文献速递口腔颌面外科口腔修复与种植

口腔颌面外科医学图像分割技术进展综述

Advancements in oral and maxillofacial surgery medical images segmentation techniques: An overview.
PubMed 文献 · J Dent · 2023-09-26

该综述系统回顾了口腔颌面外科计算机辅助分割方法的研究进展,聚焦牙齿检测分割、下颌管分割和牙槽骨分割三个方面,最常用影像技术为CBCT。分割方法分为传统图像处理与机器学习(含深度学习)两类,性能测试显示其表现与牙医标注相似,但尚无研究评估其实际应用价值。

要点

  • 深度学习分割方法性能已接近牙医标注水平,但缺乏临床实际应用价值评估。
  • CBCT是口腔颌面外科分割研究中最常用的影像技术,其次为常规CT和曲面断层片。
  • 数据集稀缺且不一致、图像伪影、数据分布不平衡及黑箱性质是主要挑战。

核心结论

  • 分割方法尤其是深度学习方法展现出前所未有的性能,但固有挑战仍存,包括数据集稀缺与不一致、图像可见伪影、数据分布不平衡及黑箱性质。
  • 尚无研究评估分割方法的实际应用价值。

研究设计与样本

  • 综述纳入报道分割方法在口腔颌面外科领域应用的全文文章和会议论文,检索至2023年7月,数据库包括Medline via PubMed、IEEE Xplore、ArXiv和Google Scholar。
  • 研究聚焦牙齿检测分割、下颌管分割和牙槽骨分割三个方面。

主要发现

  • 分割方法主要分为传统图像处理和机器学习(含深度学习)两类。
  • 在医学专业人员标注的图像数据集上性能测试显示,分割方法表现与牙医标注相似,证实其有效性。
  • 最常用影像技术为CBCT,其次为常规CT和曲面断层片。

临床怎么用

  • 精确图像分割对口腔颌面外科的精准治疗和手术规划至关重要,本综述旨在促进牙科研究者制定更准确有效的手术治疗计划。

局限性

  • 数据集稀缺且不一致。
  • 图像存在可见伪影。
  • 数据分布不平衡。
  • 深度学习的黑箱性质。
  • 尚无研究评估实际应用价值。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: This article reviews recent advances in computer-aided segmentation methods for oral and maxillofacial surgery and describes the advantages and limitations of these methods. The objective is to provide an invaluable resource for precise therapy and surgical planning in oral and maxillofacial surgery. Study selection, data and sources: This review includes full-text articles and conference proceedings reporting the application of segmentation methods in the field of oral and maxillofacial surgery. The research focuses on three aspects: tooth detection segmentation, mandibular canal segmentation and alveolar bone segmentation. The most commonly used imaging technique is CBCT, followed by conventional CT and Orthopantomography. A systematic electronic database search was performed up to July 2023 (Medline via PubMed, IEEE Xplore, ArXiv, Google Scholar were searched). RESULTS: These segmentation methods can be mainly divided into two categories: traditional image processing and machine learning (including deep learning). Performance testing on a dataset of images labeled by medical professionals shows that it performs similarly to dentists' annotations, confirming its effectiveness. However, no studies have evaluated its practical application value. CONCLUSION: Segmentation methods (particularly deep learning methods) have demonstrated unprecedented performance, while inherent challenges remain, including the scarcity and inconsistency of datasets, visible artifacts in images, unbalanced data distribution, and the "black box" nature. CLINICAL SIGNIFICANCE: Accurate image segmentation is critical for precise treatment and surgical planning in oral and maxillofacial surgery. This review aims to facilitate more accurate and effective surgical treatment planning among dental researchers.

来源:J Dent,查看原文。版权归原作者所有。

引用

  1. Zhang L, Li W, Lv J, et al. Advancements in oral and maxillofacial surgery medical images segmentation techniques: An overview. J Dent. 2023. PMID: 37769934. doi:10.1016/j.jdent.2023.104727

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。