Computational analysis in epilepsy neuroimaging: A survey of features and methods

Abstract

Epilepsy affects 65 million people worldwide, a third of whom have seizures that are resistant to anti-epileptic medications. Some of these patients may be amenable to surgical therapy or treatment with implantable devices, but this usually requires delineation of discrete structural or functional lesion(s), which is challenging in a large percentage of these patients.Advances in neuroimaging and machine learning allow semi-automated detection of malformations of cortical development (MCDs), a common cause of drug resistant epilepsy. A frequently asked question in the field is what techniques currently exist to assist radiologists in identifying these lesions, especially subtle forms of MCDs such as focal cortical dysplasia (FCD) Type I and low grade glial tumors. Below we introduce some of the common lesions encountered in patients with epilepsy and the common imaging findings that radiologists look for in these patients. We then review and discuss the computational techniques introduced over the past 10 years for quantifying and automatically detecting these imaging findings. Due to large variations in the accuracy and implementation of these studies, specific techniques are traditionally used at individual centers, often guided by local expertise, as well as selection bias introduced by the varying prevalence of specific patient populations in different epilepsy centers. We discuss the need for a multi-institutional study that combines features from different imaging modalities as well as computational techniques to definitively assess the utility of specific automated approaches to epilepsy imaging. We conclude that sharing and comparing these different computational techniques through a common data platform provides an opportunity to rigorously test and compare the accuracy of these tools across different patient populations and geographical locations. We propose that these kinds of tools, quantitative imaging analysis methods and open data platforms for aggregating and sharing data and algorithms, can play a vital role in reducing the cost of care, the risks of invasive treatments, and improve overall outcomes for patients with epilepsy.

Recommendations for the use of structural magnetic resonance imaging in the care of patients with epilepsy: A consensus report from the International League Against Epilepsy Neuroimaging Task Force

“…13 This clinical conundrum, currently one of the main barriers to effective epilepsy surgery, has motivated the development of computer-aided methods aimed at quantitatively analyzing morphology and signal of 3D MR images. 12,[67][68][69] However, there are a number of basic steps in data preparation, namely, correction for image intensity nonuniformities, registration, and tissue segmentation, that need to be carefully evaluated by the user, as their quality greatly influences final results. For instance, subject motion negatively impacts tissue segmentation and leads to artifacts that mimic lesions, including atrophy.…”

Surgical advancements in pediatric epilepsy surgery: from the mysterious to the minimally invasive

“…High-resolution structural magnetic resonance imaging (MRI) and voxel-based morphometry algorithms allow quantitative analysis of brain structure to better identify malformations of cortical development (6). Resting-state functional MRI allows the identification of functional brain circuits and the analysis of connectivity without performing tasks.…”

“…Resting-state functional MRI allows the identification of functional brain circuits and the analysis of connectivity without performing tasks. Through these techniques and many more, modern neuroimaging is rapidly evolving to identify previously undetectable lesions and map functionally eloquent neuronal circuits (6,7). The use of minimally invasive intracranial electroencephalography (EEG) recordings using stereotactic depth electrode placement, or stereo EEG (SEEG), facilitated by newly developed robotic technology to allow the efficient, accurate placement of multiple bilateral electrodes, is replacing large craniotomies for intracranial EEG recordings.…”

Adult‐onset temporal lobe epilepsy with nodular gray matter heterotopia

“…This case showed two important clinical issues. First, gray matter heterotopia, which is well known as a cause of childhood epilepsy, is rare as a cause of adult epilepsy, but it needs to be taken into consideration in the differential diagnosis of adult epilepsy . Second, as inverted‐intensity T2‐weighted image make the lesion visible so that we see the problem, the visualization may be particularly useful for diagnosis.…”