This is a retraction of: Chandan Ganesh Bangalore Yogananda, Bhavya R Shah, Maryam Vejdani-Jahromi, Sahil S Nalawade, Gowtham K Murugesan, Frank F Yu, Marco C Pinho, Benjamin C Wagner, Bruce Mickey, Toral R Patel, Baowei Fei, Ananth J Madhuranthakam, Joseph A Maldjian, A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas, Neuro-Oncology, Volume 22, Issue 3, March 2020, Pages 402–411, https://doi.org/10.1093/neuonc/noz199
The authors of this article discovered 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, which caused the reported accuracies from the TCIA/TCGA data set to be artificially inflated. Although the data have now been re-analyzed, the corrected accuracies, while promising, do not outperform other reported methods for IDH molecular marker prediction using MRI. Due to this unfortunate error, the authors have requested that the article be fully retracted. The authors apologize to the readers and reviewers of Neuro-Oncology. As a consequence of this article’s retraction, the corresponding Editorial Commentary is also retracted by the Journal (Kaufmann TJ, Erickson BJ, Can my computer tell me if this tumor is IDH mutated? Neuro-Oncology 2020 22(3); 311–312. https://doi.org/10.1093/neuonc/noaa002.