文献速递神经MR

通过混合影像组学和深度学习特征在多中心MRI协议下实现可重复的脑膜瘤分级

Reproducible meningioma grading across multi-center MRI protocols via hybrid radiomic and deep learning features.
PubMed 文献 · Neuroradiology · 2025-08-18

本研究纳入3523例经组织学确诊的脑膜瘤患者(1900例低级别,1623例高级别),从T1增强和T2加权MRI提取影像组学特征与3D自编码器深度学习特征,结合机器学习模型进行术前分级。T1增强图像上联合特征获得最高AUC 95.85%和准确率95.18%,T2加权图像上最佳AUC 94.12%和准确率93.14%;215个特征中127个ICC>0.75,显示多中心数据集上的一致性。

要点

  • 联合影像组学与深度学习特征在T1增强图像上分级性能最高,AUC 95.85%、准确率95.18%。
  • T1增强端到端3D自编码器AUC 92.15%、准确率91.14%、敏感度92.48%,优于T2加权模型。
  • 215个特征中127个ICC>0.75,提示多中心MRI协议下特征可重复性较高。

核心结论

  • 所提框架有效整合影像组学与深度学习特征,为脑膜瘤分级提供稳健、无创且可重复的方法。

研究设计与样本

  • 研究纳入3523例组织学确诊的脑膜瘤患者,其中低级别(I级)1900例、高级别(II和III级)1623例。

诊断标准与关键数值

  • T1增强图像联合影像组学与深度学习特征:AUC 95.85%、准确率95.18%;T2加权图像最佳AUC 94.12%、准确率93.14%;T1增强端到端3D自编码器AUC 92.15%、准确率91.14%、敏感度92.48%;215个特征中127个ICC>0.75。

临床应用与阅片要点

  • 作者认为该框架可提供稳健、无创且可重复的脑膜瘤分级方法。

局限性

  • 未来研究应在真实临床环境中验证该框架。
  • 未来研究应探索加入临床参数以提升其预后价值。

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

OBJECTIVE: This study aimed to create a reliable method for preoperative grading of meningiomas by combining radiomic features and deep learning-based features extracted using a 3D autoencoder. The goal was to utilize the strengths of both handcrafted radiomic features and deep learning features to improve accuracy and reproducibility across different MRI protocols.

MATERIALS AND METHODS: The study included 3,523 patients with histologically confirmed meningiomas, consisting of 1,900 low-grade (Grade I) and 1,623 high-grade (Grades II and III) cases. Radiomic features were extracted from T1-contrast-enhanced and T2-weighted MRI scans using the Standardized Environment for Radiomics Analysis (SERA). Deep learning features were obtained from the bottleneck layer of a 3D autoencoder integrated with attention mechanisms. Feature selection was performed using Principal Component Analysis (PCA) and Analysis of Variance (ANOVA). Classification was done using machine learning models like XGBoost, CatBoost, and stacking ensembles. Reproducibility was evaluated using the Intraclass Correlation Coefficient (ICC), and batch effects were harmonized with the ComBat method. Performance was assessed based on accuracy, sensitivity, and the area under the receiver operating characteristic curve (AUC).

RESULTS: For T1-contrast-enhanced images, combining radiomic and deep learning features provided the highest AUC of 95.85% and accuracy of 95.18%, outperforming models using either feature type alone. T2-weighted images showed slightly lower performance, with the best AUC of 94.12% and accuracy of 93.14%. Deep learning features performed better than radiomic features alone, demonstrating their strength in capturing complex spatial patterns. The end-to-end 3D autoencoder with T1-contrast images achieved an AUC of 92.15%, accuracy of 91.14%, and sensitivity of 92.48%, surpassing T2-weighted imaging models. Reproducibility analysis showed high reliability (ICC > 0.75) for 127 out of 215 features, ensuring consistent performance across multi-center datasets.

CONCLUSIONS: The proposed framework effectively integrates radiomic and deep learning features to provide a robust, non-invasive, and reproducible approach for meningioma grading. Future research should validate this framework in real-world clinical settings and explore adding clinical parameters to enhance its prognostic value.

来源:Neuroradiology,查看原文。版权归原作者所有。

引用

  1. Saadh MJ, Albadr RJ, Sur D, et al. Reproducible meningioma grading across multi-center MRI protocols via hybrid radiomic and deep learning features. Neuroradiology. 2025. PMID: 40824403. doi:10.1007/s00234-025-03725-8

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。