中国组织工程研究 ›› 2026, Vol. 30 ›› Issue (10): 2459-2465.doi: 10.12307/2026.624

• 口腔组织构建 oral tissue construction • 上一篇    下一篇

基于正畸治疗标志点配准实时配准系统的准确性

黄举能1,曾婧捷2,彭  颖1,卢雯蓉3,唐  敏2,张学军1   

  1. 1广西大学,广西壮族自治区南宁市  530004;2广西医科大学附属口腔医院,广西壮族自治区南宁市  530021;3河池市第一人民医院,广西壮族自治区河池市  547000
  • 收稿日期:2025-03-14 接受日期:2025-06-18 出版日期:2026-04-08 发布日期:2025-08-28
  • 通讯作者: 唐敏,博士,主任医师,广西医科大学附属口腔医院,广西壮族自治区南宁市 530021 通讯作者:张学军,博士,教授,广西大学,广西壮族自治区南宁市 530004
  • 作者简介:黄举能,男,1998年生,广东省佛山市人,汉族,广西大学毕业,硕士,主要从事医学图像、计算机视觉方面的研究。 并列第一作者:曾婧捷,女,1997年生,广西壮族自治区来宾市人,壮族,2023年广西医科大学毕业,硕士,医师,主要从事口腔正畸学方面的研究。
  • 基金资助:
    广西医疗卫生适宜技术开发与推广应用项目(S2023094),项目负责人:唐敏;国家临床重点专科建设项目(CZ000037),项目负责人:唐敏

Accuracy of a real-time registration system based on orthodontic landmarks

Huang Juneng1, Zeng Jingjie2, Peng Ying1, Lu Wenrong3, Tang Min2, Zhang Xuejun1   

  1. 1Guangxi University, Nanning 530004, Guangxi Zhuang Autonomous Region, China; 2Guangxi Medical University Stomatological Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China; 3First People’s Hospital of Hechi City, Hechi 547000, Guangxi Zhuang Autonomous Region, China
  • Received:2025-03-14 Accepted:2025-06-18 Online:2026-04-08 Published:2025-08-28
  • Contact: Tang Min, MD, Chief physician, Guangxi Medical University Stomatological Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China Co-corresponding author: Zhang Xuejun, MD, Professor, Guangxi University, Nanning 530004, Guangxi Zhuang Autonomous Region, China
  • About author:Huang Juneng, MS, Guangxi University, Nanning 530004, Guangxi Zhuang Autonomous Region, China Zeng Jingjie, MS, Physician, Guangxi Medical University Stomatological Hospital, Nanning 530021, Guangxi Zhuang Autonomous Region, China Huang Juneng and Zeng Jingjie contributed equally to this work.
  • Supported by:
    Guangxi Medical and Healthcare Appropriate Technology Development and Promotion Application Project, No. S2023094 (to TM); National Clinical Key Specialty Construction Project, No. CZ000037 (to TM)

摘要:




文题释义:
实时配准系统:是一种基于计算机视觉技术开发的工具,专门用于正畸学中头颅侧位片的精确重叠。该系统利用Labelme软件进行标志点定位,并采用自定义实时可视化配准软件,实现了治疗前后头颅侧位片的自动配准与可视化。该系统在配准过程中不仅能够提供即时反馈,还能有效减少传统方法中因人为因素导致的误差。
多标志点配准:指通过医学影像中多个解剖标志点的空间位置匹配,实现图像对齐重叠的技术。通过多个标志点共同参与配准,将误差分散到多个点上,提高图像配准的精度和稳定性。

背景:连续头颅侧位X射线片的重叠在正畸学中常用来评估正畸/矫形治疗的结果和生长发育的变化。标志点定位误差和配准方法是影响头颅侧位片重叠准确性的关键因素,目前还没有非常精准的配准系统。
目的:开发一个实时配准系统指导头颅侧位X射线片上的标志点定位,以提高头颅侧位X射线片配准精度,并评价该配准方法的准确性。
方法:根据纳排标准选择40例成年患者正畸治疗前后头颅侧位X射线片,使用Labelme软件进行治疗前后头颅侧位X射线片标志点定位。利用python语言、Opencv、PyQT编写实时可视化配准软件。通过SellaNasion(SN)重叠法、LS-5重叠法(LS-5)以及LS-5实时重叠法(LS-5R)进行配准,测量比较不同重叠方法中前鼻棘(ANS)、后鼻棘(PNS)、上牙槽座点(A)、下牙槽座点(B)、颏前点(Pog)的距离误差和成功检测率来评价配准精度。
结果与结论:①LS-5实时重叠法的标志点距离误差最小,与SN法相比所有点的距离误差均有显著性差异(P < 0.05),与LS-5重叠法相比后鼻棘(PNS)、上牙槽座点(A)、下牙槽座点(B)、颏前点(Pog)的距离误差有显著性差异(P < 0.05),且差异依次增加;②LS-5实时重叠法在1,2,3 mm精度范围内自动叠加标志点的成功检出率均高于SN重叠法;③LS-5实时重叠法与传统的SN重叠法相比,叠加误差更小,它可能是临床上更可靠的叠加连续头颅侧位图像的方法。
https://orcid.org/0009-0002-6507-7255(黄举能);https://orcid.org/0000-0002-5392-0914(曾婧捷)

中国组织工程研究杂志出版内容重点:干细胞;骨髓干细胞;造血干细胞;脂肪干细胞;肿瘤干细胞;胚胎干细胞;脐带脐血干细胞;干细胞诱导;干细胞分化;组织工程

关键词: 头颅侧位X射线片, 重叠, 多点配准, 实时配准, 准确性

Abstract: BACKGROUND: The superimposition of consecutive cephalometric lateral radiographs is commonly used in orthodontics to assess the outcomes of orthodontic/orthopedic treatments and changes in growth and development. The key factors affecting the accuracy of cephalometric superimposition are landmark localization errors and registration methods. Currently, there is no highly accurate registration system. 
OBJECTIVE: To study a real-time registration system that guides the adjustment of landmark localization on cephalometric lateral radiographs to assist in improving registration accuracy and evaluate the precision of this registration method. 
METHODS: Pre- and post-treatment cephalometric lateral radiographs of 40 adult patients were selected according to the inclusion criteria. Landmark localization on the pre- and post-treatment radiographs was performed using Labelme software. Real-time visualized registration software was developed using Python, Opencv, and PyQT. Registration was performed using the SellaNasion (SN) superimposition method, the Least Squared Averaged 5 Landmarks (LS-5) method, and the Real-time Least Squared Averaged 5 Landmarks (LS-5R) method. The distance errors and the success detection rate of landmarks anterior nasal spine (ANS), posterior nasal spine (PNS), upper alveolar seat point (A), lower alveolar seat point (B), point of anterior chin (Pog) were measured and compared to evaluate the registration accuracy.
RESULTS AND CONCLUSION: The LS-5R method exhibited the smallest landmark distance errors. Compared with the SN method, all landmark distance errors showed statistically significant differences (P < 0.05). The distance errors of PNS, A, B, and Pog landmarks with the LS-5R method were statistically different from those with the LS-5 method (P < 0.05), and the differences increased in sequence. The success detection rate of automatic landmark detection within 1mm, 2mm, and 3mm accuracy ranges was higher for the LS-5R method than for the SN superimposition method. The LS-5R method has smaller superimposition errors compared with the traditional SN method, making it a potentially more reliable method for superimposing consecutive cephalometric lateral radiographs in clinical practice.

Key words: lateral cephalogram, superimposition, multi-point registration, real-time registration, accuracy

中图分类号: