Multimodal Imaging of Cognitive Networks in Epilepsy:
This study addresses how structural, functional, and diffusion imaging can be used to predict
postoperative outcomes in three important cognitive domains: language, memory, and executive functioning. First, neural activations are examined in frontal, temporal, and parietal regions using task-related and resting-state functional MRI (fMRI) to probe the brain networks that underlie language, memory and executive functioning in patients with TLE. Second, the integrity of critical white matter fiber tracts is quantified using an advanced diffusion technique,
restriction spectrum imaging (RSI). Third, the hippocampal volume is quantified from structural MRI (sMRI). Fourth, information from fMRI, RSI, and sMRI is combined to predict individual risk for surgically-induced cognitive changes on measures of language, memory, and executive functioning. This study strives to improve health outcomes in patients with epilepsy (18-65 years) by using advanced, non-invasive technology to identify individual predictors of cognitive decline that can help to guide surgical decisions and possibly reduce morbidity associated with the removal of eloquent cortex.
Prediction of seizure lateralization and postoperative outcome through the use of deep learning applied to multi-site MRI/DTI data: An ENIGMA-Epilepsy study
This study leverages data collected through
ENIGMA-Epilepsy to test whether deep learning approaches improve upon a prediction of seizure lateralization or postoperative outcomes compared to simpler, user-driven models. Our primary aim will be to test the ability of
dense neural networks to lateralize the seizure focus compared to support vector machines (SVM). In an exploratory aim, we will test the ability of our model to predict postoperative seizure outcomes. ENIGMA’s harmonized approach allows us to test our approach in over 24 datasets, diverse in age, ethnicity, age of onset, epilepsy duration, and surgical outcomes.