Seizure detection and epileptogenic zone localisation on heavily skewed MEG data using RUSBoost machine learning technique.

Background: Epilepsy is a neurological disorder which is characterised by recurrent and involuntary seizures. Magnetoencephalography (MEG) is clinically used as a presurgical tool in locating the epileptogenic zone by localising either interictal epileptic discharges (IEDs) or ictal activities. The localisation of ictal onset provides reliable and more accurate seizure onset zones rather than localising the IEDs. Ictals or seizures are presently detected during MEG analysis by manually inspecting the recorded data. This is laborious when the duration of recordings is longer. Methods: We propose a novel method which uses statistical features such as short-time permutation entropy (STPE), gradient of STPE (GSTPE), short-time energy (STE) and short-time mean (STM) extracted from the ictal and interictal MEG data of drug resistant epilepsy patients group. Since the data is heavily skewed, the RUSBoost algorithm with k-fold cross-validation is used to classify the data into ictal and interictal by using the four feature vectors. This method is further used for localising the epileptogenic region using region-specific classifications by means of the RUSBoost algorithm. Results: The accuracy obtained for seizure detection is 93.4%. The specificity and sensitivity for the same are 93%. The localisation accuracies for each lobe are in the range of 88.1-99.1%. Discussion: Through this ictus detection method, the current scenario of laborious inspection of the ictal MEG can be reduced. The proposed system, thus, can be implemented in real-time as a better and more efficient method for seizure detection and further it can prove to be highly beneficial for patients and health-care professionals during real-time MEG recording. Furthermore, the identification of the epileptogenic lobe can provide clinicians with useful insights, and a pre-cursor for source localisation.

EEG-based P300 in mesial temporal lobe epilepsy and its correlation with cognitive functions: A case-control study.

OBJECTIVE: P300 is an event-related potential, being explored as an objective tool to assess cognition. This study aimed to investigate the characteristics of auditory and visual P300 in patients with TLE having unilateral HS using electroencephalography (EEG) and to study its correlation with cognition. METHODS: This is a cross-sectional case-control study, where P300 characteristics in thirty patients with unilateral hippocampal sclerosis with refractory epilepsy were compared with fifteen age-, gender-, and years of education-matched healthy controls (M: F-10:5, mean age-28 ±â€¯4.76 years). Among patients, 15 belonged to the right HS group (M: F-9:6, age at onset-12.92 ±â€¯10.22 years, duration of epilepsy-16.67 ±â€¯9.38 years) and 15 to the left HS group (M: F-8:7, age at onset-10.62 ±â€¯7.18 years, duration of epilepsy-15.53 ±â€¯10.14 years). All subjects underwent EEG-based auditory and visual oddball tasks and cognitive assessment. The P300 latencies (in milliseconds) as well as amplitudes (in microvolts) were predicted in EEG and were correlated with cognitive scores. Source localization of P300 was performed with the CLARA algorithm. RESULTS: The auditory P300 latencies in controls, right HS, and left HS were 323.93 ±â€¯40.28, 351.06 ±â€¯47.23, and 328.80 ±â€¯36.03, respectively (p = 0.18) and its amplitudes were 2.3040 ±â€¯1.46, 2.77 ±â€¯1.19, and 2.68 ±â€¯1.78, respectively (p = 0.48). Visual P300 latencies in controls, right HS, and left HS were 365.87 ±â€¯47.37, 359.67 ±â€¯64.45, and 376.00 ±â€¯60.06, respectively (p = 0.51) and its amplitudes were 3.93 ±â€¯2.28, 2.09 ±â€¯1.45, and 3.56 ±â€¯1.74, respectively (p = 0.014). Further, when compared to the control group the cognitive scores were lower in the patient group (p < 0.05). SIGNIFICANCE: In comparison to the controls, patients with right HS recorded lesser amplitude on visual P300 and lower scores on cognitive tests. P300 and cognitive parameters exhibited varied relationship. P300 could be a complementary objective tool to assess cognition in patients with TLE.

Content-Based Estimation of Brain MRI Tilt in Three Orthogonal Directions.

In a general scenario, the brain images acquired from magnetic resonance imaging (MRI) may experience tilt, distorting brain MR images. The tilt experienced by the brain MR images may result in misalignment during image registration for medical applications. Manually correcting (or estimating) the tilt on a large scale is time-consuming, expensive, and needs brain anatomy expertise. Thus, there is a need for an automatic way of performing tilt correction in three orthogonal directions (X, Y, Z). The proposed work aims to correct the tilt automatically by measuring the pitch angle, yaw angle, and roll angle in X-axis, Z-axis, and Y-axis, respectively. For correction of the tilt around the Z-axis (pointing to the superior direction), image processing techniques, principal component analysis, and similarity measures are used. Also, for correction of the tilt around the X-axis (pointing to the right direction), morphological operations, and tilt correction around the Y-axis (pointing to the anterior direction), orthogonal regression is used. The proposed approach was applied to adjust the tilt observed in the T1- and T2-weighted MR images. The simulation study with the proposed algorithm yielded an error of 0.40 ± 0.09°, and it outperformed the other existing studies. The tilt angle (in degrees) obtained is ranged from 6.2 ± 3.94, 2.35 ± 2.61, and 5 ± 4.36 in X-, Z-, and Y-directions, respectively, by using the proposed algorithm. The proposed work corrects the tilt more accurately and robustly when compared with existing studies.

P300 in mesial temporal lobe epilepsy and its correlation with cognition - A MEG based prospective case-control study.

PURPOSE: To assess the role of P300 in patients with temporal lobe epilepsy (TLE) with unilateral hippocampal sclerosis (HS) using magnetoencephalography (MEG) based auditory and visual oddball tasks, and to assess its correlation with neuropsychological tests. METHODS: Thirty-patients (M:F-17:13, onset-11.77 ±â€¯8.75 years, duration-16.10 ±â€¯9.61 years) with TLE-HS (Left:15, Right:15) and fifteen-healthy age, gender and years of education matched controls (M:F-10:5, age-28.13 ±â€¯4.76 years) underwent auditory and visual oddball tasks in MEG and cognition assessment using Indian Council of Medical Research (ICMR)-cognitive test battery. Independent component analysis (ICA) was applied to the magnetic evoked field responses for the detection of the P300 component. Source localization of P300 was performed with Classical LORETA Analysis Recursively Applied (CLARA). The latency and amplitude of P300 were estimated and subsequently correlated with cognitive scores. RESULTS: The visual P300 amplitude in the TLE group was lower when compared to the control group. In subgroup comparison (controls vs. right HS vs. left HS), visual P300 amplitudes were lower in the right HS group compared to both left HS and control groups (p-value = 0.014). On the other hand, no significant difference for auditory P300 latency or amplitude was noted between patients and controls as well as between subgroups. A negative correlation found between the MEG visual P300 amplitude and Indian Trial Making Test (TMT)-B duration in the patient group. CONCLUSION: Patients with TLE-HS have decreased visual-P300 amplitude. A significant correlation found between visual P300 amplitude and cognitive tests of visuospatial attention and working memory. Overall, MEG based visual P300 amplitude can be further explored with large sample size studies to establish as a complementary objective test for cognitive assessment in TLE.

Improvement in Obsessive-Compulsive Disorder Following Right Anterior Temporal Lobectomy and Amygdalohippocampectomy in a Patient with Refractory Temporal Lobe Epilepsy with Right Mesial Temporal Sclerosis.

There are reports of co-occurrence of obsessive-compulsive disorder (OCD) in patients with temporal lobe epilepsy (TLE). We present a report of a patient with refractory TLE due to hippocampal sclerosis with concomitant OCD on pharmacotherapy for both. She underwent surgery for standard anterior temporal lobectomy with amygdalohippocampectomy and reported improvement in obsessive-compulsive symptoms subsequently. We seek to further evidence of interaction between the two conditions and argue to undertake future research exploration on the same.