文献速递骨肌DR

基于深度学习方法在Laurin位自动测量髌股关节参数

Automatic measurement of the patellofemoral joint parameters in the Laurin view: a deep learning-based approach.
PubMed 文献 · Eur Radiol · 2022-07-05

回顾性收集1431例Laurin位髌股关节影像,开发U-Net模型自动分割标志点并计算沟角、适合角、髌股比和外侧髌骨倾斜角。在201例留出测试集中,模型与三位放射科医师测量的参考标准相比ICC为0.85-0.97,除髌股比外其余参数均在95%一致性界限内。

要点

  • U-Net模型可自动分割髌股关节标志点并计算SA、CA、PFR和LPT。
  • 留出测试集中模型与参考标准ICC为0.85-0.97,平均绝对差0.06-5.09。
  • 除PFR外,其余参数测量值与参考标准均在95%一致性界限内。

核心结论

  • 基于U-Net的深度学习方法在自动测量SA、CA、PFR和LPT方面具有较高的模型性能。

研究设计与样本

  • 回顾性研究,连续收集1431例Laurin位髌股关节影像,分为模型开发集(数据集1,n=1230)和留出测试集(数据集2,n=201);开发U-Net模型分割髌股关节标志点并计算参数;以三位放射科医师独立测量值的均值作为参考标准。

诊断标准与关键数值

  • 在留出测试集中,U-Net预测SA、CA、PFR和LPT与参考标准相比ICC=0.85-0.97,平均绝对差=0.06-5.09,均方根=0.09-6.90;除PFR外,其余参数测量值与参考标准均在95%一致性界限内。

临床应用与阅片要点

  • U-Net模型可用于分割髌股关节标志点并计算SA、CA、PFR和LPT,以评估髌骨不稳;在留出测试中自动测量模型表现与参考标准相当;该模型在髌骨不稳和/或髌股骨关节炎患者中仍能准确预测SA、CA、PFR和LPT。

局限性

  • 原文未报告局限性。

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

OBJECTIVES: To explore the performance of a deep learning-based algorithm for automatic patellofemoral joint (PFJ) parameter measurements from the Laurin view.

METHODS: A total of 1431 consecutive Laurin views of the PFJ were retrospectively collected and divided into two parts: (1) the model development dataset (dataset 1, n = 1230) and (2) the hold-out test set (dataset 2, n = 201). Dataset 1 was used to develop the U-shaped fully convolutional network (U-Net) model to segment the landmarks of the PFJ. Based on the predicted landmarks, the PFJ parameters were calculated, including the sulcus angle (SA), congruence angle (CA), patellofemoral ratio (PFR), and lateral patellar tilt (LPT). Dataset 2 was used to assess the model performance. The mean of three radiologists who independently measured the PFJ parameters was defined as the reference standard. Model performance was assessed by the intraclass correlation coefficient (ICC), mean absolute difference (MAD), and root mean square (RMS) compared to the reference standard. Ninety-five percent limits of agreement (95% LoA) were calculated pairwise for each radiologist, reference standard, and model.

RESULTS: Compared with the reference standard, U-Net showed good performance for predicting SA, CA, PFR, and LPT, with ICC = 0.85-0.97, MAD = 0.06-5.09, and RMS = 0.09-6.90 in the hold-out test set. Except for the PFR, the remaining parameters measured between the reference standard and the model were within the 95% LoA in the hold-out test dataset.

CONCLUSIONS: The U-Net-based deep learning approach had a relatively high model performance in automatically measuring SA, CA, PFR, and LPT.

KEY POINTS: • The U-Net model could be used to segment the landmarks of the PFJ and calculate the SA, CA, PFR, and LPT, which could be used to evaluate the patellar instability. • In the hold-out test, the automatic measurement model yielded comparable performance with reference standard. • The automatic measurement model could still accurately predict SA, CA, PFR, and LPT in patients with PI and/or PFOA.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. E T, Nai R, Liu X, et al. Automatic measurement of the patellofemoral joint parameters in the Laurin view: a deep learning-based approach. Eur Radiol. 2022. PMID: 35788755. doi:10.1007/s00330-022-08967-1

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。