Erratum: A novel fully automated MRI-based deep-learning method for classification of 1p/19q co-deletion status in brain gliomas (Neuro-Oncology Advances (2020) 2:Supplement 4 DOI: 10.1093/noajnl/vdaa066)

This is a correction to: Neuro-Oncology Advances, Volume 2, Issue Supplement 4, December 2020, doi: 10.1093/noajnl/ vdaa066. There was an error in the python code for the 3-fold cross validation procedure. This resulted in the use of the training cases instead of the set-aside test cases for the molecular marker accuracy testing procedure. This caused our reported accuracies from the TCIA/TCGA data set to be artificially inflated. The corrected accuracies for Table 1 (computed using nnU-Net1), along with the updated ROC curve for Figure 3 are provided here. The updated accuracies, while encouraging, do not outperform other reported methods for 1p/19q molecular marker prediction using MRI. (Table Presented).