Gowtham Krishnan Murugesan

This paper develops a deep learning model using T2-w MRI to predict MGMT promoter methylation in gliomas, achieving higher accuracy than histological methods.

This paper develops a deep learning model using T2-weighted MRI to classify 1p/19q co-deletion status in brain gliomas with high accuracy.

This study evaluates motion artifact effects on glioma marker classification using deep learning and develops a motion correction network to restore classification accuracy.

This paper develops a deep learning method for automated brain tumor segmentation and survival prediction using MRI data from the BraTS2019 dataset, achieving high segmentation accuracy and moderate survival prediction performance.

The paper withdraws its manuscript due to errors in analysis and requests it not be cited.

The paper develops and ensembles 2D/3D segmentation models for brain tumors using multiresolution inputs, achieving high DICE scores and survival prediction accuracy on BRATS 2019 data.

This paper develops a deep learning model to predict IDH mutation status from T2-weighted MRI scans of brain tumors, achieving 83.8% test accuracy.