文献速递妇产影像泌尿生殖MR

基于MRI的体素级影像组学与深度学习预测子宫内膜癌微卫星不稳定性:一项双中心研究

Voxel-level Radiomics and Deep Learning Based on MRI for Predicting Microsatellite Instability in Endometrial Carcinoma: A Two-center Study.
PubMed 文献 · Acad Radiol · 2025-09-03

这项双中心回顾性研究纳入375例经病理确诊的子宫内膜癌患者,基于术前多参数MRI(T2WI、DWI、CE-T1WI)构建Vision-Mamba双通道3D深度神经网络,联合体素级影像组学特征预测微卫星不稳定性。外部测试队列AUC为0.866、准确率0.875、敏感度0.833、特异度0.900,优于Vision Transformer、3D-ResNet和传统影像组学模型。

要点

  • 外部测试队列中Vision-Mamba模型AUC 0.866、准确率0.875、敏感度0.833、特异度0.900。
  • 模型融合体素级影像组学特征与多序列MRI,较传统方法更好捕捉肿瘤局部与全局异质性。
  • SHAP分析显示肿瘤实质、强化区域和弥散受限区域对MSI预测起关键作用。

核心结论

  • 体素级影像组学与深度学习模型为无创预测子宫内膜癌MSI状态提供了稳健工具,可能支持个体化治疗决策。

研究设计与样本

  • 双中心回顾性研究,纳入375例经病理确诊的子宫内膜癌患者,术前行多参数MRI(T2WI、DWI、CE-T1WI),MSI状态由免疫组化确定。

关键影像表现/征象

  • 肿瘤区域手动分割后按IBSI指南提取体素级影像组学特征。
  • 构建基于Vision-Mamba架构的双通道3D深度神经网络,联合处理体素级影像组学特征图与MR图像。
  • SHAP分析显示肿瘤实质、强化区域和弥散受限区域对MSI预测起关键作用。

诊断标准与关键数值

  • 外部测试队列:AUC 0.866、准确率0.875、敏感度0.833、特异度0.900。
  • 特征重要性排名前三位为glszm_SizeZoneNonUniformityNormalized、ngtdm_Busyness和glcm_Correlation。

临床应用与阅片要点

  • 模型在中心I队列训练和内部验证,在中心II外部队列测试,表现优于Vision Transformer、3D-ResNet和传统影像组学模型。

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

RATIONALE AND OBJECTIVES: To develop and validate a non-invasive deep learning model that integrates voxel-level radiomics with multi-sequence MRI to predict microsatellite instability (MSI) status in patients with endometrial carcinoma (EC).

METHODS: This two-center retrospective study included 375 patients with pathologically confirmed EC from two medical centers. Patients underwent preoperative multiparametric MRI (T2WI, DWI, CE-T1WI), and MSI status was determined by immunohistochemistry. Tumor regions were manually segmented, and voxel-level radiomics features were extracted following IBSI guidelines. A dual-channel 3D deep neural network based on the Vision-Mamba architecture was constructed to jointly process voxel-wise radiomics feature maps and MR images. The model was trained and internally validated on cohorts from Center I and tested on an external cohort from Center II. Performance was compared with Vision Transformer, 3D-ResNet, and traditional radiomics models. Interpretability was assessed with feature importance ranking and SHAP value visualization.

RESULTS: The Vision-Mamba model achieved strong predictive performance across all datasets. In the external test cohort, it yielded an AUC of 0.866, accuracy of 0.875, sensitivity of 0.833, and specificity of 0.900, outperforming other models. Integrating voxel-level radiomics features with MRI enabled the model to better capture both local and global tumor heterogeneity compared to traditional approaches. Interpretability analysis identified glszm_SizeZoneNonUniformityNormalized, ngtdm_Busyness, and glcm_Correlation as top features, with SHAP analysis revealing that tumor parenchyma, regions of enhancement, and diffusion restriction were pivotal for MSI prediction.

CONCLUSION: The proposed voxel-level radiomics and deep learning model provides a robust, non-invasive tool for predicting MSI status in endometrial carcinoma, potentially supporting personalized treatment decision-making.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Tian CH, Sun P, Xiao KY, et al. Voxel-level Radiomics and Deep Learning Based on MRI for Predicting Microsatellite Instability in Endometrial Carcinoma: A Two-center Study. Acad Radiol. 2025. PMID: 40908231. doi:10.1016/j.acra.2025.08.028

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。