Dataset Information

Using Low-Frequency Oscillations to Detect Temporal Lobe Epilepsy with Machine Learning.

ABSTRACT: The National Institutes of Health-sponsored Epilepsy Connectome Project aims to characterize connectivity changes in temporal lobe epilepsy (TLE) patients. The magnetic resonance imaging protocol follows that used in the Human Connectome Project, and includes 20?min of resting-state functional magnetic resonance imaging acquired at 3T using 8-band multiband imaging. Glasser parcellation atlas was combined with the FreeSurfer subcortical regions to generate resting-state functional connectivity (RSFC), amplitude of low-frequency fluctuations (ALFFs), and fractional ALFF measures. Seven different frequency ranges such as Slow-5 (0.01-0.027?Hz) and Slow-4 (0.027-0.073?Hz) were selected to compute these measures. The goal was to train machine learning classification models to discriminate TLE patients from healthy controls, and to determine which combination of the resting state measure and frequency range produced the best classification model. The samples included age- and gender-matched groups of 60 TLE patients and 59 healthy controls. Three traditional machine learning models were trained: support vector machine, linear discriminant analysis, and naive Bayes classifier. The highest classification accuracy was obtained using RSFC measures in the Slow-4?+?5 band (0.01-0.073?Hz) as features. Leave-one-out cross-validation accuracies were ?83%, with receiver operating characteristic area-under-the-curve reaching close to 90%. Increased connectivity from right area posterior 9-46v in TLE patients contributed to the high accuracies. With increased sample sizes in the near future, better machine learning models will be trained not only to aid the diagnosis of TLE, but also as a tool to understand this brain disorder.

SUBMITTER: Hwang G

PROVIDER: S-EPMC6484357 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using Low-Frequency Oscillations to Detect Temporal Lobe Epilepsy with Machine Learning.

Hwang Gyujoon G Nair Veena A VA Mathis Jed J Cook Cole J CJ Mohanty Rosaleena R Zhao Gengyan G Tellapragada Neelima N Ustine Candida C Nwoke Onyekachi O OO Rivera-Bonet Charlene C Rozman Megan M Allen Linda L Forseth Courtney C Almane Dace N DN Kraegel Peter P Nencka Andrew A Felton Elizabeth E Struck Aaron F AF Birn Rasmus R Maganti Rama R Conant Lisa L LL Humphries Colin J CJ Hermann Bruce B Raghavan Manoj M DeYoe Edgar A EA Binder Jeffrey R JR Meyerand Elizabeth E Prabhakaran Vivek V

Brain connectivity 20190301 2

The National Institutes of Health-sponsored Epilepsy Connectome Project aims to characterize connectivity changes in temporal lobe epilepsy (TLE) patients. The magnetic resonance imaging protocol follows that used in the Human Connectome Project, and includes 20 min of resting-state functional magnetic resonance imaging acquired at 3T using 8-band multiband imaging. Glasser parcellation atlas was combined with the FreeSurfer subcortical regions to generate resting-state functional connectivity ( ...[more]

PMID: 30803273

Similar Datasets

Project description:BackgroundIt is common for patients diagnosed with medial temporal lobe epilepsy (TLE) to have extrahippocampal damage. However, it is unclear whether microstructural extrahippocampal abnormalities are consistent enough to enable classification using diffusion MRI imaging. Therefore, we implemented a support vector machine (SVM)-based method to predict TLE from three different imaging modalities: mean kurtosis (MK), mean diffusivity (MD), and fractional anisotropy (FA). While MD and FA can be calculated from traditional diffusion tensor imaging (DTI), MK requires diffusion kurtosis imaging (DKI).MethodsThirty-two TLE patients and 36 healthy controls underwent DKI imaging. To measure predictive capability, a fivefold cross-validation (CV) was repeated for 1000 iterations. An ensemble of SVM models, each with a different regularization value, was trained with the subject images in the training set, and had performance assessed on the test set. The different regularization values were determined using a Bayesian-based method.ResultsMean kurtosis achieved higher accuracy than both FA and MD on every iteration, and had far superior average accuracy: 0.82 (MK), 0.68 (FA), and 0.51 (MD). Finally, the MK voxels with the highest coefficients in the predictive models were distributed within the inferior medial aspect of the temporal lobes.ConclusionThese results corroborate our earlier publications which indicated that DKI shows more promise in identifying TLE-associated pathological features than DTI. Also, the locations of the contributory MK voxels were in areas with high fiber crossing and complex fiber anatomy. These traits result in non-Gaussian water diffusion, and hence render DTI less likely to detect abnormalities. If the location of consistent microstructural abnormalities can be better understood, then it may be possible in the future to identify the various phenotypes of TLE. This is important since treatment outcome varies dependent on type of TLE.

Project description:OBJECTIVES:Brain functional topology was investigated in patients with mesial temporal lobe epilepsy (mTLE) by means of graph theory measures in two differentially defined graphs. Measures of segregation, integration, and centrality were compared between subjects with mTLE and healthy controls (HC). METHODS:Eleven subjects with mTLE (age 36.5±10.9years) and 15 age-matched HC (age 36.8±14.0years) participated in this study. Both anatomically and functionally defined adjacency matrices were used to investigate the measures. Binary undirected graphs were constructed to study network segregation by calculating global clustering and modularity, and network integration by calculating local and global efficiency. Node degree and participation coefficient were also computed in order to investigate network hubs and their classification into provincial or connector hubs. Measures were investigated in a range of low to medium graph density. RESULTS:The group of patients presented lower global segregation than HC while showing higher global but lower local integration. They also failed to engage regions that comprise the default-mode network (DMN) as hubs such as bilateral medial frontal regions, PCC/precuneus complex, and right inferior parietal lobule, which were present in controls. Furthermore, the cerebellum in subjects with mTLE seemed to be playing a major role in the integration of their functional networks, which was evident through the engagement of cerebellar regions as connector hubs. CONCLUSIONS:Functional networks in subjects with mTLE presented both global and local abnormalities compared to healthy subjects. Specifically, there was significant separation between groups, with lower global segregation and slightly higher global integration observed in patients. This could be indicative of a network that is working as a whole instead of in segregated or specialized communities, which could translate into a less robust network and more prone to disruption in the group with epilepsy. Furthermore, functional irregularities were also observed in the group of patients in terms of the engagement of cerebellar regions as hubs while failing to engage DMN-related areas as major hubs in the network. The use of two differentially defined graphs synergistically contributed to findings.

Dataset Information

Using Low-Frequency Oscillations to Detect Temporal Lobe Epilepsy with Machine Learning.

Publications

Using Low-Frequency Oscillations to Detect Temporal Lobe Epilepsy with Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure