文献速递骨肌MR

基于MRI的深度学习影像组学用于诊断与中轴型脊柱关节炎相关的骶髂关节炎

Use of MRI-based deep learning radiomics to diagnose sacroiliitis related to axial spondyloarthritis.
PubMed 文献 · Eur J Radiol · 2024-02-01

该回顾性研究纳入485例经骶髂关节MRI诊断的与中轴型脊柱关节炎相关的骶髂关节炎患者(n=288)或非骶髂关节炎患者(n=197),随机分为训练组(n=388)和测试组(n=97),采用3D U-Net自动分割骶髂关节,并用ResNet50、ResNet101和DenseNet121诊断,通过堆叠方法构建集成模型,最终将深度学习影像组学特征与临床因素结合构建联合模型,联合模型诊断性能最高(AUC 0.910,准确率0.856),优于最佳集成模型(AUC 0.868,准确率0.825)(均P<0.05)。

要点

  • 联合模型诊断axSpA相关骶髂关节炎AUC 0.910、准确率0.856,优于最佳集成模型AUC 0.868、准确率0.825(均P<0.05)。
  • ResNet50作为最优基础模型,AUC和准确率分别为0.839和0.804。
  • 自动深度学习分割与手动勾画显示良好相关性。

核心结论

  • 将深度学习影像组学特征与临床因素结合构建的联合模型对axSpA相关骶髂关节炎具有 excellent 诊断性能(AUC 0.910,准确率0.856)。

研究设计与样本

  • 回顾性研究,纳入2018年5月至2022年10月经骶髂关节MRI诊断的axSpA相关骶髂关节炎(n=288)或非骶髂关节炎(n=197)患者共485例,随机分为训练组(n=388)和测试组(n=97);数据来自三台MRI扫描仪;采用3D U-Net卷积神经网络自动分割骶髂关节,用ResNet50、ResNet101和DenseNet121三种CNN基于单模态诊断,通过堆叠方法构建集成模型,以最优集成模型作为DLR特征,并用多变量logistic回归结合临床因素构建联合模型;用ROC曲线、校准曲线和决策曲线分析(DCA)评估模型性能。

诊断标准与关键数值

  • ResNet50作为最优基础模型,AUC 0.839,准确率0.804。
  • 联合模型诊断axSpA相关骶髂关节炎AUC 0.910,准确率0.856。
  • 最佳集成模型AUC 0.868,准确率0.825;联合模型优于最佳集成模型(均P<0.05)。
  • 自动深度学习分割与手动勾画显示良好相关性。

临床应用与阅片要点

  • 作者认为联合模型在诊断axSpA相关骶髂关节炎中具有 excellent 诊断性能。
  • DCA显示联合模型具有良好的临床效用。

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: This study aimed to evaluate the performance of a deep learning radiomics (DLR) model, which integrates multimodal MRI features and clinical information, in diagnosing sacroiliitis related to axial spondyloarthritis (axSpA).

MATERIAL &amp; METHODS: A total of 485 patients diagnosed with sacroiliitis related to axSpA (n = 288) or non-sacroiliitis (n = 197) by sacroiliac joint (SIJ) MRI between May 2018 and October 2022 were retrospectively included in this study. The patients were randomly divided into training (n = 388) and testing (n = 97) cohorts. Data were collected using three MRI scanners. We applied a convolutional neural network (CNN) called 3D U-Net for automated SIJ segmentation. Additionally, three CNNs (ResNet50, ResNet101, and DenseNet121) were used to diagnose axSpA-related sacroiliitis using a single modality. The prediction results of all the CNN models across different modalities were integrated using a stacking method based on different algorithms to construct ensemble models, and the optimal ensemble model was used as DLR signature. A combined model incorporating DLR signature with clinical factors was developed using multivariable logistic regression. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).

RESULTS: Automated deep learning-based segmentation and manual delineation showed good correlation. ResNet50, as the optimal basic model, achieved an area under the curve (AUC) and accuracy of 0.839 and 0.804, respectively. The combined model yielded the highest performance in diagnosing axSpA-related sacroiliitis (AUC: 0.910; accuracy: 0.856) and outperformed the best ensemble model (AUC: 0.868; accuracy: 0.825) (all P < 0.05). Moreover, the DCA showed good clinical utility in the combined model.

CONCLUSION: We developed a diagnostic model for axSpA-related sacroiliitis by combining the DLR signature with clinical factors, which resulted in excellent diagnostic performance.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang K, Liu C, Pan J, et al. Use of MRI-based deep learning radiomics to diagnose sacroiliitis related to axial spondyloarthritis. Eur J Radiol. 2024. PMID: 38325189. doi:10.1016/j.ejrad.2024.111347

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。