A personalized automated system of 3D facial soft tissue landmarks annotation based on deep learning and computer vision

Sep 29, 2026

Study objective focused on developing a personalized automated system to annotate three-dimensional facial soft tissue landmarks using deep learning and computer vision. Automated landmark results were compared with manual expert annotations to evaluate accuracy and clinical feasibility for facial morphology research. A cohort of 55 Chinese orthodontic patients, including normal morphology and severe craniofacial deformities, supported standardized template construction and personalized keypoint transfer for efficient batch processing. Results were assessed across clinically relevant landmarks for both global and deformity-specific performance.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Objective

Methods

Results

Conclusions

Introduction

Wu et al. BMCOral Health (2026) 26:6 BMC Oral Health [https://doi.org/10.1186/s12903-025-07448-3](https://doi.org/10.1186/s12903-025-07448-3) RESEARCH Open Access A personalized automated system of 3D facial soft tissue landmarks annotation based on deep learning and computer vision Yongwei Wu 1†, Zichen Zhao 1†, Jinglin Lu 1, Qiaohui Ying 1, XinYi Huang 1, Xin Zhang 1, Changyun Sun 1, Jian Yu2* and Jie Guo 1* Abstract Objective This study aims to develop a personalized automated system for annotating three-dimensional (3D) facial soft tissue landmarks utilizing deep learning and computer vision. By comparing the results of automated annotations with manual annotations, the accuracy and clinical applicability of the proposed algorithm were systematically evaluated, providing an efficient and precise analysis system for facial morphology research. Methods A total of 55 Chinese orthodontic patients (24 males, 31 females; mean age 23.4 ± 7.01 years) were recruited from Shandong University Stomatological Hospital, comprising 40 patients with normal facial morphology and 15 with severe craniofacial deformities (mandibular asymmetry, severe skeletal Class II and III; n = 5 each) . This study constructed a personalized automated system based on deep learning and computer vision. Through standardized facial template construction with 68 key points, automated 68-landmark annotation of original scans, 3D facial nonlinear registration, and personalized keypoint transfer, the system enables one-time personalized annotation of the standard template and subsequent automatic batch mapping to multiple facial scan models. Deformityspecific personalized templates were constructed for severe malocclusions. Annotation accuracy was evaluated against manual annotations by experienced orthodontic experts using 21 clinically relevant landmarks. Results The system demonstrated outstanding accuracy with an average Euclidean distance of 0.95 ± 0.48 mm for 21 selected landmarks, surpassing most existing algorithms. Proportion-based analysis revealed that 96. 3% of all landmarks achieved clinically acceptable accuracy within 2.0 mm, with 84. 0% within 1.5 mm and 57. 0% achieving sub-millimeter precision. The average errors for linear and angular measurements were 0.31 ± 0.35 mm and 1.05 ± 0. 90°, respectively. For mandibular deformity samples, personalized templates significantly improved accuracy, reducing mean Euclidean distance from 0.95 ± 0.33 mm (standardized template) to 0.84 ± 0.21 mm (personalized template), with significant error reductions across all 21 landmarks, particularly in mandibular regions. †Yongwei Wu and Zichen Zhao contributed equally to this work. *Correspondence: Jian Yu 1368861 [1282@163.com](1282@163.com) Jie Guo [kqgjsdu@163.com](kqgjsdu@163.com) Full list of author information is available at the end of the article © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/l](vecommons.org/l)icenses/by-nc-nd/4.0/. Wu et al. BMC Or

FAQs

What problem does the study address?

The study develops an automated system to annotate 3D facial soft tissue landmarks, aiming to replace or assist manual landmarking in facial morphology research and orthodontic workflows.

How was the automated system constructed and personalized?

It uses standardized facial template construction with 68 key points, 3D facial nonlinear registration, and personalized keypoint transfer, then performs one-time template annotation followed by automatic batch mapping. Deformity-specific templates were built for severe malocclusions.

How accurate was the system compared with manual annotation?

The system achieved an average Euclidean distance of 0.95 ± 0.48 mm across 21 selected landmarks, with 96.3% within 2.0 mm and 84.0% within 1.5 mm. For mandibular deformity cases, personalized templates improved accuracy, reducing mean distance from 0.95 ± 0.33 mm to 0.84 ± 0.21 mm.

Sep 29, 2026

Uploaded by Well Done