深度学习影像组学模型可能有助于提高脑膜瘤术前分级的预测性能
本研究纳入132例经病理证实的脑膜瘤患者(训练队列105例,测试队列27例),基于增强T1WI提取影像组学特征和深度学习特征,采用SMOTE平衡样本后以LightGBM算法构建深度学习影像组学模型(DLRM),并与影像组学模型(RM)和深度学习模型(DLM)比较。DLRM在训练队列和测试队列中区分低级别与高级别脑膜瘤的AUC分别为0.988和0.935,优于RM(0.980和0.918)和DLM(0.892和0.718)。结论认为DLRM对脑膜瘤分级的无创个体化预测具有良好性能,临床实用性优于影像组学特征。
要点
- DLRM在测试队列区分低级别与高级别脑膜瘤的AUC为0.935,优于RM的0.918和DLM的0.718。
- DLRM在测试队列的准确率、敏感度和特异度分别为0.926、0.900和0.924。
- 基于增强T1WI的DLRM可能有助于脑膜瘤术前无创分级预测。
核心结论
- 基于增强T1WI的SMOTE-DLRM对脑膜瘤分级的无创个体化预测具有良好性能,临床实用性优于影像组学特征。
研究设计与样本
- 回顾性研究,连续纳入132例经病理证实的脑膜瘤患者,分为训练队列105例和测试队列27例;从增强T1WI(轴位和矢状位)提取影像组学特征,从轴位肿瘤最大层面提取深度学习特征;采用SMOTE平衡样本数,以LightGBM算法构建DLRM,并类似方法构建RM和DLM进行对比;采用ROC分析评估鉴别效能。
诊断标准与关键数值
- DLRM区分低级别与高级别脑膜瘤的AUC在训练队列为0.988、测试队列为0.935;RM的AUC在训练队列为0.980、测试队列为0.918;DLM的AUC在训练队列为0.892、测试队列为0.718;DLRM在测试队列的准确率为0.926、敏感度为0.900、特异度为0.924。
临床应用与阅片要点
- 原文结论认为DLRM对脑膜瘤分级的无创个体化预测具有良好性能,临床实用性优于影像组学特征,可能有助于提高术前分级的预测性能。
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
PURPOSE: This study aimed to investigate the clinical usefulness of the enhanced-T1WI-based deep learning radiomics model (DLRM) in differentiating low- and high-grade meningiomas.
METHODS: A total of 132 patients with pathologically confirmed meningiomas were consecutively enrolled (105 in the training cohort and 27 in the test cohort). Radiomics features and deep learning features were extracted from T1 weighted images (T1WI) (both axial and sagittal) and the maximum slice of the axial tumor lesion, respectively. Then, the synthetic minority oversampling technique (SMOTE) was utilized to balance the sample numbers. The optimal discriminative features were selected for model building. LightGBM algorithm was used to develop DLRM by a combination of radiomics features and deep learning features. For comparison, a radiomics model (RM) and a deep learning model (DLM) were constructed using a similar method as well. Differentiating efficacy was determined by using the receiver operating characteristic (ROC) analysis.
RESULTS: A total of 15 features were selected to construct the DLRM with SMOTE, which showed good discrimination performance in both the training and test cohorts. The DLRM outperformed RM and DLM for differentiating low- and high-grade meningiomas (training AUC: 0.988 vs. 0.980 vs. 0.892; test AUC: 0.935 vs. 0.918 vs. 0.718). The accuracy, sensitivity, and specificity of the DLRM with SMOTE were 0.926, 0.900, and 0.924 in the test cohort, respectively.
CONCLUSION: The DLRM with SMOTE based on enhanced T1WI images has favorable performance for noninvasively individualized prediction of meningioma grades, which exhibited favorable clinical usefulness superior over the radiomics features.
引用
- Yang, Xu, Zhang, et al. A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma. Neuroradiology. 2022. PMID: 35037985. doi:10.1007/s00234-022-02894-0
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。