文献速递牙体牙髓病

人工智能驱动牙髓腔锥形束CT自动分割的系统综述

Progress of Artificial Intelligence-Driven Solutions for Automated Segmentation of Dental Pulp Space on Cone-Beam Computed Tomography Images. A Systematic Review.
PubMed 文献 · J Endod · 2024-05-29

本系统综述检索PubMed、Web of Science和Cochrane数据库至2024年2月,纳入13项研究,评估人工智能驱动锥形束CT图像上牙髓腔自动分割的性能。多数研究显示高准确性,但不同结构和牙型间存在差异,且因方法学细节不足和评估技术不一致,证据等级较低,结论需谨慎解读。

要点

  • AI自动分割牙髓腔总体准确性高,髓腔优于根管,单根牙优于多根牙。
  • MB2根管分割也表现出高性能,最短分割时间为13秒。
  • 证据等级低,方法学报告不足,根管分割和伪影图像性能有待改进。

核心结论

  • 人工智能驱动模型在牙髓腔分割中表现出色,但结论需谨慎解读,普遍性受限。

研究设计与样本

  • 系统综述,检索PubMed、Web of Science和Cochrane数据库至2024年2月,纳入13项研究。
  • 两名独立评审员筛选文献、提取数据并评估质量,分歧由第三名评审员解决。
  • 采用QUADAS-2工具评估偏倚风险。

主要发现

  • 多数研究显示各自分割方法准确性高,但不同结构(髓腔、根管)和牙型(单根、多根)间存在差异。
  • 髓腔分割性能略优于根管分割,单根牙分割略优于多根牙。
  • 第二近中颊根管(MB2)分割也表现出高性能。
  • 分割所需最短时间为13秒。

临床怎么用

  • AI自动分割可辅助牙髓病诊断、治疗计划和临床教学,但需注意证据等级低。
  • 临床应用中应关注根管分割和伪影图像的性能限制。

局限性

  • 方法学细节不足和评估技术不一致导致潜在偏倚和低证据等级。
  • 根管分割和伪影诱导图像中的人工智能性能有待进一步测试和改进。

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

INTRODUCTION: Automated segmentation of 3-dimensional pulp space on cone-beam computed tomography images presents a significant opportunity for enhancing diagnosis, treatment planning, and clinical education in endodontics. The aim of this systematic review was to investigate the performance of artificial intelligence-driven automated pulp space segmentation on cone-beam computed tomography images. METHODS: A comprehensive electronic search was performed using PubMed, Web of Science, and Cochrane databases, up until February 2024. Two independent reviewers participated in the selection of studies, data extraction, and evaluation of the included studies. Any disagreements were resolved by a third reviewer. The Quality Assessment of Diagnostic Accuracy Studies-2 tool was used to assess the risk of bias. RESULTS: Thirteen studies that met the eligibility criteria were included. Most studies demonstrated high accuracy in their respective segmentation methods, although there was some variation across different structures (pulp chamber, root canal) and tooth types (single-rooted, multirooted). Automated segmentation showed slightly superior performance for segmenting the pulp chamber compared to the root canal and single-rooted teeth compared to multi-rooted ones. Furthermore, the second mesiobuccal (MB2) canalsegmentation also demonstrated high performance. In terms of time efficiency, the minimum time required for segmentation was 13 seconds. CONCLUSION: Artificial intelligence-driven models demonstrated outstanding performance in pulp space segmentation. Nevertheless, these findings warrant careful interpretation, and their generalizability is limited due to the potential risk and low evidence level arising from inadequately detailed methodologies and inconsistent assessment techniques. In addition, there is room for further improvement, specifically for root canal segmentation and testing of artificial intelligence performance in artifact-induced images.

来源:J Endod,查看原文。版权归原作者所有。

引用

  1. Alfadley A, Shujaat S, Jamleh A, et al. Progress of Artificial Intelligence-Driven Solutions for Automated Segmentation of Dental Pulp Space on Cone-Beam Computed Tomography Images. A Systematic Review. J Endod. 2024. PMID: 38821262. doi:10.1016/j.joen.2024.05.012

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。