Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement

Abstract Objectives This study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities o...

Full description

Saved in:
Bibliographic Details
Main Authors: Potjanee Kanchanapiboon, Pitipat Tunksook, Prinya Tunksook, Panrasee Ritthipravat, Supatchai Boonpratham, Yodhathai Satravaha, Chaiyapol Chaweewannakorn, Supakit Peanchitlertkajorn
Format: Article
Language:English
Published: SpringerOpen 2024-09-01
Series:Progress in Orthodontics
Subjects:
Online Access:https://doi.org/10.1186/s40510-024-00535-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334487196893184
author Potjanee Kanchanapiboon
Pitipat Tunksook
Prinya Tunksook
Panrasee Ritthipravat
Supatchai Boonpratham
Yodhathai Satravaha
Chaiyapol Chaweewannakorn
Supakit Peanchitlertkajorn
author_facet Potjanee Kanchanapiboon
Pitipat Tunksook
Prinya Tunksook
Panrasee Ritthipravat
Supatchai Boonpratham
Yodhathai Satravaha
Chaiyapol Chaweewannakorn
Supakit Peanchitlertkajorn
author_sort Potjanee Kanchanapiboon
collection DOAJ
description Abstract Objectives This study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities on unseen datasets. Methods Three clinicians independently rated CVMS on 1380 lateral cephalograms, resulting in the creation of five datasets: two consensus-based datasets (Complete Agreement and Majority Voting), and three datasets based on a single rater’s evaluations. Additionally, landmarks annotation of the second to fourth cervical vertebrae and patients’ information underwent a feature selection process. These datasets were used to train various ML models and identify the top-performing model for each dataset. These models were subsequently tested on their generalization capabilities. Results Features that considered significant in the consensus-based datasets were consistent with a CVMS guideline. The Support Vector Machine model on the Complete Agreement dataset achieved the highest accuracy (77.4%), followed by the Multi-Layer Perceptron model on the Majority Voting dataset (69.6%). Models from individual ratings showed lower accuracies (60.4–67.9%). The consensus-based training models also exhibited lower coefficient of variation (CV), indicating superior generalization capability compared to models from single raters. Conclusion ML models trained on consensus-based datasets for CVMS classification exhibited the highest accuracy, with significant features consistent with the original CVMS guidelines. These models also showed robust generalization capabilities, underscoring the importance of dataset quality.
format Article
id doaj-art-ddab0ebf532d4f9fb31f6558cb787852
institution Kabale University
issn 2196-1042
language English
publishDate 2024-09-01
publisher SpringerOpen
record_format Article
series Progress in Orthodontics
spelling doaj-art-ddab0ebf532d4f9fb31f6558cb7878522025-08-20T03:45:32ZengSpringerOpenProgress in Orthodontics2196-10422024-09-0125111410.1186/s40510-024-00535-1Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreementPotjanee Kanchanapiboon0Pitipat Tunksook1Prinya Tunksook2Panrasee Ritthipravat3Supatchai Boonpratham4Yodhathai Satravaha5Chaiyapol Chaweewannakorn6Supakit Peanchitlertkajorn7Division of Nuclear Medicine, Department of Radiology, Faculty of Medicine Siriraj Hospital, Mahidol UniversityDepartment of Orthodontics, Faculty of Dentistry, Mahidol UniversityPrivate PracticeDepartment of Biomedical Engineering, Faculty of Engineering, Mahidol UniversityDepartment of Orthodontics, Faculty of Dentistry, Mahidol UniversityDepartment of Orthodontics, Faculty of Dentistry, Mahidol UniversityDepartment of Orthodontics, Faculty of Dentistry, Mahidol UniversityDepartment of Orthodontics, Faculty of Dentistry, Mahidol UniversityAbstract Objectives This study aimed to assess the accuracy of machine learning (ML) models with feature selection technique in classifying cervical vertebral maturation stages (CVMS). Consensus-based datasets were used for models training and evaluation for their model generalization capabilities on unseen datasets. Methods Three clinicians independently rated CVMS on 1380 lateral cephalograms, resulting in the creation of five datasets: two consensus-based datasets (Complete Agreement and Majority Voting), and three datasets based on a single rater’s evaluations. Additionally, landmarks annotation of the second to fourth cervical vertebrae and patients’ information underwent a feature selection process. These datasets were used to train various ML models and identify the top-performing model for each dataset. These models were subsequently tested on their generalization capabilities. Results Features that considered significant in the consensus-based datasets were consistent with a CVMS guideline. The Support Vector Machine model on the Complete Agreement dataset achieved the highest accuracy (77.4%), followed by the Multi-Layer Perceptron model on the Majority Voting dataset (69.6%). Models from individual ratings showed lower accuracies (60.4–67.9%). The consensus-based training models also exhibited lower coefficient of variation (CV), indicating superior generalization capability compared to models from single raters. Conclusion ML models trained on consensus-based datasets for CVMS classification exhibited the highest accuracy, with significant features consistent with the original CVMS guidelines. These models also showed robust generalization capabilities, underscoring the importance of dataset quality.https://doi.org/10.1186/s40510-024-00535-1Cervical vertebral maturation stagesMachine learningArtificial intelligenceConsensus-based modelLandmark annotation
spellingShingle Potjanee Kanchanapiboon
Pitipat Tunksook
Prinya Tunksook
Panrasee Ritthipravat
Supatchai Boonpratham
Yodhathai Satravaha
Chaiyapol Chaweewannakorn
Supakit Peanchitlertkajorn
Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
Progress in Orthodontics
Cervical vertebral maturation stages
Machine learning
Artificial intelligence
Consensus-based model
Landmark annotation
title Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
title_full Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
title_fullStr Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
title_full_unstemmed Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
title_short Classification of cervical vertebral maturation stages with machine learning models: leveraging datasets with high inter- and intra-observer agreement
title_sort classification of cervical vertebral maturation stages with machine learning models leveraging datasets with high inter and intra observer agreement
topic Cervical vertebral maturation stages
Machine learning
Artificial intelligence
Consensus-based model
Landmark annotation
url https://doi.org/10.1186/s40510-024-00535-1
work_keys_str_mv AT potjaneekanchanapiboon classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT pitipattunksook classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT prinyatunksook classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT panraseeritthipravat classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT supatchaiboonpratham classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT yodhathaisatravaha classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT chaiyapolchaweewannakorn classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement
AT supakitpeanchitlertkajorn classificationofcervicalvertebralmaturationstageswithmachinelearningmodelsleveragingdatasetswithhighinterandintraobserveragreement