Convolutional Neural Networks for Pediatric Refractory Epilepsy Classification Using Resting-State Functional Magnetic Resonance Imaging.

Objective: This study aims to evaluate the performance of convolutional neural networks (CNNs) trained with resting-state functional magnetic resonance imaging (rfMRI) latency data in the classification of patients with pediatric epilepsy from healthy controls.

Methods: Preoperative rfMRI and anatomic magnetic resonance imaging scans were obtained from 63 pediatric patients with refractory epilepsy and 259 pediatric healthy controls. Latency maps of the temporal difference between rfMRI and the global mean signal were calculated using voxel-wise cross-covariance.

In situ study of the metal-insulator transition in VO2 by EELS and ab initio calculations.

Changes in the dielectric properties during the thermochromic transition of commercial VO(2) powders were determined in situ, by analyzing the low-loss region of the electron energy-loss spectroscopy (EELS) spectra in a transmission electron microscope at room temperature (insulator phase) and 100 degrees C (metallic phase). A comparison of experimental EELS spectra and ab initio density-functional theory calculations (WIEN2k code) within the generalized gradient approximation (GGA) is presented. A characteristic peak around 5.