Background Isocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. Currently, reliable IDH mutation determination requires invasive surgical procedures. The purpose of this study was to develop a highly-accurate, MRI-based, voxel-wise deep-learning IDH-classification network using T2-weighted (T2w) MR images and compare its performance to a multi-contrast network. Methods Multi-parametric brain MRI data and corresponding genomic information were obtained for 214 subjects (94 IDH-mutated, 120 IDH wild-type) from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). Two separate networks were developed including a T2w image only network (T2-net) and a multi-contrast (T2w, FLAIR, and T1 post-contrast) network (TS-net) to perform IDH classification and simultaneous single label tumor segmentation. The networks were trained using 3D-Dense-UNets. Three-fold cross-validation was performed to generalize the networks’ performance. ROC analysis was also performed. Dice-scores were computed to determine tumor segmentation accuracy. Results T2-net demonstrated a mean cross-validation accuracy of 97.14% ±0.04 in predicting IDH mutation status, with a sensitivity of 0.97 ±0.03, specificity of 0.98 ±0.01, and an AUC of 0.98 ±0.01.  TS-net achieved a mean cross-validation accuracy of 97.12% ±0.09, with a sensitivity of 0.98 ±0.02, specificity of 0.97 ±0.001, and an AUC of 0.99 ±0.01. The mean whole tumor segmentation Dice-scores were 0.85 ±0.009 for T2-net and 0.89 ±0.006 for TS-net. Conclusion We demonstrate high IDH classification accuracy using only T2-weighted MR images. This represents an important milestone towards clinical translation.

BackgroundIsocitrate dehydrogenase (IDH) mutation status has emerged as an important prognostic marker in gliomas. Currently, reliable IDH mutation determination requires invasive surgical procedures. The purpose of this study was to develop a highly-accurate, MRI-based, voxel-wise deep-learning IDH-classification network using T2-weighted (T2w) MR images and compare its performance to a multi-contrast network.MethodsMulti-parametric brain MRI data and corresponding genomic information were obtained for 214 subjects (94 IDH-mutated, 120 IDH wild-type) from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). Two separate networks were developed including a T2w image only network (T2-net) and a multi-contrast (T2w, FLAIR, and T1 post-contrast), network (TS-net) to perform IDH classification and simultaneous single label tumor segmentation. The networks were trained using 3D-Dense-UNets. A three-fold cross-validation was performed to generalize the networks’ performance. ROC analysis was also performed. Dice-scores were computed to determine tumor segmentation accuracy.ResultsT2-net demonstrated a mean cross-validation accuracy of 97.14% +/-0.04 in predicting IDH mutation status, with a sensitivity of 0.97 +/-0.03, specificity of 0.98 +/-0.01, and an AUC of 0.98 +/-0.01. TS-net achieved a mean cross-validation accuracy of 97.12% +/-0.09, with a sensitivity of 0.98 +/-0.02, specificity of 0.97 +/-0.001, and an AUC of 0.99 +/-0.01. The mean whole tumor segmentation Dice-scores were 0.85 +/-0.009 for T2-net and 0.89 +/-0.006 for TS-net.ConclusionWe demonstrate high IDH classification accuracy using only T2-weighted MRI. This represents an important milestone towards clinical translation.Keypoints – 1IDH status is an important prognostic marker for gliomas. 2. We developed a non-invasive, MRI based, highly accurate deep-learning method for the determination of IDH status 3. The deep-learning networks utilizes only T2 weighted MR images to predict IDH status thereby facilitating clinical translation.IMPORTANCE OF THE STUDYOne of the most important recent discoveries in brain glioma biology has been the identification of the isocitrate dehydrogenase (IDH) mutation status as a marker for therapy and prognosis. The mutated form of the gene confers a better prognosis and treatment response than gliomas with the non-mutated or wild-type form. Currently, the only reliable way to determine IDH mutation status is to obtain glioma tissue either via an invasive brain biopsy or following open surgical resection. The ability to non-invasively determine IDH mutation status has significant implications in determining therapy and predicting prognosis. We developed a highly accurate, deep learning network that utilizes only T2-weighted MR images and outperforms previously published methods. The high IDH classification accuracy of our T2w image only network (T2-net) marks an important milestone towards clinical translation. Imminent clinical translation is feasible because T2-weighted MR imaging is widely available and routinely performed in the assessment of gliomas.

No abstract

Background One of the most important recent discoveries in brain glioma biology has been the identification of the isocitrate dehydrogenase (IDH) mutation and 1p/19q co-deletion status as markers for therapy and prognosis. 1p/19q co-deletion is the defining genomic marker for oligodendrogliomas and confers a better prognosis and treatment response than gliomas without it. Our group has previously developed a highly accurate deep-learning network for determining IDH mutation status using T2-weighted (T2w) MRI only. The purpose of this study was to develop a similar 1p/19q deep-learning classification network. Methods Multiparametric brain MRI and corresponding genomic information were obtained for 368 subjects from The Cancer Imaging Archive and The Cancer Genome Atlas. 1p/19 co-deletions were present in 130 subjects. Two-hundred and thirty-eight subjects were non-co-deleted. A T2w image-only network (1p/19q-net) was developed to perform 1p/19q co-deletion status classification and simultaneous single-label tumor segmentation using 3D-Dense-UNets. Three-fold cross-validation was performed to generalize the network performance. Receiver operating characteristic analysis was also performed. Dice scores were computed to determine tumor segmentation accuracy. Results 1p/19q-net demonstrated a mean cross-validation accuracy of 93.46% across the 3 folds (93.4%, 94.35%, and 92.62%, SD = 0.8) in predicting 1p/19q co-deletion status with a sensitivity and specificity of 0.90 ± 0.003 and 0.95 ± 0.01, respectively and a mean area under the curve of 0.95 ± 0.01. The whole tumor segmentation mean Dice score was 0.80 ± 0.007. Conclusion We demonstrate high 1p/19q co-deletion classification accuracy using only T2w MR images. This represents an important milestone toward using MRI to predict glioma histology, prognosis, and response to treatment.

We developed a fully automated method for brain tumor segmentation using deep learning; 285 brain tumor cases with multiparametric magnetic resonance images from the BraTS2018 data set were used. We designed 3 separate 3D-Dense-UNets to simplify the complex multiclass segmentation problem into individual binary-segmentation problems for each subcomponent. We implemented a 3-fold cross-validation to generalize the network's performance. The mean cross-validation Dice-scores for whole tumor (WT), tumor core (TC), and enhancing tumor (ET) segmentations were 0.92, 0.84, and 0.80, respectively. We then retrained the individual binary-segmentation networks using 265 of the 285 cases, with 20 cases held-out for testing. We also tested the network on 46 cases from the BraTS2017 validation data set, 66 cases from the BraTS2018 validation data set, and 52 cases from an independent clinical data set. The average Dice-scores for WT, TC, and ET were 0.90, 0.84, and 0.80, respectively, on the 20 held-out testing cases. The average Dice-scores for WT, TC, and ET on the BraTS2017 validation data set, the BraTS2018 validation data set, and the clinical data set were as follows: 0.90, 0.80, and 0.78; 0.90, 0.82, and 0.80; and 0.85, 0.80, and 0.77, respectively. A fully automated deep learning method was developed to segment brain tumors into their subcomponents, which achieved high prediction accuracy on the BraTS data set and on the independent clinical data set. This method is promising for implementation into a clinical workflow.