In this paper we propose a method for predicting the status of MGMT promoter methylation in high-grade gliomas. From available MR images, segment tumor using deep convolutional neural networks and extract both radiomic features shape learned by variational autoencoder. We implemented standard machine learning workflow to obtain predictions, consisting feature selection followed training random ...

abstract   purpose: the aim of this study was to report the main ct scan and mri findings of gliomas in a group of iranian patients. material and methods: the mri and ct scan of 96 pathologically proven patients of gliomas were retrospectively evaluated in a period of five years in our university affiliated hospital. we included all cases who had both ct scan and mri in our study. results: amon...

Abstract PURPOSE Though patients with glioblastoma generally have poor overall survival (OS), OS estimates range significantly. We sought to develop a radiomics-based model predictive of in using preoperative MRI scans identify these differences and guide clinical care. METHODS The primary endpoint was OS, determined from the date surgery death or last follow-up. T1, FLAIR, T2, post-contrast T1...

Abstract An artificial intelligence (AI) model’s performance is strongly influenced by the input features. Therefore, it vital to find optimal feature set. It more crucial for survival prediction of glioblastoma multiforme (GBM) type brain tumor. In this study, we identify best set predicting days (SD) GBM patients that outrank current state-of-the-art methodologies. The proposed approach an en...

Sixty-five patients with dilated cardiomyopathy underwent 24 hour electrocardiographic monitoring: 62 (95.4%) showed ventricular arrhythmias and 52 (80%) complex ventricular arrhythmias (multiform ventricular extrasystoles, paired ventricular extrasystoles and ventricular tachycardia). Complex ventricular arrhythmias correlated significantly with some haemodynamic indices of ventricular dysfunc...