Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT

ObjectiveTraditional gingival thickness (GT) assessment methods provide only point measurements or simple classifications, lacking spatial distribution information. This study aimed to develop a CBCT-based 3D visualization system for gingival thickness using deep learning, providing a novel spatial...

Full description

Saved in:
Bibliographic Details
Main Authors: Lan Yang, ZiCheng Zhu, Yongshan Li, Jieying Huang, Xiaoli Wang, Haoran Zheng, Jiang Chen
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Dental Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fdmed.2025.1635155/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849235184339124224
author Lan Yang
Lan Yang
ZiCheng Zhu
Yongshan Li
Jieying Huang
Xiaoli Wang
Haoran Zheng
Jiang Chen
author_facet Lan Yang
Lan Yang
ZiCheng Zhu
Yongshan Li
Jieying Huang
Xiaoli Wang
Haoran Zheng
Jiang Chen
author_sort Lan Yang
collection DOAJ
description ObjectiveTraditional gingival thickness (GT) assessment methods provide only point measurements or simple classifications, lacking spatial distribution information. This study aimed to develop a CBCT-based 3D visualization system for gingival thickness using deep learning, providing a novel spatial assessment tool for implant surgery planning.MethodsCBCT and intraoral scanning (IOS) data from 50 patients with tooth loss were collected to establish a standardized dataset. DeepLabV3+ architecture was employed for semantic segmentation of gingival and bone tissues. A 3D visualization algorithm incorporating vertical scanning strategy, triangular mesh construction, and gradient color mapping was innovatively developed to transform 2D slices into continuous 3D surfaces.ResultsThe semantic segmentation model achieved a mIoU of 85.92 ± 0.43%. The 3D visualization system successfully constructed a comprehensive spatial distribution model of gingival thickness, clearly demonstrating GT variations from alveolar ridge to labial aspect through gradient coloration. The 3D model enabled millimeter-precision quantification, supporting multi-angle and multi-level GT assessment that overcame the limitations of traditional 2D measurements.ConclusionThis system represents a methodological advancement from qualitative to spatial quantitative GT assessment. The intuitive 3D visualization serves as an innovative preoperative tool that identifies high-risk areas and guides personalized surgical planning, enhancing predictability for aesthetic and complex implant cases.
format Article
id doaj-art-e2c2d34ede2c4f1995baa9311289b514
institution Kabale University
issn 2673-4915
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Dental Medicine
spelling doaj-art-e2c2d34ede2c4f1995baa9311289b5142025-08-20T04:02:51ZengFrontiers Media S.A.Frontiers in Dental Medicine2673-49152025-08-01610.3389/fdmed.2025.16351551635155Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCTLan Yang0Lan Yang1ZiCheng Zhu2Yongshan Li3Jieying Huang4Xiaoli Wang5Haoran Zheng6Jiang Chen7School of Stomatology, Craniomaxillofacial Implant Research Center, Fujian Medical University, Fuzhou, Fujian, ChinaGuangdong Engineering Research Center of Oral Restoration and Reconstruction & Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Department of Oral Implantology, School and Hospital of Stomatology, Guangzhou Medical University, Guangzhou, Guangdong, ChinaSchool of Data Science & School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, ChinaGuangdong Engineering Research Center of Oral Restoration and Reconstruction & Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Department of Oral Implantology, School and Hospital of Stomatology, Guangzhou Medical University, Guangzhou, Guangdong, ChinaGuangdong Engineering Research Center of Oral Restoration and Reconstruction & Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Department of Oral Implantology, School and Hospital of Stomatology, Guangzhou Medical University, Guangzhou, Guangdong, ChinaSchool of Intelligent Vehicles, Guangzhou Panyu Polytechnic, Guangzhou, ChinaSchool of Intelligent Vehicles, Guangzhou Panyu Polytechnic, Guangzhou, ChinaSchool of Stomatology, Craniomaxillofacial Implant Research Center, Fujian Medical University, Fuzhou, Fujian, ChinaObjectiveTraditional gingival thickness (GT) assessment methods provide only point measurements or simple classifications, lacking spatial distribution information. This study aimed to develop a CBCT-based 3D visualization system for gingival thickness using deep learning, providing a novel spatial assessment tool for implant surgery planning.MethodsCBCT and intraoral scanning (IOS) data from 50 patients with tooth loss were collected to establish a standardized dataset. DeepLabV3+ architecture was employed for semantic segmentation of gingival and bone tissues. A 3D visualization algorithm incorporating vertical scanning strategy, triangular mesh construction, and gradient color mapping was innovatively developed to transform 2D slices into continuous 3D surfaces.ResultsThe semantic segmentation model achieved a mIoU of 85.92 ± 0.43%. The 3D visualization system successfully constructed a comprehensive spatial distribution model of gingival thickness, clearly demonstrating GT variations from alveolar ridge to labial aspect through gradient coloration. The 3D model enabled millimeter-precision quantification, supporting multi-angle and multi-level GT assessment that overcame the limitations of traditional 2D measurements.ConclusionThis system represents a methodological advancement from qualitative to spatial quantitative GT assessment. The intuitive 3D visualization serves as an innovative preoperative tool that identifies high-risk areas and guides personalized surgical planning, enhancing predictability for aesthetic and complex implant cases.https://www.frontiersin.org/articles/10.3389/fdmed.2025.1635155/full3D visualizationgingival thicknessdeep learningcone beam computed tomographyimplant restoration
spellingShingle Lan Yang
Lan Yang
ZiCheng Zhu
Yongshan Li
Jieying Huang
Xiaoli Wang
Haoran Zheng
Jiang Chen
Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
Frontiers in Dental Medicine
3D visualization
gingival thickness
deep learning
cone beam computed tomography
implant restoration
title Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
title_full Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
title_fullStr Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
title_full_unstemmed Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
title_short Clinical-oriented 3D visualization and quantitative analysis of gingival thickness using convolutional neural networks and CBCT
title_sort clinical oriented 3d visualization and quantitative analysis of gingival thickness using convolutional neural networks and cbct
topic 3D visualization
gingival thickness
deep learning
cone beam computed tomography
implant restoration
url https://www.frontiersin.org/articles/10.3389/fdmed.2025.1635155/full
work_keys_str_mv AT lanyang clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT lanyang clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT zichengzhu clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT yongshanli clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT jieyinghuang clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT xiaoliwang clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT haoranzheng clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct
AT jiangchen clinicaloriented3dvisualizationandquantitativeanalysisofgingivalthicknessusingconvolutionalneuralnetworksandcbct