Classification of Brain Tumor IDH Status using MRI and Deep Learning

Abstract

Isocitrate dehydrogenase (IDH) mutation status is an important marker in glioma diagnosis and therapy. We propose a novel automated pipeline for predicting IDH status noninvasively using deep learning and T2-weighted (T2w) MR images with minimal preprocessing (N4 bias correction and normalization to zero mean and unit variance). T2w MRI and genomic data were obtained from The Cancer Imaging Archive dataset (TCIA) for 260 subjects (120 High grade and 140 Low grade gliomas). A fully automated 2D densely connected model was trained to classify IDH mutation status on 208 subjects and tested on another held-out set of 52 subjects, using 5-fold cross validation. Data leakage was avoided by ensuring subject separation during the slice-wise randomization. Mean classification accuracy of 90.5% was achieved for each axial slice in predicting the three classes of no tumor, IDH mutated and IDH wild-type. Test accuracy of 83.8% was achieved in predicting IDH mutation status for individual subjects on the test dataset of 52 subjects. We demonstrate a deep learning method to predict IDH mutation status using T2w MRI alone. Radiologic imaging studies using deep learning methods must address data leakage (subject duplication) in the randomization process to avoid upward bias in the reported classification accuracy.

Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2–4 glioma patients: a deep Radiomics Approach

“…Our model with noteworthy AUC and sensitivity may help in the above-mentioned situation. Finally, the acquired satisfactory and encouraging results are in accordance with other multi-scanner and multi-centre studies, which have reported realistic generalisable prediction rates for noninvasive IDH mutation status determination [19,56,57].…”

“…We claim that such a combination benefits feature extraction given the small number of samples. Model performance often degrades using multi-scanner and multi-centre cohorts, as shown by similar work using the Cancer Imaging Archive (TCIA) which studied structural images rather than DTI [56,57]. On the other hand, we have an unbalanced cohort as expected because IDH1 or IDH2 mutations are common in 70-80% of gliomas [10,29].…”