文献速递类风湿关节炎

autoscoRA:深度学习自动进行类风湿关节炎影像学损伤的Sharp/van der Heijde评分

autoscoRA: Deep Learning to Automate Sharp/van der Heijde Scoring of Radiographic Damage in Rheumatoid Arthritis.
PubMed 文献 · Arthritis Rheumatol · 2026-04-21

研究开发了全自动深度学习系统autoscoRA,用于对类风湿关节炎患者手和足X线片进行Sharp/van der Heijde(SvdH)评分。在包含769例患者、12144张X线片的数据集上,模型在关节间隙狭窄、骨侵蚀及总SvdH评分上与人类评分者一致性极好(组内相关系数0.9),并在检测纵向进展方面平均一致性达70%。

要点

  • autoscoRA可全自动提取关节并评分关节间隙狭窄与骨侵蚀。
  • 模型与人类评分者总SvdH评分的组内相关系数为0.9。
  • 检测纵向进展时与人类读者平均一致性为70%。

核心结论

  • autoscoRA这种自动化系统可用于促进临床试验、登记研究和观察性研究中的影像学关节损伤评分,并最终用于常规临床护理。

研究设计与样本

  • 使用迄今最大的成人类风湿关节炎数据集训练基于深度学习的autoscoRA系统,自动完成关节提取及关节间隙狭窄和骨侵蚀评分。
  • 数据集包括769例患者(其中155例在测试集),共3437次访视(707次在测试集)和12144张X线片(2507张在测试集)。

主要发现

  • 模型在关节水平和总SvdH评分上与人类评分者对关节间隙狭窄、骨侵蚀及联合评分均达到极好一致性(组内相关系数0.9)。
  • 在由第二位人类读者评分的子集上,模型与第一位人类读者的一致性优于第二位人类读者。
  • autoscoRA在检测关节损伤纵向进展方面与人类读者一致性良好,在不同SvdH评分截断值定义进展时平均一致性为70%。

关键数值与推荐

  • 总SvdH评分与人类评分者的组内相关系数为0.9。
  • 检测纵向进展时与人类读者平均一致性为70%。

临床怎么用

  • 可用于临床试验、登记研究和观察性研究中辅助影像学关节损伤评分。
  • 未来可能应用于常规临床护理。

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

OBJECTIVE: Regular imaging by conventional radiography to assess for joint damage is a cornerstone in the management of rheumatoid arthritis. Scoring systems to quantify such damage, such as the widely used Sharp/van der Heijde (SvdH) score, are limited by the requirement of time and experienced staff as well as intra- and interrater variability. To alleviate these problems, autoscoRA, a fully automated scoring system to assign SvdH scores to radiographs of the hands and feet was developed. METHODS: Using the hitherto largest data set of adult patients with rheumatoid arthritis, autoscoRA, a deep learning-based system, was trained to automatically perform joint extraction and scoring of joint space narrowing and bone erosion. RESULTS: The data set included 769 patients (155 of whom were in the test set) with 3,437 visits (707) and 12,144 radiographs (2,507). The model reached excellent agreement with a human scorer for joint space narrowing, erosion, and combined scores both on the joint level and for summed total SvdH scores (intraclass correlation 0.9). On a subset of data scored by a second human reader, the model outperformed the former in terms of agreement with the first human reader. In addition, autoscoRA demonstrated good agreement with a human reader for detecting longitudinal progression of joint damage across different SvdH score cutoffs defining the presence of progression (average agreement of 70%). CONCLUSION: Automated systems like autoscoRA could be used to facilitate scoring of radiographic joint damage in clinical trials, registries, and observational studies, and, eventually, routine clinical care.

来源:Arthritis Rheumatol,查看原文。版权归原作者所有。

引用

  1. Deimel T, Weiser PJ, Urschler M, et al. autoscoRA: Deep Learning to Automate Sharp/van der Heijde Scoring of Radiographic Damage in Rheumatoid Arthritis. Arthritis Rheumatol. 2026. PMID: 42011795. doi:10.1002/art.70196

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。