文献速递脊柱关节炎

中轴型脊柱关节炎脊髓骨髓水肿的自动检测:基于两个大型3期试验数据集的训练与验证

Automated detection of spinal bone marrow oedema in axial spondyloarthritis: training and validation using two large phase 3 trial datasets.
PubMed 文献 · Rheumatology (Oxford) · 2025-01-01

研究利用两个3期试验中686例中轴型脊柱关节炎患者的3483次脊髓MRI,训练并验证SpineNet机器学习模型自动评分骨髓水肿,并与专家评分比较。Model 1在放射学阳性与阴性亚组中的AUC分别为0.94与0.97,性能与专家阅片者相当。作者认为机器学习软件在中轴型脊柱关节炎的MRI骨髓水肿自动评估方面具有潜力。

要点

  • Model 1在放射学阳性axSpA数据集AUC 0.94、准确率75.8%、kappa 0.50,与专家阅片间准确率76.8%、kappa 0.47相当。
  • Model 1在放射学阴性axSpA数据集AUC 0.97、准确率74.6%、kappa 0.52,与专家阅片间准确率74.2%、kappa 0.46相当。
  • Model 1在两项数据集中的AUC、准确率和kappa均优于Model 2。

核心结论

  • 机器学习软件在中轴型脊柱关节炎的MRI骨髓水肿自动评估方面显示出潜力,可带来一致性提高、人力成本降低以及阅片者间和阅片者内变异性最小化等益处。

研究设计与样本

  • 研究使用SpineNet软件的中轴型脊柱关节炎患者脊髓MRI数据来自两个临床试验数据集,共3483次MRI、686例患者,用于训练和验证机器学习算法。
  • 评分流程包括椎体检测与标注以及椎体单元骨髓水肿存在与否的分类两个步骤。
  • 测试了两种模型:Model 1不进行手动分割,Model 2包含一个中间手动分割步骤。
  • 模型输出与人类专家评分使用kappa统计量、平衡准确率、敏感度、特异度和AUC进行比较。
  • 试验注册:MEASURE 1研究(NCT01358175)和PREVENT研究(NCT02696031)。

主要发现

  • 在骨髓水肿存在与不存在的判断上,两种模型的表现与专家阅片者相当。
  • 以绝对读者共识评分作为外部参考时,Model 1的AUC为0.94(Model 2为0.88)、准确率为75.8%(Model 2为70.5%)、kappa为0.50(Model 2为0.31)。
  • 在放射学阳性中轴型脊柱关节炎数据集中,专家阅片者间准确率为76.8%、kappa为0.47,Model 1的表现与之相似。
  • 在放射学阴性中轴型脊柱关节炎数据集中,Model 1的AUC为0.97(Model 2为0.91)、准确率为74.6%(Model 2为70%)、kappa为0.52(Model 2为0.27)。
  • 在放射学阴性中轴型脊柱关节炎数据集中,专家阅片者间准确率为74.2%、kappa为0.46,Model 1的表现与之相当。

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)。

原文

OBJECTIVE: To evaluate the performance of machine learning (ML) models for the automated scoring of spinal MRI bone marrow oedema (BMO) in patients with axial spondyloarthritis (axSpA) and compare them with expert scoring. METHODS: ML algorithms using SpineNet software were trained and validated on 3483 spinal MRIs from 686 axSpA patients across two clinical trial datasets. The scoring pipeline involved (i) detection and labelling of vertebral bodies and (ii) classification of vertebral units for the presence or absence of BMO. Two models were tested: Model 1, without manual segmentation, and Model 2, incorporating an intermediate manual segmentation step. Model outputs were compared with those of human experts using kappa statistics, balanced accuracy, sensitivity, specificity and AUC. RESULTS: Both models performed comparably to expert readers, regarding presence vs absence of BMO. Model 1 outperformed Model 2, with an AUC of 0.94 (vs 0.88), accuracy of 75.8% (vs 70.5%) and kappa of 0.50 (vs 0.31) using absolute reader consensus scoring as the external reference; this performance was similar to the expert inter-reader accuracy of 76.8% and kappa of 0.47 in a radiographic axSpA dataset. In a non-radiographic axSpA dataset, Model 1 achieved an AUC of 0.97 (vs 0.91 for Model 2), accuracy of 74.6% (vs 70%) and kappa of 0.52 (vs 0.27), comparable to the expert inter-reader accuracy of 74.2% and kappa of 0.46. CONCLUSION: ML software shows potential for automated MRI BMO assessment in axSpA, offering benefits such as improved consistency, reduced labour costs and minimized inter- and intra-reader variability. TRIAL REGISTRATION: Clinicaltrials.gov, http://clinicaltrials.gov, MEASURE 1 study (NCT01358175); PREVENT study (NCT02696031).

来源:Rheumatology (Oxford),查看原文。版权归原作者所有。

引用

  1. Jamaludin A, Windsor R, Ather S, et al. Automated detection of spinal bone marrow oedema in axial spondyloarthritis: training and validation using two large phase 3 trial datasets. Rheumatology (Oxford). 2025. PMID: 40489668. doi:10.1093/rheumatology/keaf323

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。