Department of Neurosurgery of Huashan Hospital, State Key Laboratory of Medical Neurobiology, MOE Frontiers Center for Brain Science and Institutes of Brain Science, Fudan University, Shanghai, China.
Department of Radiology, Huashan Hospital, Fudan University, Shanghai, China.
Eur Radiol. 2024 May;34(5):2997-3008. doi: 10.1007/s00330-023-10258-2. Epub 2023 Oct 19.
To establish a deep learning (DL) model for predicting tumor grades and expression of pathologic markers of meningioma.
A total of 1192 meningioma patients from two centers who underwent surgical resection between September 2018 and December 2021 were retrospectively included. The pathological data and post-contrast T1-weight images for each patient were collected. The patients from institute I were subdivided into training, validation, and testing sets, while the patients from institute II served as the external testing cohort. The fine-tuned ResNet50 model based on transfer learning was adopted to classify WHO grade in the whole cohort and predict Ki-67 index, H3K27me3, and progesterone receptor (PR) status of grade 1 meningiomas. The predictive performance was evaluated by the accuracy and loss curve, confusion matrix, receiver operating characteristic curve (ROC), and area under curve (AUC).
The DL prediction model for each label achieved high predictive performance in two cohorts. For WHO grade prediction, the area under the curve (AUC) was 0.966 (95%CI 0.957-0.975) in the internal testing set and 0.669 (95%CI 0.643-0.695) in the external validation cohort. The AUC in predicting Ki-67 index, H3K27me3, and PR status were 0.905 (95%CI 0.895-0.915), 0.773 (95%CI 0.760-0.786), and 0.771 (95%CI 0.750-0.792) in the internal testing set and 0.591 (95%CI 0.562-0.620), 0.658 (95%CI 0.648-0.668), and 0.703 (95%CI 0.674-0.732) in the external validation cohort, respectively.
DL models can preoperatively predict meningioma grades and pathologic marker expression with favorable predictive performance.
Our DL model could predict meningioma grades and expression of pathologic markers and identify high-risk patients with WHO grade 1 meningioma, which would suggest a more aggressive operative intervention preoperatively and a more frequent follow-up schedule postoperatively.
WHO grades and some pathologic markers of meningioma were associated with therapeutic strategies and clinical outcomes. A deep learning-based approach was employed to develop a model for predicting meningioma grades and the expression of pathologic markers. Preoperative prediction of meningioma grades and the expression of pathologic markers was beneficial for clinical decision-making.
建立一种深度学习（DL）模型，用于预测脑膜瘤的肿瘤分级和病理标志物表达。
回顾性纳入 2018 年 9 月至 2021 年 12 月期间在两个中心接受手术切除的 1192 例脑膜瘤患者。收集每位患者的病理数据和增强后 T1 加权图像。研究所 I 的患者分为训练集、验证集和测试集，而研究所 II 的患者作为外部测试队列。采用基于迁移学习的微调 ResNet50 模型对整个队列进行 WHO 分级分类，并预测 1 级脑膜瘤的 Ki-67 指数、H3K27me3 和孕激素受体（PR）状态。通过准确性和损失曲线、混淆矩阵、受试者工作特征曲线（ROC）和曲线下面积（AUC）评估预测性能。
在两个队列中，DL 预测模型对每个标签的预测性能均较高。对于 WHO 分级预测，内部测试集的 AUC 为 0.966（95%CI 0.957-0.975），外部验证集的 AUC 为 0.669（95%CI 0.643-0.695）。在预测 Ki-67 指数、H3K27me3 和 PR 状态方面，内部测试集的 AUC 分别为 0.905（95%CI 0.895-0.915）、0.773（95%CI 0.760-0.786）和 0.771（95%CI 0.750-0.792），外部验证集的 AUC 分别为 0.591（95%CI 0.562-0.620）、0.658（95%CI 0.648-0.668）和 0.703（95%CI 0.674-0.732）。
DL 模型可以术前预测脑膜瘤分级和病理标志物表达，具有良好的预测性能。
我们的 DL 模型可以预测脑膜瘤分级和病理标志物的表达，并识别出 WHO 1 级脑膜瘤的高危患者，这将有助于术前采取更积极的手术干预措施，并在术后进行更频繁的随访。
脑膜瘤的 WHO 分级和一些病理标志物与治疗策略和临床结果相关。采用基于深度学习的方法开发了一种预测脑膜瘤分级和病理标志物表达的模型。术前预测脑膜瘤分级和病理标志物表达有助于临床决策。
