Engineering Commons^™

Seizure Detection Using Deep Learning, Information Theoretic Measures And Factor Graphs, Bahareh Salafian

Electronic Thesis and Dissertation Repository

Epilepsy is a common neurological disorder that disrupts normal electrical activity in the brain causing severe impact on patients’ daily lives. Accurate seizure detection based on long-term time-series electroencephalogram (EEG) signals has gained vital importance for epileptic seizure diagnosis. However, visual analysis of these recordings is a time-consuming task for neurologists. Therefore, the purpose of this thesis is to propose an automatic hybrid model-based /data-driven algorithm that exploits inter-channel and temporal correlations. Hence, we use mutual information (MI) estimator to compute correlation between EEG channels as spatial features and employ a carefully designed 1D convolutional neural network (CNN) to extract …

A Framework For Evaluating Cortical Architectural Anomalies In Temporal Lobe Epilepsy Patients, Hossein Rajali

Electronic Thesis and Dissertation Repository

Focal cortical dysplasia (FCD) are localized regions of malformed cerebral cortex that are frequently associated with drug-resistant epilepsy. Currently, there is a lack of research towards providing quantitative methods for characterizing minor abnormalities in cortical architecture, hindering efforts to determine whether removal affects surgical outcome, and define potential imaging correlates. In our work, we have developed a tool to extract relevant features associated with cortical architectural abnormalities that can deal with artifacts including cortical layer distortions and morphological differences caused by cortical folding effects, and processing artifacts due to improper sectioning. This framework was applied to detect abnormalities across multiple …

Histological Quantification In Temporal Lobe Epilepsy, Charlotte Anne Blinston

Electronic Thesis and Dissertation Repository

Approximately 30 percent of epilepsy patients suffer from refractory temporal lobe epilepsy which is commonly treated with resection of the epileptogenic tissue. However, surgical treatment presents many challenges in locating the epileptogenic focus and thus not all patients become seizure-free following surgery. Advances in techniques can lead to improved localization of the epileptogenic zone and may be validated by correlating MRI with neuropathology of the excised cortical tissue. Focal cortical dysplasias are a neuropathological group of cortical malformations that are often found in cases of refractory epilepsy, however, they are subtle and difficult to quantify. The purpose of this research …

Multivariate Analysis Of Mr Images In Temporal Lobe Epilepsy, Diego H. Cantor-Rivera

Electronic Thesis and Dissertation Repository

Epilepsy stands aside from other neurological diseases because clinical patterns of progression are unknown: The etiology of each epilepsy case is unique and so it is the individual prognosis. Temporal lobe epilepsy (TLE) is the most frequent type of focal epilepsy and the surgical excision of the hippocampus and the surrounding tissue is an accepted treatment in refractory cases, specially when seizures become frequent increasingly affecting the performance of daily tasks and significantly decreasing the quality of life of the patient. The sensitivity of clinical imaging is poor for patients with no hippocampal involvement and invasive procedures such as the …

Magnetic Resonance Imaging And Histology Correlation In The Neocortex In Temporal Lobe Epilepsy., Maged Goubran, Robert R Hammond, Sandrine De Ribaupierre, Jorge G Burneo, Seyed Mirsattari, David A Steven, Andrew G Parrent, Terry M Peters, Ali R Khan

Robarts Imaging Publications

OBJECTIVE: To investigate the histopathological correlates of quantitative relaxometry and diffusion tensor imaging (DTI) and to determine their efficacy in epileptogenic lesion detection for preoperative evaluation of focal epilepsy.

METHODS: We correlated quantitative relaxometry and DTI with histological features of neuronal density and morphology in 55 regions of the temporal lobe neocortex, selected from 13 patients who underwent epilepsy surgery. We made use of a validated nonrigid image registration protocol to obtain accurate correspondences between in vivo magnetic resonance imaging and histology images.

RESULTS: We found T1 to be a predictor of neuronal density in the neocortical gray matter (GM) …

Registration Of In-Vivo To Ex-Vivo Mri Of Surgically Resected Specimens: A Pipeline For Histology To In-Vivo Registration., Maged Goubran, Sandrine De Ribaupierre, Robert R Hammond, Catherine Currie, Jorge G Burneo, Andrew G Parrent, Terry M Peters, Ali R Khan

Robarts Imaging Publications

BACKGROUND: Advances in MRI have the potential to improve surgical treatment of epilepsy through improved identification and delineation of lesions. However, validation is currently needed to investigate histopathological correlates of these new imaging techniques. The purpose of this work is to develop and evaluate a protocol for deformable image registration of in-vivo to ex-vivo resected brain specimen MRI. This protocol, in conjunction with our previous work on ex-vivo to histology registration, completes a registration pipeline for histology to in-vivo MRI, enabling voxel-based validation of novel and existing MRI techniques with histopathology.

NEW METHOD: A combination of image-based and landmark-based 3D …

Quantitative Relaxometry And Diffusion Mri For Lateralization In Mts And Non-Mts Temporal Lobe Epilepsy., Ali R Khan, Maged Goubran, Sandrine De Ribaupierre, Robert R Hammond, Jorge G Burneo, Andrew G Parrent, Terry M Peters

Robarts Imaging Publications

We developed novel methodology for investigating the use of quantitative relaxometry (T1 and T2) and diffusion tensor imaging (DTI) for lateralization in temporal lobe epilepsy. Patients with mesial temporal sclerosis confirmed by pathology (N=8) and non-MTS unilateral temporal lobe epilepsy (N=6) were compared against healthy controls (N=19) using voxel-based analysis restricted to the anterior temporal lobes, and laterality indices for each MRI metric (T1, T2, fractional anisotropy (FA), mean diffusivity, axial and radial diffusivities) were computed based on the proportion of significant voxels on each side. The diffusivity metrics were the most lateralizing MRI metrics in MTS and non-MTS subsets, …

Detection Of Temporal Lobe Epilepsy Using Support Vector Machines In Multi-Parametric Quantitative Mr Imaging., Diego Cantor-Rivera, Ali R Khan, Maged Goubran, Seyed M Mirsattari, Terry M Peters

Robarts Imaging Publications

The detection of MRI abnormalities that can be associated to seizures in the study of temporal lobe epilepsy (TLE) is a challenging task. In many cases, patients with a record of epileptic activity do not present any discernible MRI findings. In this domain, we propose a method that combines quantitative relaxometry and diffusion tensor imaging (DTI) with support vector machines (SVM) aiming to improve TLE detection. The main contribution of this work is two-fold: on one hand, the feature selection process, principal component analysis (PCA) transformations of the feature space, and SVM parameterization are analyzed as factors constituting a classification …

Image Registration Of Ex-Vivo Mri To Sparsely Sectioned Histology Of Hippocampal And Neocortical Temporal Lobe Specimens., Maged Goubran, Cathie Crukley, Sandrine De Ribaupierre, Terence M Peters, Ali R Khan

Robarts Imaging Publications

Intractable or drug-resistant epilepsy occurs in up to 30% of epilepsy patients, with many of these patients undergoing surgical excision of the affected brain region to achieve seizure control. Recent magnetic resonance imaging (MRI) sequences and analysis techniques have the potential to detect abnormalities not identified with diagnostic MRI protocols. Prospective studies involving pre-operative imaging and collection of surgically-resected tissue provide a unique opportunity for verification and tuning of these image analysis techniques, since direct comparison can be made against histopathology, and can lead to better prediction of surgical outcomes and potentially less invasive procedures. To carry out MRI and …

Fusion And Visualization Of Intraoperative Cortical Images With Preoperative Models For Epilepsy Surgical Planning And Guidance., A Wang, S M Mirsattari, A G Parrent, T M Peters

Robarts Imaging Publications

OBJECTIVE: During epilepsy surgery it is important for the surgeon to correlate the preoperative cortical morphology (from preoperative images) with the intraoperative environment. Augmented Reality (AR) provides a solution for combining the real environment with virtual models. However, AR usually requires the use of specialized displays, and its effectiveness in the surgery still needs to be evaluated. The objective of this research was to develop an alternative approach to provide enhanced visualization by fusing a direct (photographic) view of the surgical field with the 3D patient model during image guided epilepsy surgery.

MATERIALS AND METHODS: We correlated the preoperative plan …