Magnetic resonance imaging-based deep learning for predicting subtypes of glioma.

Abstract

Purpose: To explore the value of deep learning based on magnetic resonance imaging (MRI) in the classification of glioma subtypes.

Methods: This study retrospectively included 747 adult patients with surgically pathologically confirmed gliomas from a public database and 64 patients from our hospital. Patients were classified into IDH-wildtype (IDHwt) (490 cases), IDH-mutant/1p19q-noncodeleted (IDHmut-intact) (105 cases), and IDH-mutant/1p19q-codeleted (IDHmut-codel) (216 cases) based on their pathological findings, with the public database of patients were divided into training and validation sets, and patients from our hospital were used as an independent test set. The models were developed based on five categories of preoperative T1-weighted, T1-weighted gadolinium contrast-enhanced, T2-weighted and T2-weighted fluid-attenuated inversion recovery (T1w, T1c, T2w and FLAIR) magnetic resonance imaging (MRI) of four sequences and mixed imaging of the four sequences, respectively. The receiver operating characteristic curve (ROC), area under the curve (AUC) of the ROC were generated in the jupyter notebook tool using python language to evaluate the accuracy of the models in classification and comparing the predictive value of different MRI sequences.

Results: IDHwt, IDHmut-intact and IDHmut-codel were the best classified in the model containing only FLAIR sequences, with test set AUCs of 0.790, 0.737 and 0.820, respectively; and the worst classified in the model containing only T1w sequences, with test set AUCs of 0.621, 0.537 and 0.760, respectively.

Conclusion: We have developed a set of models that can effectively classify glioma subtypes and that work best when only the FLAIR sequence model is included.