Abstract

Background

Glioma prognosis depends on isocitrate dehydrogenase (IDH) mutation status. We aimed to predict the IDH status of gliomas from preoperative MR images using a fully automated hybrid approach with convolutional neural networks (CNNs) and radiomics.

Methods

We reviewed 1166 preoperative MR images of gliomas (grades II–IV) from Severance Hospital (n = 856), Seoul National University Hospital (SNUH; n = 107), and The Cancer Imaging Archive (TCIA; n = 203). The Severance set was subdivided into the development (n = 727) and internal test (n = 129) sets. Based on T1 postcontrast, T2, and fluid-attenuated inversion recovery images, a fully automated model was developed that comprised a CNN for tumor segmentation (Model 1) and CNN-based classifier for IDH status prediction (Model 2) that uses a hybrid approach based on 2D tumor images and radiomic features from 3D tumor shape and loci guided by Model 1. The trained model was tested on internal (a subset of the Severance set) and external (SNUH and TCIA) test sets.

Results

The CNN for tumor segmentation (Model 1) achieved a dice coefficient of 0.86–0.92 across datasets. Our hybrid model achieved accuracies of 93.8%, 87.9%, and 78.8%, with areas under the receiver operating characteristic curves of 0.96, 0.94, and 0.86 and areas under the precision-recall curves of 0.88, 0.82, and 0.81 in the internal test, SNUH, and TCIA sets, respectively.

Conclusions

Our fully automated hybrid model demonstrated the potential to be a highly reproducible and generalizable tool across different datasets for the noninvasive prediction of the IDH status of gliomas.

中文翻译：

---

全自动混合方法，通过深度学习和放射学来预测神经胶质瘤的IDH突变状态

抽象的

背景

脑胶质瘤的预后取决于异柠檬酸脱氢酶（IDH）突变状态。我们旨在使用卷积神经网络（CNN）和放射线学的全自动混合方法从术前MR图像预测神经胶质瘤的IDH状态。

方法

我们回顾了Severance医院（n = 856），首尔国立大学医院（SNUH; n = 107）和癌症影像档案库（TCIA; n = 203）的1166例神经胶质瘤的术前MR图像。遣散费集细分为开发集（n = 727）和内部测试集（n = 129）。基于T1造影后，T2和液体衰减的反转恢复图像，开发了一个全自动模型，该模型包含用于肿瘤分割的CNN（模型1）和基于IDN的CNN分类器 状态预测（模型2），该模型使用基于模型1引导的3D肿瘤形状和基因座的2D肿瘤图像和放射线特征的混合方法，对训练后的模型进行了内部（遣散费集的子集）和外部（SNUH和TCIA）测试仪。

结果

各个数据集的CNN用于肿瘤分割（模型1）的骰子系数为0.86-0.92。我们的混合模型在内部测试中实现了93.8％，87.9％和78.8％的精度，接收器工作特性曲线下的面积为0.96、0.94和0.86，精确召回曲线下的面积为0.88、0.82和0.81。 ，SNUH和TCIA集。

结论

我们的全自动混合模型证明了在神经胶质瘤IDH状态的非侵入性预测中，跨不同数据集的高度可复制和通用化工具的潜力。