg, Seth ; Claes, Peter</creatorcontrib><description>Objectives
To develop and evaluate a geometric deep‐learning network to automatically place seven palatal landmarks on digitized maxillary dental casts.
Settings and Sample Population
The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts.
Materials and Methods
A geometric deep‐learning network was developed to hierarchically learn features from point‐clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks.
Results
Repeat‐measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size.
Conclusions
The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.</description><identifier>ISSN: 1601-6335</identifier><identifier>EISSN: 1601-6343</identifier><identifier>DOI: 10.1111/ocr.12513</identifier><identifier>PMID: 34169645</identifier><language>eng</language><publisher>England: Wiley Subscription Services, Inc</publisher><subject>3D shape analysis ; automatic landmarking ; Deep Learning ; Dentition ; geometric deep learning ; Humans ; Imaging, Three-Dimensional ; Maxilla ; Palate ; Quality control ; Reproducibility of Results ; Teeth</subject><ispartof>Orthodontics & craniofacial research, 2021-12, Vol.24 (S2), p.144-152</ispartof><rights>2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd</rights><rights>2021 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.</rights><rights>Copyright © 2021 John Wiley & Sons A/S</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93</citedby><cites>FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93</cites><orcidid>0000-0002-9539-5193 ; 0000-0001-9489-9819 ; 0000-0002-7680-932X ; 0000-0001-9467-4556 ; 0000-0002-0524-0025</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27923,27924</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/34169645$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Croquet, Balder</creatorcontrib><creatorcontrib>Matthews, Harold</creatorcontrib><creatorcontrib>Mertens, Jules</creatorcontrib><creatorcontrib>Fan, Yi</creatorcontrib><creatorcontrib>Nauwelaers, Nele</creatorcontrib><creatorcontrib>Mahdi, Soha</creatorcontrib><creatorcontrib>Hoskens, Hanne</creatorcontrib><creatorcontrib>El Sergani, Ahmed</creatorcontrib><creatorcontrib>Xu, Tianmin</creatorcontrib><creatorcontrib>Vandermeulen, Dirk</creatorcontrib><creatorcontrib>Bronstein, Michael</creatorcontrib><creatorcontrib>Marazita, Mary</creatorcontrib><creatorcontrib>Weinberg, Seth</creatorcontrib><creatorcontrib>Claes, Peter</creatorcontrib><title>Automated landmarking for palatal shape analysis using geometric deep learning</title><title>Orthodontics & craniofacial research</title><addtitle>Orthod Craniofac Res</addtitle><description>Objectives
To develop and evaluate a geometric deep‐learning network to automatically place seven palatal landmarks on digitized maxillary dental casts.
Settings and Sample Population
The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts.
Materials and Methods
A geometric deep‐learning network was developed to hierarchically learn features from point‐clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks.
Results
Repeat‐measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size.
Conclusions
The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.</description><subject>3D shape analysis</subject><subject>automatic landmarking</subject><subject>Deep Learning</subject><subject>Dentition</subject><subject>geometric deep learning</subject><subject>Humans</subject><subject>Imaging, Three-Dimensional</subject><subject>Maxilla</subject><subject>Palate</subject><subject>Quality control</subject><subject>Reproducibility of Results</subject><subject>Teeth</subject><issn>1601-6335</issn><issn>1601-6343</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp1kV1LwzAUhoMobk4v_ANS8EYv5vLVNL0RZPgFoiB6HbLmdHamTU1aZf_e6HSoYG4STh4ezjkvQvsEn5B4Jq7wJ4SmhG2gIRGYjAXjbHP9ZukA7YSwwJhiSsU2GjBORC54OkS3Z33nat2BSaxuTK39c9XMk9L5pNVWd9om4Um3kOhG22WoQtKHD2AOrobOV0ViANrEgvZNrO-irVLbAHtf9wg9Xpw_TK_GN3eX19Ozm3HBOWNjXkpucmOIhoxQBiajktJZaQQQI3CWciMZoQQwJxhziXVWzISOLBU5h5yN0OnK2_azGkwBTee1Va2v4gRL5XSlfv801ZOau1clJZFUkCg4-hJ499JD6FRdhQJsXAK4Piia8jTNuZRZRA__oAvX-7iOSIloo0zEoUboeEUV3oXgoVw3Q7D6SEnFlNRnSpE9-Nn9mvyOJQKTFfBWWVj-b1J30_uV8h2PXJvI</recordid><startdate>202112</startdate><enddate>202112</enddate><creator>Croquet, Balder</creator><creator>Matthews, Harold</creator><creator>Mertens, Jules</creator><creator>Fan, Yi</creator><creator>Nauwelaers, Nele</creator><creator>Mahdi, Soha</creator><creator>Hoskens, Hanne</creator><creator>El Sergani, Ahmed</creator><creator>Xu, Tianmin</creator><creator>Vandermeulen, Dirk</creator><creator>Bronstein, Michael</creator><creator>Marazita, Mary</creator><creator>Weinberg, Seth</creator><creator>Claes, Peter</creator><general>Wiley Subscription Services, Inc</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QP</scope><scope>K9.</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0002-9539-5193</orcidid><orcidid>https://orcid.org/0000-0001-9489-9819</orcidid><orcidid>https://orcid.org/0000-0002-7680-932X</orcidid><orcidid>https://orcid.org/0000-0001-9467-4556</orcidid><orcidid>https://orcid.org/0000-0002-0524-0025</orcidid></search><sort><creationdate>202112</creationdate><title>Automated landmarking for palatal shape analysis using geometric deep learning</title><author>Croquet, Balder ; Matthews, Harold ; Mertens, Jules ; Fan, Yi ; Nauwelaers, Nele ; Mahdi, Soha ; Hoskens, Hanne ; El Sergani, Ahmed ; Xu, Tianmin ; Vandermeulen, Dirk ; Bronstein, Michael ; Marazita, Mary ; Weinberg, Seth ; Claes, Peter</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>3D shape analysis</topic><topic>automatic landmarking</topic><topic>Deep Learning</topic><topic>Dentition</topic><topic>geometric deep learning</topic><topic>Humans</topic><topic>Imaging, Three-Dimensional</topic><topic>Maxilla</topic><topic>Palate</topic><topic>Quality control</topic><topic>Reproducibility of Results</topic><topic>Teeth</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Croquet, Balder</creatorcontrib><creatorcontrib>Matthews, Harold</creatorcontrib><creatorcontrib>Mertens, Jules</creatorcontrib><creatorcontrib>Fan, Yi</creatorcontrib><creatorcontrib>Nauwelaers, Nele</creatorcontrib><creatorcontrib>Mahdi, Soha</creatorcontrib><creatorcontrib>Hoskens, Hanne</creatorcontrib><creatorcontrib>El Sergani, Ahmed</creatorcontrib><creatorcontrib>Xu, Tianmin</creatorcontrib><creatorcontrib>Vandermeulen, Dirk</creatorcontrib><creatorcontrib>Bronstein, Michael</creatorcontrib><creatorcontrib>Marazita, Mary</creatorcontrib><creatorcontrib>Weinberg, Seth</creatorcontrib><creatorcontrib>Claes, Peter</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Calcium & Calcified Tissue Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Orthodontics & craniofacial research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Croquet, Balder</au><au>Matthews, Harold</au><au>Mertens, Jules</au><au>Fan, Yi</au><au>Nauwelaers, Nele</au><au>Mahdi, Soha</au><au>Hoskens, Hanne</au><au>El Sergani, Ahmed</au><au>Xu, Tianmin</au><au>Vandermeulen, Dirk</au><au>Bronstein, Michael</au><au>Marazita, Mary</au><au>Weinberg, Seth</au><au>Claes, Peter</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated landmarking for palatal shape analysis using geometric deep learning</atitle><jtitle>Orthodontics & craniofacial research</jtitle><addtitle>Orthod Craniofac Res</addtitle><date>2021-12</date><risdate>2021</risdate><volume>24</volume><issue>S2</issue><spage>144</spage><epage>152</epage><pages>144-152</pages><issn>1601-6335</issn><eissn>1601-6343</eissn><abstract>Objectives
To develop and evaluate a geometric deep‐learning network to automatically place seven palatal landmarks on digitized maxillary dental casts.
Settings and Sample Population
The sample comprised individuals with permanent dentition of various ethnicities. The network was trained from manual landmark annotations on 732 dental casts and evaluated on 104 dental casts.
Materials and Methods
A geometric deep‐learning network was developed to hierarchically learn features from point‐clouds representing the 3D surface of each cast. These features predict the locations of seven palatal landmarks.
Results
Repeat‐measurement reliability was <0.3 mm for all landmarks on all casts. Accuracy is promising. The proportion of test subjects with errors less than 2 mm was between 0.93 and 0.68, depending on the landmark. Unusually shaped and large palates generate the highest errors. There was no evidence for a difference in mean palatal shape estimated from manual compared to the automatic landmarking. The automatic landmarking reduces sample variation around the mean and reduces measurements of palatal size.
Conclusions
The automatic landmarking method shows excellent repeatability and promising accuracy, which can streamline patient assessment and research studies. However, landmark indications should be subject to visual quality control.</abstract><cop>England</cop><pub>Wiley Subscription Services, Inc</pub><pmid>34169645</pmid><doi>10.1111/ocr.12513</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-9539-5193</orcidid><orcidid>https://orcid.org/0000-0001-9489-9819</orcidid><orcidid>https://orcid.org/0000-0002-7680-932X</orcidid><orcidid>https://orcid.org/0000-0001-9467-4556</orcidid><orcidid>https://orcid.org/0000-0002-0524-0025</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1601-6335 |
| ispartof | Orthodontics & craniofacial research, 2021-12, Vol.24 (S2), p.144-152 |
| issn | 1601-6335 1601-6343 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8818261 |
| source | Wiley |
| subjects | 3D shape analysis automatic landmarking Deep Learning Dentition geometric deep learning Humans Imaging, Three-Dimensional Maxilla Palate Quality control Reproducibility of Results Teeth |
| title | Automated landmarking for palatal shape analysis using geometric deep learning |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T09%3A11%3A44IST&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=Automated%20landmarking%20for%20palatal%20shape%20analysis%20using%20geometric%20deep%20learning&rft.jtitle=Orthodontics%20&%20craniofacial%20research&rft.au=Croquet,%20Balder&rft.date=2021-12&rft.volume=24&rft.issue=S2&rft.spage=144&rft.epage=152&rft.pages=144-152&rft.issn=1601-6335&rft.eissn=1601-6343&rft_id=info:doi/10.1111/ocr.12513&rft_dat=%3Cproquest_pubme%3E2545594887%3C/proquest_pubme%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c4433-4f84d9dd1ae7123ed72822bfd6e1d60754d83121e04100480a7cb6a7122694e93%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2618223644&rft_id=info:pmid/34169645&rfr_iscdi=true |