Zhu Yuanpeng, Yin Xiangjie, Chen Zefu, Zhang Haoran, Xu Kexin, Zhang Jianguo, Wu Nan
Department of Orthopedic Surgery, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences, Beijing, 100730, China.
Beijing Key Laboratory for Genetic Research of Skeletal Deformity, Beijing, 100730, China.
Spine Deform. 2025 Jan;13(1):19-27. doi: 10.1007/s43390-024-00954-4. Epub 2024 Sep 25.
This study aims to provide an overview of different deep learning algorithms (DLAs), identify the limitations, and summarize potential solutions to improve the performance of DLAs.
We reviewed eligible studies on DLAs for automated Cobb angle estimation on X-rays and conducted a meta-analysis. A systematic literature search was conducted in six databases up until September 2023. Our meta-analysis included an evaluation of reported circular mean absolute error (CMAE) from the studies, as well as a subgroup analysis of implementation strategies. Risk of bias was assessed using the revised Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). This study was registered in PROSPERO prior to initiation (CRD42023403057).
We identified 120 articles from our systematic search (n = 3022), eventually including 50 studies in the systematic review and 17 studies in the meta-analysis. The overall estimate for CMAE was 2.99 (95% CI 2.61-3.38), with high heterogeneity (94%, p < 0.01). Segmentation-based methods showed greater accuracy (p < 0.01), with a CMAE of 2.40 (95% CI 1.85-2.95), compared to landmark-based methods, which had a CMAE of 3.31 (95% CI 2.89-3.72).
According to our limited meta-analysis results, DLAs have shown relatively high accuracy for automated Cobb angle measurement. In terms of CMAE, segmentation-based methods may perform better than landmark-based methods. We also summarized potential ways to improve model design in future studies. It is important to follow quality guidelines when reporting on DLAs.
本研究旨在概述不同的深度学习算法（DLA），识别其局限性，并总结提高DLA性能的潜在解决方案。
我们回顾了关于用于X射线自动测量Cobb角的DLA的合格研究，并进行了荟萃分析。截至2023年9月，在六个数据库中进行了系统的文献检索。我们的荟萃分析包括对研究报告的圆形平均绝对误差（CMAE）的评估，以及实施策略的亚组分析。使用修订后的诊断准确性研究质量评估（QUADAS-2）评估偏倚风险。本研究在启动前已在PROSPERO注册（CRD42023403057）。
我们从系统检索中识别出120篇文章（n = 3022），最终在系统评价中纳入50项研究，在荟萃分析中纳入17项研究。CMAE的总体估计值为2.99（95%CI 2.61-3.38），异质性较高（94%，p < 0.01）。与基于标志点的方法相比，基于分割的方法显示出更高的准确性（p < 0.01），CMAE为2.40（95%CI 1.85-2.95），而基于标志点的方法CMAE为3.31（95%CI 2.89-3.72）。
根据我们有限的荟萃分析结果，DLA在自动测量Cobb角方面显示出相对较高的准确性。就CMAE而言，基于分割的方法可能比基于标志点的方法表现更好。我们还总结了未来研究中改进模型设计的潜在方法。在报告DLA时遵循质量指南很重要。
