基于三维分割CT扫描的全下肢膝骨关节炎自动地标定位方法准确性评估
本研究提出一套评估方案,对30例骨关节炎下肢三维CT图像中的87个股骨、胫骨、腓骨和髌骨地标进行自动定位准确性评估,以两名有经验临床医生手动定位作为参考标准。操作者内和操作者间变异性平均中位误差分别为2.0 mm和2.3 mm,手动与自动定位方法间平均中位误差为2.4 mm,约42%的自动地标位于其边界框内。
要点
- 自动地标定位与手动定位的平均中位误差为2.4 mm,范围0.0至22.8 mm。
- 操作者内平均中位误差2.0 mm,操作者间平均中位误差2.3 mm,自动方法误差置信区间与二者一致。
- 约42%的自动地标位于边界框内,框外地标距框平均距离1.4 mm。
核心结论
- 自动地标定位误差与手动定位的操作者内和操作者间变异性置信区间一致,误差随地标位置和坐标不同而变化;手动分割定义参考标准存在困难,强调需要严格的地标定位验证评估方案。
研究设计与样本
- 方法学研究,对30例骨关节炎下肢三维CT分割图像中的87个地标(股骨、胫骨、腓骨、髌骨)进行评估,以两名有经验临床医生手动定位为参考标准,量化操作者内和操作者间变异性,并按相同流程评估自动地标定位与手动定位的距离。
诊断标准与关键数值
- 操作者内变异性:平均中位误差2.0 mm,最大42.1 mm。
- 操作者间变异性:误差范围0.0至43.5 mm,所有地标平均中位误差2.3 mm。
- 手动与自动定位方法间:平均中位误差2.4 mm,范围0.0至22.8 mm。
- 约42%的自动地标位于其边界框内,框外地标距框平均距离1.4 mm。
局限性
- 手动分割定义参考标准存在困难,操作者内和操作者间变异性提示这一点。
- 结果强调需要严格的地标定位验证评估方案,包括统计检验假设的验证和群体大小的影响。
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)。
英文原文(摘要)· 点击展开
In preoperative planning, a number of techniques for registration of anatomical landmarks on bones, or "bones landmarking", have been developed for automatic measurement of lower limbs. However, the evaluation of these techniques is often neglected, reducing confidence in results and limiting clinical applications. We propose a protocol to evaluate landmarking techniques applied to thirty 3D images of osteoarthritic lower limbs. The protocol includes the evaluation of the ground truth based on manual landmarking performed by two experienced clinicians. Intra- and inter-operator variability were quantified. Automatic landmarking was evaluated using the same procedure and compared to manual landmarking by computing distances with bounding boxes including manual landmarks. The method was applied to 87 landmarks on the femur, tibia, fibula, and patella. For intra-operator variability, the mean median error was 2.0 mm, with a maximum of 42.1 mm. For inter-operator variability, errors ranged from 0.0 to 43.5 mm, with a mean median error of 2.3 mm across all landmarks. The mean median error between manual and automatic landmarking methods was 2.4 mm, with a range from 0.0 mm to 22.8 mm. Confidence intervals of automatic landmarking errors were consistent with intra- and inter-operator variability confidence intervals. Approximately 42 % of the automatic landmarks were inside their bounding boxes, with a mean distance of 1.4 mm from the box for landmarks on the outside. Results showed different errors depending on landmark location and coordinates. Intra- and inter-operator variability shed light on the difficulty of defining ground truth based on manual segmentation. This finding emphasizes the need for a rigorous evaluation protocol for landmarking validation, including the verification of statistical test hypotheses and population size influence.
引用
- Horteur C, Fougeron N, Gaulin B, et al. Accuracy evaluation of an automatic landmarking method based on 3D segmented CT scans of full lower limbs with knee osteoarthritis. Eur J Radiol. 2025. PMID: 40652606. doi:10.1016/j.ejrad.2025.112292
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。