可解释多参数深度学习实现脑膜瘤全自动分割与无创分级
本研究基于257例病理确诊脑膜瘤患者的术前T2和T1C MRI,构建两阶段深度学习模型用于分割和分级,并在61例外部队列验证。联合T1C和T2模型外部队列分割Dice系数0.910,分级AUC 0.770(95%CI 0.644-0.895),准确率72.1%,敏感度73.3%,特异度71.7%,均高于人类阅片者。RCAM显示模型关注肿瘤边缘区域特征。
要点
- 联合T1C和T2的深度学习模型可全自动分割脑膜瘤并无创预测分级。
- 外部队列分级AUC 0.770,准确率72.1%,优于人类阅片者(AUC 0.675-0.690)。
- RCAM提示模型分级依据肿瘤边缘区域特征,阅片时可关注瘤缘表现。
核心结论
- 联合T1C和T2的可解释多参数深度学习模型能够实现脑膜瘤的全自动分割与无创分级,并在外部验证中表现稳健。
研究设计与样本
- 研究为回顾性多中心(机构训练集加外部验证集)深度学习模型开发与验证研究。
- 训练集纳入257例病理确诊脑膜瘤患者(低级别162例,高级别95例),均行术前脑MRI包括T2和T1C。
- 外部验证集纳入61例脑膜瘤患者(低级别46例,高级别15例)。
- 模型基于多参数三维U-net和ResNet构建两阶段分割与分类深度学习分级模型。
- 采用Relevance-weighted Class Activation Mapping(RCAM)解释深度学习特征对分级的贡献。
关键影像表现/征象
- RCAM显示深度学习分级模型的激活图位于脑膜瘤表面区域,提示模型识别肿瘤边缘特征用于分级。
诊断标准与关键数值
- 外部队列联合T1C和T2模型分割Dice系数为0.910。
- 外部队列联合T1C和T2模型分级AUC为0.770(95%CI 0.644-0.895),准确率72.1%,敏感度73.3%,特异度71.7%。
- 联合模型分级AUC和准确率高于人类阅片者(AUC 0.675-0.690,准确率65.6-68.9%)。
临床应用与阅片要点
- 日常阅片可关注脑膜瘤边缘区域特征,与模型RCAM提示的分级依据相印证。
- 联合T1C和T2序列信息有助于提高无创分级性能,优于单序列模型。
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: To establish a robust interpretable multiparametric deep learning (DL) model for automatic noninvasive grading of meningiomas along with segmentation.
METHODS: In total, 257 patients with pathologically confirmed meningiomas (162 low-grade, 95 high-grade) who underwent a preoperative brain MRI, including T2-weighted (T2) and contrast-enhanced T1-weighted images (T1C), were included in the institutional training set. A two-stage DL grading model was constructed for segmentation and classification based on multiparametric three-dimensional U-net and ResNet. The models were validated in the external validation set consisting of 61 patients with meningiomas (46 low-grade, 15 high-grade). Relevance-weighted Class Activation Mapping (RCAM) method was used to interpret the DL features contributing to the prediction of the DL grading model.
RESULTS: On external validation, the combined T1C and T2 model showed a Dice coefficient of 0.910 in segmentation and the highest performance for meningioma grading compared to the T2 or T1C only models, with an area under the curve (AUC) of 0.770 (95% confidence interval: 0.644-0.895) and accuracy, sensitivity, and specificity of 72.1%, 73.3%, and 71.7%, respectively. The AUC and accuracy of the combined DL grading model were higher than those of the human readers (AUCs of 0.675-0.690 and accuracies of 65.6-68.9%, respectively). The RCAM of the DL grading model showed activated maps at the surface regions of meningiomas indicating that the model recognized the features at the tumor margin for grading.
CONCLUSIONS: An interpretable multiparametric DL model combining T1C and T2 can enable fully automatic grading of meningiomas along with segmentation.
KEY POINTS: • The multiparametric DL model showed robustness in grading and segmentation on external validation. • The diagnostic performance of the combined DL grading model was higher than that of the human readers. • The RCAM interpreted that DL grading model recognized the meaningful features at the tumor margin for grading.
引用
- Jun, Park, Shin, et al. Intelligent noninvasive meningioma grading with a fully automatic segmentation using interpretable multiparametric deep learning. Eur Radiol. 2023. PMID: 37052658. doi:10.1007/s00330-023-09590-4
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。