A Review of the Surgical Procedures for the Treatment of Drug-Resistant Epilepsy and Their Seizure Control Outcomes

Background: Drug-resistant epilepsy can be defined as the existence of seizures within 6 months, despite adequate therapy regimens with one or more antiepileptic drugs. Epilepsy surgery has been the standard therapy to help those patients who suffer from drug-resistant epilepsy. The goal of this surgery is to halt or reduce the intensity of seizures. This literature review aims to provide an overview of existing surgical procedures for the treatment of drug-resistant epilepsy and the degree of seizure control they provide based on available literature. Methods: Data were collected from medical journal databases, aggregators, and individual publications. The most used databases were PubMed, Medline and NCBI. Some of the keywords used to search these databases include: “drug resistant epilepsy”, “seizure control”, and “neurosurgery”. Results: Epileptic surgery is divided into resective and non-resective procedures. Studies have shown that a full resection of the epileptogenic brain area increases the probability of seizure eradication, however, the risks of postoperative impairments grow as the resection area is extended. On the other hand, patients who are unsuitable for seizure focus removal by resective surgery, such as those with multifocal seizures or overlapping epileptogenic zone with a functional cortex, may benefit from non-resective surgical options such as Vagus Nerve Stimulation and Responsive Neurostimulation. Conclusion: This literature review discusses the comprehensive treatment of epilepsy, especially the surgical treatment of drug-resistant epilepsy. The reviewed studies have shown that epilepsy surgery has promising outcomes in achieving seizure freedom/reducing seizure frequency with minimal adverse effects when performed correctly with the appropriate choice of surgical candidates.

Bridging finite element and deep learning: High-resolution stress distribution prediction in structural components

Finite-element analysis(FEA)for structures has been broadly used to conduct stress analysis of various civil and mechanical engineering structures.Conventional methods,such as FEA,provide high fidelity results but require the solution of large linear systems that can be computationally intensive.Instead,Deep Learning(DL)techniques can generate results significantly faster than conventional run-time analysis.This can prove extremely valuable in real-time structural assessment applications.Our proposed method uses deep neural networks in the form of convolutional neural networks(CNN)to bypass the FEA and predict high-resolution stress distributions on loaded steel plates with variable loading and boundary conditions.The CNN was designed and trained to use the geometry,boundary conditions,and load as input to predict the stress contours.The proposed technique’s performance was compared to finite-element simulations using a partial differential equation(PDE)solver.The trained DL model can predict the stress distributions with a mean absolute error of 0.9%and an absolute peak error of 0.46%for the von Mises stress distribution.This study shows the feasibility and potential of using DL techniques to bypass FEA for stress analysis applications.