PDF(Pubmed)
Abstract：
OBJECTIVE: This systematic review and meta-analysis aimed to investigate the accuracy and efficiency of artificial intelligence (AI)-driven automated landmark detection for cephalometric analysis on two-dimensional (2D) lateral cephalograms and three-dimensional (3D) cone-beam computed tomographic (CBCT) images.
METHODS: An electronic search was conducted in the following databases: PubMed, Web of Science, Embase, and grey literature with search timeline extending up to January 2024.
METHODS: Studies that employed AI for 2D or 3D cephalometric landmark detection were included.
METHODS: The selection of studies, data extraction, and quality assessment of the included studies were performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A meta-analysis was conducted to evaluate the accuracy of the 2D landmarks identification based on both mean radial error and standard error.
RESULTS: Following the removal of duplicates, title and abstract screening, and full-text reading, 34 publications were selected. Amongst these, 27 studies evaluated the accuracy of AI-driven automated landmarking on 2D lateral cephalograms, while 7 studies involved 3D-CBCT images. A meta-analysis, based on the success detection rate of landmark placement on 2D images, revealed that the error was below the clinically acceptable threshold of 2 mm (1.39 mm; 95% confidence interval: 0.85-1.92 mm). For 3D images, meta-analysis could not be conducted due to significant heterogeneity amongst the study designs. However, qualitative synthesis indicated that the mean error of landmark detection on 3D images ranged from 1.0 to 5.8 mm. Both automated 2D and 3D landmarking proved to be time-efficient, taking less than 1 min. Most studies exhibited a high risk of bias in data selection (n = 27) and reference standard (n = 29).
CONCLUSIONS: The performance of AI-driven cephalometric landmark detection on both 2D cephalograms and 3D-CBCT images showed potential in terms of accuracy and time efficiency. However, the generalizability and robustness of these AI systems could benefit from further improvement.
BACKGROUND: PROSPERO: CRD42022328800.
METHODS: An electronic search was conducted in the following databases: PubMed, Web of Science, Embase, and grey literature with search timeline extending up to January 2024.
METHODS: Studies that employed AI for 2D or 3D cephalometric landmark detection were included.
METHODS: The selection of studies, data extraction, and quality assessment of the included studies were performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A meta-analysis was conducted to evaluate the accuracy of the 2D landmarks identification based on both mean radial error and standard error.
RESULTS: Following the removal of duplicates, title and abstract screening, and full-text reading, 34 publications were selected. Amongst these, 27 studies evaluated the accuracy of AI-driven automated landmarking on 2D lateral cephalograms, while 7 studies involved 3D-CBCT images. A meta-analysis, based on the success detection rate of landmark placement on 2D images, revealed that the error was below the clinically acceptable threshold of 2 mm (1.39 mm; 95% confidence interval: 0.85-1.92 mm). For 3D images, meta-analysis could not be conducted due to significant heterogeneity amongst the study designs. However, qualitative synthesis indicated that the mean error of landmark detection on 3D images ranged from 1.0 to 5.8 mm. Both automated 2D and 3D landmarking proved to be time-efficient, taking less than 1 min. Most studies exhibited a high risk of bias in data selection (n = 27) and reference standard (n = 29).
CONCLUSIONS: The performance of AI-driven cephalometric landmark detection on both 2D cephalograms and 3D-CBCT images showed potential in terms of accuracy and time efficiency. However, the generalizability and robustness of these AI systems could benefit from further improvement.
BACKGROUND: PROSPERO: CRD42022328800.
摘要：
目的：本系统综述和荟萃分析旨在研究人工智能（AI）驱动的自动界标检测对二维（2D）侧位头颅图和三维（3D）锥形束计算机断层扫描（CBCT）图像进行头颅测量分析的准确性和效率。
方法：在以下数据库中进行了电子搜索：PubMed，WebofScience,Embase,和灰色文献，搜索时间表延长至2024年1月。
方法：包括使用AI进行2D或3D头颅标志检测的研究。
方法：研究的选择，数据提取,纳入研究的质量评估由两名评审员独立进行.使用诊断准确性研究质量评估2工具评估偏倚风险。进行了荟萃分析，以基于平均径向误差和标准误差评估2D界标识别的准确性。
结果：删除重复项之后，标题和摘要筛选，全文阅读，选择了34种出版物。其中,27项研究评估了人工智能驱动的自动界标在2D侧脑图上的准确性，而7项研究涉及3D-CBCT图像。荟萃分析，基于二维图像上地标放置的成功率，显示误差低于临床可接受的阈值2mm（1.39mm;95％置信区间：0.85-1.92mm）。对于3D图像，由于研究设计之间的显著异质性，无法进行荟萃分析。然而,定性综合表明，在3D图像上进行界标检测的平均误差在1.0到5.8mm之间。事实证明，自动2D和3D地标具有时效性，服用少于1分钟。大多数研究在数据选择（n=27）和参考标准（n=29）方面表现出很高的偏倚风险。
结论：AI驱动的头颅标志检测在2D头图和3D-CBCT图像上的表现在准确性和时间效率方面显示出潜力。然而,这些人工智能系统的通用性和鲁棒性可以从进一步的改进中受益。
背景：PROSPERO：CRD42022328800。
方法：在以下数据库中进行了电子搜索：PubMed，WebofScience,Embase,和灰色文献，搜索时间表延长至2024年1月。
方法：包括使用AI进行2D或3D头颅标志检测的研究。
方法：研究的选择，数据提取,纳入研究的质量评估由两名评审员独立进行.使用诊断准确性研究质量评估2工具评估偏倚风险。进行了荟萃分析，以基于平均径向误差和标准误差评估2D界标识别的准确性。
结果：删除重复项之后，标题和摘要筛选，全文阅读，选择了34种出版物。其中,27项研究评估了人工智能驱动的自动界标在2D侧脑图上的准确性，而7项研究涉及3D-CBCT图像。荟萃分析，基于二维图像上地标放置的成功率，显示误差低于临床可接受的阈值2mm（1.39mm;95％置信区间：0.85-1.92mm）。对于3D图像，由于研究设计之间的显著异质性，无法进行荟萃分析。然而,定性综合表明，在3D图像上进行界标检测的平均误差在1.0到5.8mm之间。事实证明，自动2D和3D地标具有时效性，服用少于1分钟。大多数研究在数据选择（n=27）和参考标准（n=29）方面表现出很高的偏倚风险。
结论：AI驱动的头颅标志检测在2D头图和3D-CBCT图像上的表现在准确性和时间效率方面显示出潜力。然而,这些人工智能系统的通用性和鲁棒性可以从进一步的改进中受益。
背景：PROSPERO：CRD42022328800。
