Classification of Brain Tumor IDH Status using MRI and Deep Learning

• Published in: bioRxiv
• Main Authors: Nalawade, Sahil, Murugesan, Gowtham, Maryam Vejdani Jahromi, Fisicaro, Ryan, Chandan Ganesh Bangalore Yogananda, Wagner, Ben, Mickey, Bruce, Maher, Elizabeth, Pinho, Marco, Fei, Baowei, Madhuranthakam, Ananth, Maldjian, Joseph
• Format: Paper
• Language: English
• Published: Cold Spring Harbor Cold Spring Harbor Laboratory Press 04.09.2019; Cold Spring Harbor Laboratory
• Edition: 1.1
• Subjects: Accuracy; Automation; Brain cancer; Brain tumors; Classification; Deep learning; Glioma; Isocitrate dehydrogenase; Leakage; Magnetic resonance imaging; Mutation; Neuroimaging; Neuroscience; Teaching methods; Deep learning; Convolutional networks; MRI; Isocitrate dehydrogenase (IDH); Tumor classification; Radiomics
• ISSN: 2692-8205; 2692-8205
• DOI: 10.1101/757344

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.