文献速递神经肿瘤

整合卷积神经网络、影像组学与语义的多模态模型预测胶质母细胞瘤分子亚型与预后

Predicting glioblastoma molecular subtypes and prognosis with a multimodal model integrating convolutional neural network, radiomics, and semantics.
PubMed 文献 · J Neurosurg · 2022-12-02

研究纳入训练集222例、验证集107例胶质母细胞瘤患者,构建整合MRI图像、影像报告语义与临床信息的多模态CNN模型预测分子亚型与1年预后。基于C3D的模型预测IDH1突变准确率最高达91.11%,外部验证中IDH1、ATRX、MGMT及1年预后组准确率分别为88.30%、76.67%、85.71%、85.71%。

要点

  • 基于C3D的模型预测IDH1突变状态准确率最高,达91.11%。
  • 加入语义特征使MGMT启动子甲基化预测精确率提高11.21%、召回率提高14.28%。
  • 外部验证中C3D模型在IDH1、ATRX、MGMT及1年预后组准确率均显著优于3D ResNet50。

核心结论

  • 作者提出整合C3D、影像组学与语义的多模态模型,在预测胶质母细胞瘤IDH1、ATRX、MGMT分子亚型及1年预后方面表现良好。

研究设计与样本

  • 训练集纳入中山大学肿瘤防治中心222例胶质母细胞瘤患者,验证集纳入中山大学肿瘤防治中心、首都医科大学宣武医院和吉林大学第一医院共107例胶质母细胞瘤患者。
  • 多模态模型以MR图像(增强前后T1加权和T2加权)、对应MRI印象及临床患者信息训练,原始图像用Multimodal Brain Tumor Image Segmentation Benchmark工具包分割。
  • 卷积特征用3D残差深度神经网络(ResNet50)和卷积3D(C3D)提取,影像组学特征用pyradiomics提取,报告文本用word2vec转换为词嵌入,三类特征整合后训练神经网络。
  • 采用准确率、精确率、召回率和F1分数评价模型性能。

主要发现

  • 基于C3D的模型预测IDH1突变状态准确率最高,为91.11%。
  • 加入语义特征使MGMT启动子甲基化状态预测的精确率提高11.21%、召回率提高14.28%。
  • 基于C3D的模型在IDH1、ATRX、MGMT和1年预后组的受试者工作特征曲线下面积分别为0.976、0.953、0.955和0.976。
  • 外部验证中基于C3D的模型在IDH1、ATRX、MGMT和1年预后组准确率分别为88.30%、76.67%、85.71%和85.71%,相比3D ResNet50的83.51%、66.67%、82.14%和70.79%均有显著提高。

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)。

原文

OBJECTIVE: The aim of this study was to build a convolutional neural network (CNN)-based prediction model of glioblastoma (GBM) molecular subtype diagnosis and prognosis with multimodal features. METHODS: In total, 222 GBM patients were included in the training set from Sun Yat-sen University Cancer Center (SYSUCC) and 107 GBM patients were included in the validation set from SYSUCC, Xuanwu Hospital Capital Medical University, and the First Hospital of Jilin University. The multimodal model was trained with MR images (pre- and postcontrast T1-weighted images and T2-weighted images), corresponding MRI impression, and clinical patient information. First, the original images were segmented using the Multimodal Brain Tumor Image Segmentation Benchmark toolkit. Convolutional features were extracted using 3D residual deep neural network (ResNet50) and convolutional 3D (C3D). Radiomic features were extracted using pyradiomics. Report texts were converted to word embedding using word2vec. These three types of features were then integrated to train neural networks. Accuracy, precision, recall, and F1-score were used to evaluate the model performance. RESULTS: The C3D-based model yielded the highest accuracy of 91.11% in the prediction of IDH1 mutation status. Importantly, the addition of semantics improved precision by 11.21% and recall in MGMT promoter methylation status prediction by 14.28%. The areas under the receiver operating characteristic curves of the C3D-based model in the IDH1, ATRX, MGMT, and 1-year prognosis groups were 0.976, 0.953, 0.955, and 0.976, respectively. In external validation, the C3D-based model showed significant improvement in accuracy in the IDH1, ATRX, MGMT, and 1-year prognosis groups, which were 88.30%, 76.67%, 85.71%, and 85.71%, respectively (compared with 3D ResNet50: 83.51%, 66.67%, 82.14%, and 70.79%, respectively). CONCLUSIONS: The authors propose a novel multimodal model integrating C3D, radiomics, and semantics, which had a great performance in predicting IDH1, ATRX, and MGMT molecular subtypes and the 1-year prognosis of GBM.

来源:J Neurosurg,查看原文。版权归原作者所有。

引用

  1. Zhong S, Ren JX, Yu ZP, et al. Predicting glioblastoma molecular subtypes and prognosis with a multimodal model integrating convolutional neural network, radiomics, and semantics. J Neurosurg. 2022. PMID: 36461822. doi:10.3171/2022.10.JNS22801

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。