Deep learning for the classification of cervical maturation degree and pubertal growth spurts: A pilot study

This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. The study sample included 890 cephalograms. The images were classified into six cervical stages independentl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Korean journal of orthodontics (2012) Jg. 52; H. 2; S. 112
Hauptverfasser: Mohammad-Rahimi, Hossein, Motamadian, Saeed Reza, Nadimi, Mohadeseh, Hassanzadeh-Samani, Sahel, Minabi, Mohammad A S, Mahmoudinia, Erfan, Lee, Victor Y, Rohban, Mohammad Hossein
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Korea (South) 25.03.2022
Schlagworte:
ISSN:2234-7518
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.
AbstractList This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs. The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses. The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model. The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.
This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs.ObjectiveThis study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing lateral cephalometric radiographs.The study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses.MethodsThe study sample included 890 cephalograms. The images were classified into six cervical stages independently by two orthodontists. The images were also categorized into three degrees on the basis of the growth spurt: pre-pubertal, growth spurt, and post-pubertal. Subsequently, the samples were fed to a transfer learning model implemented using the Python programming language and PyTorch library. In the last step, the test set of cephalograms was randomly coded and provided to two new orthodontists in order to compare their diagnosis to the artificial intelligence (AI) model's performance using weighted kappa and Cohen's kappa statistical analyses.The model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model.ResultsThe model's validation and test accuracy for the six-class CVM diagnosis were 62.63% and 61.62%, respectively. Moreover, the model's validation and test accuracy for the three-class classification were 75.76% and 82.83%, respectively. Furthermore, substantial agreements were observed between the two orthodontists as well as one of them and the AI model.The newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.ConclusionsThe newly developed AI model had reasonable accuracy in detecting the CVM stage and high reliability in detecting the pubertal stage. However, its accuracy was still less than that of human observers. With further improvements in data quality, this model should be able to provide practical assistance to practicing dentists in the future.
Author Rohban, Mohammad Hossein
Mohammad-Rahimi, Hossein
Minabi, Mohammad A S
Hassanzadeh-Samani, Sahel
Mahmoudinia, Erfan
Nadimi, Mohadeseh
Motamadian, Saeed Reza
Lee, Victor Y
Author_xml – sequence: 1
  givenname: Hossein
  orcidid: 0000-0002-4971-5926
  surname: Mohammad-Rahimi
  fullname: Mohammad-Rahimi, Hossein
  organization: Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Berlin, Germany
– sequence: 2
  givenname: Saeed Reza
  surname: Motamadian
  fullname: Motamadian, Saeed Reza
  organization: Dentofacial Deformities Research Center, Research Institute of Dental Sciences & Department of Orthodontics, School of Dentistry, Shahid Beheshti University of Medical Sciences, Tehran, Iran
– sequence: 3
  givenname: Mohadeseh
  surname: Nadimi
  fullname: Nadimi, Mohadeseh
  organization: Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences (TUMS), Tehran, Iran
– sequence: 4
  givenname: Sahel
  surname: Hassanzadeh-Samani
  fullname: Hassanzadeh-Samani, Sahel
  organization: Dentofacial Deformities Research Center, Research Institute of Dental Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran
– sequence: 5
  givenname: Mohammad A S
  surname: Minabi
  fullname: Minabi, Mohammad A S
  organization: Department of Computer Engineering, Sirjan University of Technology, Kerman, Iran
– sequence: 6
  givenname: Erfan
  surname: Mahmoudinia
  fullname: Mahmoudinia, Erfan
  organization: Department of Computer Engineering, Sharif University of Technology, Tehran, Iran
– sequence: 7
  givenname: Victor Y
  surname: Lee
  fullname: Lee, Victor Y
  organization: Private Practice, New York, USA
– sequence: 8
  givenname: Mohammad Hossein
  orcidid: 0000-0001-6589-850X
  surname: Rohban
  fullname: Rohban, Mohammad Hossein
  organization: Department of Computer Engineering, Sharif University of Technology, Tehran, Iran
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35321950$$D View this record in MEDLINE/PubMed
BookMark eNo1UDtPwzAY9FBES-kfYEAeWRriL34kbFV5SpVYYI5c50ub4sTBdkD990RqueV0D91wV2TSuQ4JuWFpwlPO7r8OrkogBUgEJJAwBhMyA8j4UgmWT8kihEM6Qo4KsksyzUQGrBDpjNhHxJ5a1L5ruh2tnadxj9RYHUJTN0bHxnXU1dSg_xmlpa2Ogz_ZFe48ItVdRfthiz6O8c6737inoR98DA90RfvGukhDHKrjNbmotQ24OPOcfD4_faxfl5v3l7f1arM0XMq4rBG2XKESqFSlCyYKLXQtJVMccqNQKokV5EKposi4zgBHm2FqsKhNhQbm5O6023v3PWCIZdsEg9bqDt0QSpDjUC7ynI_V23N12LZYlb1vWu2P5f9D8Af43Ws3
CitedBy_id crossref_primary_10_1007_s11357_024_01394_8
crossref_primary_10_1016_j_bspc_2024_107088
crossref_primary_10_4103_1735_3327_369629
crossref_primary_10_3390_app13063850
crossref_primary_10_1016_j_mjafi_2025_08_012
crossref_primary_10_1186_s12903_025_05482_9
crossref_primary_10_1038_s41368_025_00351_1
crossref_primary_10_3390_app122211864
crossref_primary_10_1371_journal_pone_0323776
crossref_primary_10_3390_children12081023
crossref_primary_10_3390_diagnostics15091059
crossref_primary_10_3390_healthcare12131311
crossref_primary_10_4103_aihb_aihb_140_24
crossref_primary_10_3390_diagnostics13162713
crossref_primary_10_1038_s41598_022_27062_5
crossref_primary_10_3390_jcm13144047
crossref_primary_10_1016_j_ejwf_2023_10_001
crossref_primary_10_3390_diagnostics15030257
crossref_primary_10_1016_j_ejwf_2023_02_003
crossref_primary_10_3390_healthcare11202760
crossref_primary_10_1007_s11282_023_00678_7
crossref_primary_10_1007_s00784_025_06216_5
crossref_primary_10_1016_j_jdent_2024_105442
crossref_primary_10_1186_s13005_025_00521_w
crossref_primary_10_3390_jcm13020344
crossref_primary_10_1038_s41598_023_40839_6
crossref_primary_10_1186_s40510_024_00535_1
crossref_primary_10_23736_S2724_6329_24_04930_1
crossref_primary_10_1186_s13005_025_00498_6
crossref_primary_10_1016_j_jobcr_2023_08_005
crossref_primary_10_1111_ocr_12644
crossref_primary_10_1038_s41597_025_05542_3
crossref_primary_10_5624_isd_20250045
ContentType Journal Article
DBID NPM
7X8
DOI 10.4041/kjod.2022.52.2.112
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
ExternalDocumentID 35321950
Genre Journal Article
GroupedDBID 34H
5-W
8JR
8XY
9ZL
AENEX
ALMA_UNASSIGNED_HOLDINGS
EBS
EF.
EJD
HYE
KQ8
M48
NPM
P5Y
RPM
7X8
ID FETCH-LOGICAL-c466t-fe2b47e75e77da9159a5af6617428c7e676ed285779934a32e28c1e0ce9fcdec2
IEDL.DBID 7X8
ISICitedReferencesCount 35
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000777041900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2234-7518
IngestDate Fri Jul 11 06:55:32 EDT 2025
Thu Jan 02 22:55:27 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Computer algorithm
Growth evaluation
Artificial intelligence
Cervical vertebrae
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c466t-fe2b47e75e77da9159a5af6617428c7e676ed285779934a32e28c1e0ce9fcdec2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-4971-5926
0000-0001-6589-850X
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC8964471
PMID 35321950
PQID 2642885884
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2642885884
pubmed_primary_35321950
PublicationCentury 2000
PublicationDate 20220325
PublicationDateYYYYMMDD 2022-03-25
PublicationDate_xml – month: 3
  year: 2022
  text: 20220325
  day: 25
PublicationDecade 2020
PublicationPlace Korea (South)
PublicationPlace_xml – name: Korea (South)
PublicationTitle Korean journal of orthodontics (2012)
PublicationTitleAlternate Korean J Orthod
PublicationYear 2022
SSID ssj0000651823
Score 2.4119992
Snippet This study aimed to present and evaluate a new deep learning model for determining cervical vertebral maturation (CVM) degree and growth spurts by analyzing...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 112
Title Deep learning for the classification of cervical maturation degree and pubertal growth spurts: A pilot study
URI https://www.ncbi.nlm.nih.gov/pubmed/35321950
https://www.proquest.com/docview/2642885884
Volume 52
WOSCitedRecordID wos000777041900005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8UwEA5uBy8uuG9E8Bp9zdK0XkRc8OLDg8K7PdJk6vZsq63-fmfaqidB8NJDYCBkpjPf7IwdxM74RDkldJBO6NxFIkVHRKCxSCKTDVwUhXbZhB0Ok9EovekDbnVfVvmlE1tFHUpPMfIjSUA5obbKk-pV0NYoyq72KzSm2axCKEMlXXaUfMdY0LwifKYkMxpBLSjD0PXN6IGOjp6fShoVKuWhkYeSeml-R5mttblc_O89l9hCjzP5aScYy2wKihU2OQeoeL8o4p4jXuWI_7gnBE0lQy2XeJlz32oQpH-huZ_dcQB0zYG7InC8M-XwJ_wenfjmgdfV-1tTH_NTXj1Oyoa3M2tX2d3lxe3ZlejXLQiv47gROchMW7AGrA0uRZzjjMvRfqP3nHgLsY0hyMRYi5hGOyUBjyMYeEhzH8DLNTZTlAVsMI5emcljrwZIp1WmsjTLgnY2DcZCqvJNtv_1eGMUZ8pRuALK93r883ybbL3jwLjq5m6MlVGSttZu_YF6m80Ta6laTJodNpvjzwy7bM5_NI_1214rJ_gd3lx_AvVGyLo
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+for+the+classification+of+cervical+maturation+degree+and+pubertal+growth+spurts%3A+A+pilot+study&rft.jtitle=Korean+journal+of+orthodontics+%282012%29&rft.au=Mohammad-Rahimi%2C+Hossein&rft.au=Motamadian%2C+Saeed+Reza&rft.au=Nadimi%2C+Mohadeseh&rft.au=Hassanzadeh-Samani%2C+Sahel&rft.date=2022-03-25&rft.issn=2234-7518&rft.volume=52&rft.issue=2&rft.spage=112&rft_id=info:doi/10.4041%2Fkjod.2022.52.2.112&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2234-7518&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2234-7518&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2234-7518&client=summon