Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans

IntroductionAccurate assessment of midpalatal suture (MPS) maturation is critical in orthodontics, particularly for planning treatment strategies in patients with maxillary transverse deficiency (MTD). Although cone-beam computed tomography (CBCT) provides detailed imaging suitable for MPS classific...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahshid Nik Ravesh, Nazila Ameli, Manuel Lagravere Vich, Hollis Lai
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Dental Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdmed.2025.1583455/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850157068733906944
author Mahshid Nik Ravesh
Nazila Ameli
Manuel Lagravere Vich
Hollis Lai
author_facet Mahshid Nik Ravesh
Nazila Ameli
Manuel Lagravere Vich
Hollis Lai
author_sort Mahshid Nik Ravesh
collection DOAJ
description IntroductionAccurate assessment of midpalatal suture (MPS) maturation is critical in orthodontics, particularly for planning treatment strategies in patients with maxillary transverse deficiency (MTD). Although cone-beam computed tomography (CBCT) provides detailed imaging suitable for MPS classification, manual interpretation is often subjective and time-consuming.MethodsThis study aimed to develop and evaluate a lightweight two-dimensional convolutional neural network (2D CNN) for the automated classification of MPS maturation stages using axial CBCT slices. A retrospective dataset of CBCT images from 111 patients was annotated based on Angelieri's classification system and grouped into three clinically relevant categories: AB (Stages A and B), C, and DE (Stages D and E). A 9-layer CNN architecture was trained and evaluated using standard classification metrics and receiver operating characteristic (ROC) curve analysis.ResultsThe model achieved a test accuracy of 96.49%. Class-wise F1-scores were 0.95 for category AB, 1.00 for C, and 0.95 for DE. Area under the ROC curve (AUC) scores were 0.10 for AB, 0.62 for C, and 0.98 for DE. Lower AUC values in the early and transitional stages (AB and C) likely reflect known anatomical overlap and subjectivity in expert labeling.DiscussionThese findings indicate that the proposed 2D CNN demonstrates high accuracy and robustness in classifying MPS maturation stages from CBCT images. Its compact architecture and strong performance suggest it is suitable for real-time clinical decision-making, particularly in identifying cases that may benefit from surgical intervention. Moreover, its lightweight design makes it adaptable for use in resource-limited settings. Future work will explore volumetric models to further enhance diagnostic reliability and confidence.
format Article
id doaj-art-03299dae8f6b4ff6abdb0ca9b5b4e9d8
institution OA Journals
issn 2673-4915
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Dental Medicine
spelling doaj-art-03299dae8f6b4ff6abdb0ca9b5b4e9d82025-08-20T02:24:17ZengFrontiers Media S.A.Frontiers in Dental Medicine2673-49152025-06-01610.3389/fdmed.2025.15834551583455Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scansMahshid Nik RaveshNazila AmeliManuel Lagravere VichHollis LaiIntroductionAccurate assessment of midpalatal suture (MPS) maturation is critical in orthodontics, particularly for planning treatment strategies in patients with maxillary transverse deficiency (MTD). Although cone-beam computed tomography (CBCT) provides detailed imaging suitable for MPS classification, manual interpretation is often subjective and time-consuming.MethodsThis study aimed to develop and evaluate a lightweight two-dimensional convolutional neural network (2D CNN) for the automated classification of MPS maturation stages using axial CBCT slices. A retrospective dataset of CBCT images from 111 patients was annotated based on Angelieri's classification system and grouped into three clinically relevant categories: AB (Stages A and B), C, and DE (Stages D and E). A 9-layer CNN architecture was trained and evaluated using standard classification metrics and receiver operating characteristic (ROC) curve analysis.ResultsThe model achieved a test accuracy of 96.49%. Class-wise F1-scores were 0.95 for category AB, 1.00 for C, and 0.95 for DE. Area under the ROC curve (AUC) scores were 0.10 for AB, 0.62 for C, and 0.98 for DE. Lower AUC values in the early and transitional stages (AB and C) likely reflect known anatomical overlap and subjectivity in expert labeling.DiscussionThese findings indicate that the proposed 2D CNN demonstrates high accuracy and robustness in classifying MPS maturation stages from CBCT images. Its compact architecture and strong performance suggest it is suitable for real-time clinical decision-making, particularly in identifying cases that may benefit from surgical intervention. Moreover, its lightweight design makes it adaptable for use in resource-limited settings. Future work will explore volumetric models to further enhance diagnostic reliability and confidence.https://www.frontiersin.org/articles/10.3389/fdmed.2025.1583455/fulldeep learningconvolutional neural networksmidpalatal sutureCBCTorthodonticsmaxillary transverse deficiency
spellingShingle Mahshid Nik Ravesh
Nazila Ameli
Manuel Lagravere Vich
Hollis Lai
Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
Frontiers in Dental Medicine
deep learning
convolutional neural networks
midpalatal suture
CBCT
orthodontics
maxillary transverse deficiency
title Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
title_full Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
title_fullStr Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
title_full_unstemmed Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
title_short Automated classification of midpalatal suture maturation using 2D convolutional neural networks on CBCT scans
title_sort automated classification of midpalatal suture maturation using 2d convolutional neural networks on cbct scans
topic deep learning
convolutional neural networks
midpalatal suture
CBCT
orthodontics
maxillary transverse deficiency
url https://www.frontiersin.org/articles/10.3389/fdmed.2025.1583455/full
work_keys_str_mv AT mahshidnikravesh automatedclassificationofmidpalatalsuturematurationusing2dconvolutionalneuralnetworksoncbctscans
AT nazilaameli automatedclassificationofmidpalatalsuturematurationusing2dconvolutionalneuralnetworksoncbctscans
AT manuellagraverevich automatedclassificationofmidpalatalsuturematurationusing2dconvolutionalneuralnetworksoncbctscans
AT hollislai automatedclassificationofmidpalatalsuturematurationusing2dconvolutionalneuralnetworksoncbctscans