Prediction of IDH and TERT promoter mutations in low-grade glioma from magnetic resonance images using a convolutional neural network

Abstract

Identification of genotypes is crucial for treatment of glioma. Here, we developed a method to predict tumor genotypes using a pretrained convolutional neural network (CNN) from magnetic resonance (MR) images and compared the accuracy to that of a diagnosis based on conventional radiomic features and patient age. Multisite preoperative MR images of 164 patients with grade II/III glioma were grouped by IDH and TERT promoter (pTERT) mutations as follows: (1) IDH wild type, (2) IDH and pTERT co-mutations, (3) IDH mutant and pTERT wild type. We applied a CNN (AlexNet) to four types of MR sequence and obtained the CNN texture features to classify the groups with a linear support vector machine. The classification was also performed using conventional radiomic features and/or patient age. Using all features, we succeeded in classifying patients with an accuracy of 63.1%, which was significantly higher than the accuracy obtained from using either the radiomic features or patient age alone. In particular, prediction of the pTERT mutation was significantly improved by the CNN texture features. In conclusion, the pretrained CNN texture features capture the information of IDH and TERT genotypes in grade II/III gliomas better than the conventional radiomic features.

Figure 1

Feature extraction by AlexNet. The lesion image was cut out using a VOI and resized to 243 × 243 pixels. The image was cropped to 227 × 227 pixels with a shift of ±8 pixels and rotated/flipped for data augmentation. The augmented image was input to the pretrained AlexNet to acquire the texture features for classification.

Figure 2

Example of input images. Representative lesion images of each sequence for each molecular subtype of WHO grade II/III gliomas were shown.

Figure 3

Classification accuracy of lesions from normal tissue. The average classification accuracies in all folds of cross-validation are shown with 95% confidence intervals.

Figure 4

Classification accuracy of genotype status for different features. (a–c) Each bar shows the averaged classification accuracy of three molecular subtypes consisting of 1) IDH wild type, 2) IDH and pTERT comutated, and 3) IDH mutant and pTERT wild type (a), the IDH mutation alone (b), or the pTERT mutation alone (c). The label of each bar denotes the features used for the classification: Age, patient age; Radiomics, conventional radiomic features from MR images with three location parameters; CNN, features extracted by AlexNet; CNN + Radiomics + Age, all of these features. The average was calculated from the accuracies, which were balanced among classes, for each test dataset in 10-fold nested cross-validation. Error bars show 95% confidence intervals of the classification accuracy. Dotted lines denote chance level. *p < 0.05, **p < 0.01, and ***p < 0.001 significant difference among different features (one-way ANOVA with a Tukey-Kramer post hoc test).