Utilizing Clinical Trial Data to Assess Timing of Surgical Treatment for Emphysema Patients.

BACKGROUND: Lung volume reduction surgery (LVRS) and medical therapy are 2 available treatment options in dealing with severe emphysema, which is a chronic lung disease. However, or there are currently limited guidelines on the timing of LVRS for patients with different characteristics. OBJECTIVE: The objective of this study is to assess the timing of receiving LVRS in terms of patient outcomes, taking into consideration a patient's characteristics. METHODS: A finite-horizon Markov decision process model for patients with severe emphysema was developed to determine the short-term (5 y) and long-term timing of emphysema treatment. Maximizing the expected life expectancy, expected quality-adjusted life-years, and total expected cost of each treatment option were applied as the objective functions of the model. To estimate parameters in the model, the data provided by the National Emphysema Treatment Trial were used. RESULTS: The results indicate that the treatment timing strategy for patients with upper-lobe predominant emphysema is to receive LVRS regardless of their specific characteristics. However, for patients with non-upper-lobe-predominant emphysema, the optimal strategy depends on the age, maximum workload level, and forced expiratory volume in 1 second level. CONCLUSION: This study demonstrates the utilization of clinical trial data to gain insights into the timing of surgical treatment for patients with emphysema, considering patient age, observable health condition, and location of emphysema. HIGHLIGHTS: Both short-term and long-term Markov decision process models were developed to assess the timing of receiving lung volume reduction surgery in patients with severe emphysema.How clinical trial data can be used to estimate the parameters and obtain short-term results from the Markov decision process model is demonstrated.The results provide insights into the timing of receiving lung volume reduction surgery as a function of a patient's characteristics, including age, emphysema location, maximum workload, and forced expiratory volume in 1 second level.

Gradient Boosted Trees for Spatial Data and Its Application to Medical Imaging Data.

Boosting Trees are one of the most successful statistical learning approaches that involve sequentially growing an ensemble of simple regression trees ("weak learners"). This paper proposes a gradient Boosted Trees algorithm for Spatial Data (Boost-S) with covariate information. Boost-S integrates the spatial correlation into the classical framework of eXtreme Gradient Boosting. Each tree is constructed by solving a regularized optimization problem, where the objective function takes into account the underlying spatial correlation and involves two penalty terms on tree complexity. A computationally-efficient greedy heuristic algorithm is proposed to obtain an ensemble of trees. The proposed Boost-S is applied to the spatially-correlated FDG-PET (fluorodeoxyglucose-positron emission tomography) imaging data collected from clinical trials of cancer chemoradiotherapy. Our numerical investigations successfully demonstrate the advantages of the proposed Boost-S over existing approaches for this particular application.

Multitask Learning Radiomics on Longitudinal Imaging to Predict Survival Outcomes following Risk-Adaptive Chemoradiation for Non-Small Cell Lung Cancer.

Medical imaging provides quantitative and spatial information to evaluate treatment response in the management of patients with non-small cell lung cancer (NSCLC). High throughput extraction of radiomic features on these images can potentially phenotype tumors non-invasively and support risk stratification based on survival outcome prediction. The prognostic value of radiomics from different imaging modalities and time points prior to and during chemoradiation therapy of NSCLC, relative to conventional imaging biomarker or delta radiomics models, remains uncharacterized. We investigated the utility of multitask learning of multi-time point radiomic features, as opposed to single-task learning, for improving survival outcome prediction relative to conventional clinical imaging feature model benchmarks. Survival outcomes were prospectively collected for 45 patients with unresectable NSCLC enrolled on the FLARE-RT phase II trial of risk-adaptive chemoradiation and optional consolidation PD-L1 checkpoint blockade (NCT02773238). FDG-PET, CT, and perfusion SPECT imaging pretreatment and week 3 mid-treatment was performed and 110 IBSI-compliant pyradiomics shape-/intensity-/texture-based features from the metabolic tumor volume were extracted. Outcome modeling consisted of a fused Laplacian sparse group LASSO with component-wise gradient boosting survival regression in a multitask learning framework. Testing performance under stratified 10-fold cross-validation was evaluated for multitask learning radiomics of different imaging modalities and time points. Multitask learning models were benchmarked against conventional clinical imaging and delta radiomics models and evaluated with the concordance index (c-index) and index of prediction accuracy (IPA). FDG-PET radiomics had higher prognostic value for overall survival in test folds (c-index 0.71 [0.67, 0.75]) than CT radiomics (c-index 0.64 [0.60, 0.71]) or perfusion SPECT radiomics (c-index 0.60 [0.57, 0.63]). Multitask learning of pre-/mid-treatment FDG-PET radiomics (c-index 0.71 [0.67, 0.75]) outperformed benchmark clinical imaging (c-index 0.65 [0.59, 0.71]) and FDG-PET delta radiomics (c-index 0.52 [0.48, 0.58]) models. Similarly, the IPA for multitask learning FDG-PET radiomics (30%) was higher than clinical imaging (26%) and delta radiomics (15%) models. Radiomics models performed consistently under different voxel resampling conditions. Multitask learning radiomics for outcome modeling provides a clinical decision support platform that leverages longitudinal imaging information. This framework can reveal the relative importance of different imaging modalities and time points when designing risk-adaptive cancer treatment strategies.

Sensitivity analysis of FDG PET tumor voxel cluster radiomics and dosimetry for predicting mid-chemoradiation regional response of locally advanced lung cancer.

We investigated the sensitivity of regional tumor response prediction to variability in voxel clustering techniques, imaging features, and machine learning algorithms in 25 patients with locally advanced non-small cell lung cancer (LA-NSCLC) enrolled on the FLARE-RT clinical trial. Metabolic tumor volumes (MTV) from pre-chemoradiation (PETpre) and mid-chemoradiation fluorodeoxyglucose-positron emission tomography (FDG PET) images (PETmid) were subdivided into K-means or hierarchical voxel clusters by standardized uptake values (SUV) and 3D-positions. MTV cluster separability was evaluated by CH index, and morphologic changes were captured by Dice similarity and centroid Euclidean distance. PETpre conventional features included SUVmean, MTV/MTV cluster size, and mean radiation dose. PETpre radiomics consisted of 41 intensity histogram and 3D texture features (PET Oncology Radiomics Test Suite) extracted from MTV or MTV clusters. Machine learning models (multiple linear regression, support vector regression, logistic regression, support vector machines) of conventional features or radiomic features were constructed to predict PETmid response. Leave-one-out-cross-validated root-mean-squared-error (RMSE) for continuous response regression (ΔSUVmean) and area-under-receiver-operating-characteristic-curve (AUC) for binary response classification were calculated. K-means MTV 2-clusters (MTVhi, MTVlo) achieved maximum CH index separability (Friedman p < 0.001). Between PETpre and PETmid, MTV cluster pairs overlapped (Dice 0.70-0.87) and migrated 0.6-1.1 cm. PETmid ΔSUVmean response prediction was superior in MTV and MTVlo (RMSE = 0.17-0.21) compared to MTVhi (RMSE = 0.42-0.52, Friedman p < 0.001). PETmid ΔSUVmean response class prediction performance trended higher in MTVlo (AUC = 0.83-0.88) compared to MTVhi (AUC = 0.44-0.58, Friedman p = 0.052). Models were more sensitive to MTV/MTV cluster regions (Friedman p = 0.026) than feature sets/algorithms (Wilcoxon signed-rank p = 0.36). Top-ranked radiomic features included GLZSM-LZHGE (large-zone-high-SUV), GTSDM-CP (cluster-prominence), GTSDM-CS (cluster-shade) and NGTDM-CNT (contrast). Top-ranked features were consistent between MTVhi and MTVlo cluster pairs but varied between MTVhi-MTVlo clusters, reflecting distinct regional radiomic phenotypes. Variability in tumor voxel cluster response prediction can inform robust radiomic target definition for risk-adaptive chemoradiation in patients with LA-NSCLC. FLARE-RT trial: NCT02773238.

Voxel Forecast for Precision Oncology: Predicting Spatially Variant and Multiscale Cancer Therapy Response on Longitudinal Quantitative Molecular Imaging.

PURPOSE: Prediction of spatially variant response to cancer therapies can inform risk-adaptive management within precision oncology. We developed the "Voxel Forecast" multiscale regression framework for predicting spatially variant tumor response to chemoradiotherapy on fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) imaging. EXPERIMENTAL DESIGN: Twenty-five patients with locally advanced non-small cell lung cancer, enrolled on the FLARE-RT phase II trial (NCT02773238), underwent FDG PET/CT imaging prior to (PETpre) and during week 3 (PETmid) of concurrent chemoradiotherapy. Voxel Forecast was designed to predict tumor voxel standardized uptake value (SUV) on PETmid from baseline patient-level and voxel-level covariates using a custom generalized least squares (GLS) algorithm. Matérn covariance matrices were fit to patient- specific empirical variograms of distance-dependent intervoxel correlation. Regression coefficients from variogram-based weights and corresponding standard errors were estimated using the jackknife technique. The framework was validated using statistical simulations of known spatially variant tumor response. Mean absolute prediction errors (MAEs) of Voxel Forecast models were calculated under leave-one-patient-out cross-validation. RESULTS: Patient-level forecasts resulted in tumor voxel SUV MAE on PETmid of 1.5 g/mL while combined patient- and voxel-level forecasts achieved lower MAE of 1.0 g/mL (P < 0.0001). PETpre voxel SUV was the most important predictor of PETmid voxel SUV. Patients with a greater percentage of under-responding tumor voxels were classified as PETmid nonresponders (P = 0.030) with worse overall survival prognosis (P < 0.001). CONCLUSIONS: Voxel Forecast multiscale regression provides a statistical framework to predict voxel-wise response patterns during therapy. Voxel Forecast can be extended to predict spatially variant response on multimodal quantitative imaging and may eventually guide optimized spatial-temporal dose distributions for precision cancer therapy.

Deep learning for patient-specific quality assurance: Identifying errors in radiotherapy delivery by radiomic analysis of gamma images with convolutional neural networks.

PURPOSE: Patient-specific quality assurance (QA) for intensity-modulated radiation therapy (IMRT) is a ubiquitous clinical procedure, but conventional methods have often been criticized as being insensitive to errors or less effective than other common physics checks. Recently, there has been interest in the application of radiomics, quantitative extraction of image features, to radiotherapy QA. In this work, we investigate a deep learning approach to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific QA. METHODS: Planar dose maps from 186 IMRT beams from 23 IMRT plans were evaluated. Each plan was transferred to a cylindrical phantom CT geometry. Three sets of planar doses were exported from each plan corresponding to (a) the error-free case, (b) a random multileaf collimator (MLC) error case, and (c) a systematic MLC error case. Each plan was delivered to the electronic portal imaging device (EPID), and planned and measured doses were used to calculate gamma images in an EPID dosimetry software package (for a total of 558 gamma images). Two radiomic approaches were used. In the first, a convolutional neural network with triplet learning was used to extract image features from the gamma images. In the second, a handcrafted approach using texture features was used. The resulting metrics from both approaches were input into four machine learning classifiers (support vector machines, multilayer perceptrons, decision trees, and k-nearest-neighbors) in order to determine whether images contained the introduced errors. Two experiments were considered: the two-class experiment classified images as error-free or containing any MLC error, and the three-class experiment classified images as error-free, containing a random MLC error, or containing a systematic MLC error. Additionally, threshold-based passing criteria were calculated for comparison. RESULTS: In total, 303 gamma images were used for model training and 255 images were used for model testing. The highest classification accuracy was achieved with the deep learning approach, with a maximum accuracy of 77.3% in the two-class experiment and 64.3% in the three-class experiment. The performance of the handcrafted approach with texture features was lower, with a maximum accuracy of 66.3% in the two-class experiment and 53.7% in the three-class experiment. Variability between the results of the four machine learning classifiers was lower for the deep learning approach vs the texture feature approach. Both radiomic approaches were superior to threshold-based passing criteria. CONCLUSIONS: Deep learning with convolutional neural networks can be used to classify the presence or absence of introduced radiotherapy treatment delivery errors from patient-specific gamma images. The performance of the deep learning network was superior to a handcrafted approach with texture features, and both radiomic approaches were better than threshold-based passing criteria. The results suggest that radiomic QA is a promising direction for clinical radiotherapy.

Error Detection in Intensity-Modulated Radiation Therapy Quality Assurance Using Radiomic Analysis of Gamma Distributions.

PURPOSE: To improve the detection of errors in intensity-modulated radiation therapy (IMRT) with a novel method that uses quantitative image features from radiomics to analyze gamma distributions generated during patient specific quality assurance (QA). METHODS AND MATERIALS: One hundred eighty-six IMRT beams from 23 patient treatments were delivered to a phantom and measured with electronic portal imaging device dosimetry. The treatments spanned a range of anatomic sites; half were head and neck treatments, and the other half were drawn from treatments for lung and rectal cancers, sarcoma, and glioblastoma. Planar gamma distributions, or gamma images, were calculated for each beam using the measured dose and calculated doses from the 3-dimensional treatment planning system under various scenarios: a plan without errors and plans with either simulated random or systematic multileaf collimator mispositioning errors. The gamma images were randomly divided into 2 sets: a training set for model development and testing set for validation. Radiomic features were calculated for each gamma image. Error detection models were developed by training logistic regression models on these radiomic features. The models were applied to the testing set to quantify their predictive utility, determined by calculating the area under the curve (AUC) of the receiver operator characteristic curve, and were compared with traditional threshold-based gamma analysis. RESULTS: The AUC of the random multileaf collimator mispositioning model on the testing set was 0.761 compared with 0.512 for threshold-based gamma analysis. The AUC for the systematic mispositioning model was 0.717 versus 0.660 for threshold-based gamma analysis. Furthermore, the models could discriminate between the 2 types of errors simulated here, exhibiting AUCs of approximately 0.5 (equivalent to random guessing) when applied to the error they were not designed to detect. CONCLUSIONS: The feasibility of error detection in patient-specific IMRT QA using radiomic analysis of QA images has been demonstrated. This methodology represents a substantial step forward for IMRT QA with improved sensitivity and specificity over current QA methods and the potential to distinguish between different types of errors.

Interval importance index to select relevant ATR-FTIR wavenumber Intervals for falsified drug classification.

The commerce of falsified drugs has substantially grown in recent years due to facilitated access to technologies needed for copying authentic pharmaceutical products. Attenuated Total Reflectance coupled with Fourier Transform Infrared (ATR-FTIR) spectroscopy has been successfully employed as an analytical tool to identify falsified products and support legal agents in interrupting illegal operations. ATR-FTIR spectroscopy typically yields datasets comprised of hundreds of highly correlated wavenumbers, which may compromise the performance of classical multivariate techniques used for sample classification. In this paper we propose a new wavenumber interval selection method aimed at selecting regions of spectra that best discriminate samples of seized drugs into two classes, authentic or falsified. The discriminative power of spectra regions is represented by an Interval Importance Index (III) based on the Two-Sample Kolmogorov-Smirnov test statistic, which is a novel proposition of this paper. The III guides an iterative forward approach for wavenumber selection; different data mining techniques are used for sample classification. In 100 replications using the best combination of classification technique and wavenumber intervals, we obtained average 99.87% accurate classifications on a Cialis® dataset, while retaining 12.5% of the authentic wavenumbers, and average 99.43% accurate classifications on a Viagra® dataset, while retaining 23.75% of the authentic wavenumbers. Our proposition was compared with alternative approaches for individual and interval wavenumber selection available in the literature, always leading to more consistent and easier to interpret results.

Network Optimization of Functional Connectivity Within Default Mode Network Regions to Detect Cognitive Decline.

The rapid aging of the world's population is causing an increase in the prevalence of cognitive decline and degenerative brain disease in the elderly. Current diagnoses of amnestic and nonamnestic mild cognitive impairment, which may represent early stage Alzheimer's disease or related degenerative conditions, are based on clinical grounds. The recent emergence of advanced network analyses of functional magnetic resonance imaging (fMRI) data taken at cognitive rest has provided insight that declining functional connectivity of the default mode network (DMN) may be correlated with neurological disorders, and particularly prodromal Alzheimer's disease. The goal of this paper is to develop a network analysis technique using fMRI data to characterize transition stages from healthy brain aging to cognitive decline. Previous studies primarily focused on inter-nodal connectivity of the DMN and often assume functional homogeneity within each DMN region. In this paper, we develop a technique that focuses on identifying critical intra-nodal DMN connectivity by incorporating sparsity into connectivity modeling of the k -cardinality tree (KCT) problem. Most biological networks are efficient and formed by sparse connections, and the KCT can potentially reveal sparse connectivity patterns that are biologically informative. The KCT problem is NP-hard, and existing solution approaches are mostly heuristic. Mathematical formulations of the KCT problem in the literature are not compact and do not provide good solution bounds. This paper presents new KCT formulations and a fast heuristic approach to efficiently solve the KCT models for large DMN regions. The results in this paper demonstrate that traditional fMRI group analysis on DMN regions cannot detect any statistically significant connectivity differences between normal aging and cognitively impaired subjects in DMN regions, and the proposed KCT approaches are more sensitive than the state-of-the-art regional homogeneity approach in detecting significant differences in both left and right medial temporal regions of the DMN.

Altered visual contrast gain control is sensitive for idiopathic generalized epilepsies.

OBJECTIVE: Visual hyperexcitability in the form of abnormal contrast gain control has been shown in photosensitive epilepsy and idiopathic generalized epilepsies. We assessed the accuracy and reliability of measures of visual contrast gain control in discerning individuals with idiopathic generalized epilepsies from healthy controls. METHODS: Twenty-four adult patients with idiopathic generalized epilepsy and 32 neurotypical control subjects from two study sites participated in a prospective, cross-sectional study. We recorded steady-state visual evoked potentials to a wide range of contrasts of a flickering grating stimulus. The resultant response magnitude vs. contrast curves were fitted to a standard model of contrast response function, and the model parameters were used as input features to a linear classifier to separate patients from controls. Additionally we compared the relative contribution of model parameters towards the classification using a sparse feature-selection approach. RESULTS: Classification accuracy was 80% or better. Sensitivity and specificity both were 80-85%. Cross validation confirmed robust classifier performance generalizable across the data from the two samples. Patients' relative lack of gain control at high contrasts was the most important information distinguishing patients from controls. CONCLUSIONS: Individuals with idiopathic generalized epilepsy were distinguishable from the neurotypical with a high degree of accuracy and reliability by a reduction in gain control at high contrasts. SIGNIFICANCE: Gain control is an essential neural operation that regulates neuronal sensitivity to stimuli and may represent a novel biomarker of hyperexcitability.

Voxel selection framework in multi-voxel pattern analysis of FMRI data for prediction of neural response to visual stimuli.

Multi-voxel pattern analysis (MVPA) of functional magnetic resonance imaging (fMRI) data is an emerging approach for probing the neural correlates of cognition. MVPA allows cognitive states to be modeled as distributed patterns of neural activity and classified according to stimulus conditions. In practice, building a robust, generalizable classification model can be challenging because the number of voxels (features) far exceeds the number of stimulus instances/data observations. To avoid model overfitting, there is a need to select informative voxels before building a classification model. In this paper, we propose a robust feature (voxel) selection framework using mutual information (MI) and partial least square regression (PLS) to establish an informativeness index for prioritizing selection of voxels based on the degree of their association to the experimental conditions. We evaluated the robustness of our proposed framework by assessing performance of standard classification algorithms, when combined with our feature selection approach, in a publicly-available fMRI dataset of object-level representation widely used to benchmark MVPA performance (Haxby, 2001). The computational results suggest that our feature selection framework based on MI and PLS drastically improves the classification accuracy relative to those previously reported in the literature. Our results also suggest that highly informative voxels may provide meaningful insight into the functional-anatomic relationship of brain activity and stimulus conditions.

Respiratory trace feature analysis for the prediction of respiratory-gated PET quantification.

The benefits of respiratory gating in quantitative PET/CT vary tremendously between individual patients. Respiratory pattern is among many patient-specific characteristics that are thought to play an important role in gating-induced imaging improvements. However, the quantitative relationship between patient-specific characteristics of respiratory pattern and improvements in quantitative accuracy from respiratory-gated PET/CT has not been well established. If such a relationship could be estimated, then patient-specific respiratory patterns could be used to prospectively select appropriate motion compensation during image acquisition on a per-patient basis. This study was undertaken to develop a novel statistical model that predicts quantitative changes in PET/CT imaging due to respiratory gating. Free-breathing static FDG-PET images without gating and respiratory-gated FDG-PET images were collected from 22 lung and liver cancer patients on a PET/CT scanner. PET imaging quality was quantified with peak standardized uptake value (SUV(peak)) over lesions of interest. Relative differences in SUV(peak) between static and gated PET images were calculated to indicate quantitative imaging changes due to gating. A comprehensive multidimensional extraction of the morphological and statistical characteristics of respiratory patterns was conducted, resulting in 16 features that characterize representative patterns of a single respiratory trace. The six most informative features were subsequently extracted using a stepwise feature selection approach. The multiple-regression model was trained and tested based on a leave-one-subject-out cross-validation. The predicted quantitative improvements in PET imaging achieved an accuracy higher than 90% using a criterion with a dynamic error-tolerance range for SUV(peak) values. The results of this study suggest that our prediction framework could be applied to determine which patients would likely benefit from respiratory motion compensation when clinicians quantitatively assess PET/CT for therapy target definition and response assessment.

Local functional connectivity as a pre-surgical tool for seizure focus identification in non-lesion, focal epilepsy.

Successful resection of cortical tissue engendering seizure activity is efficacious for the treatment of refractory, focal epilepsy. The pre-operative localization of the seizure focus is therefore critical to yielding positive, post-operative outcomes. In a small proportion of focal epilepsy patients presenting with normal MRI, identification of the seizure focus is significantly more challenging. We examined the capacity of resting state functional MRI (rsfMRI) to identify the seizure focus in a group of four non-lesion, focal (NLF) epilepsy individuals. We predicted that computing patterns of local functional connectivity in and around the epileptogenic zone combined with a specific reference to the corresponding region within the contralateral hemisphere would reliably predict the location of the seizure focus. We first averaged voxel-wise regional homogeneity (ReHo) across regions of interest (ROIs) from a standardized, probabilistic atlas for each NLF subject as well as 16 age- and gender-matched controls. To examine contralateral effects, we computed a ratio of the mean pair-wise correlations of all voxels within a ROI with the corresponding contralateral region (IntraRegional Connectivity - IRC). For each subject, ROIs were ranked (from lowest to highest) on ReHo, IRC, and the mean of the two values. At the group level, we observed a significant decrease in the rank for ROI harboring the seizure focus for the ReHo rankings as well as for the mean rank. At the individual level, the seizure focus ReHo rank was within bottom 10% lowest ranked ROIs for all four NLF epilepsy patients and three out of the four for the IRC rankings. However, when the two ranks were combined (averaging across ReHo and IRC ranks and scalars), the seizure focus ROI was either the lowest or second lowest ranked ROI for three out of the four epilepsy subjects. This suggests that rsfMRI may serve as an adjunct pre-surgical tool, facilitating the identification of the seizure focus in focal epilepsy.

Link Clustering to Explore Brain Dynamics Using Resting State Functional MRI.

Quantitative network analysis of brain networks has been an important tool for characterizing brain function. Cognitive abilities emerge from coordinated activity of distributed brain regions that may participate in multiple networks at different times. However, neuroimaging has few available tools to model and quantify networks with spatially overlapping nodes that are active at different times. The dynamics of network reconfiguration may yield important insight into networks that are damaged with neurodegenerative disease. We describe here an approach that uses a graph analytic technique called link clustering, which identifies communities that have overlapping functional nodes, demonstrating its ability to highlight differences in the dynamic reorganization of networks between subjects with Alzheimer's dementia and normal controls.

KINALYZER, a computer program for reconstructing sibling groups.

A software suite KINALYZER reconstructs full-sibling groups without parental information using data from codominant marker loci such as microsatellites. KINALYZER utilizes a new algorithm for sibling reconstruction in diploid organisms based on combinatorial optimization. KINALYZER makes use of a Minimum 2-Allele Set Cover approach based on Mendelian inheritance rules and finds the smallest number of sibling groups that contain all the individuals in the sample. Also available is a 'Greedy Consensus' approach that reconstructs sibgroups using subsets of loci and finds the consensus of the partial solutions. Unlike likelihood methods for sibling reconstruction, KINALYZER does not require information about population allele frequencies and it makes no assumptions regarding the mating system of the species. KINALYZER is freely available as a web-based service.

Quantitative complexity analysis in multi-channel intracranial EEG recordings form epilepsy brains.

Epilepsy is a brain disorder characterized clinically by temporary but recurrent disturbances of brain function that may or may not be associated with destruction or loss of consciousness and abnormal behavior. Human brain is composed of more than 10 to the power 10 neurons, each of which receives electrical impulses known as action potentials from others neurons via synapses and sends electrical impulses via a sing output line to a similar (the axon) number of neurons. When neuronal networks are active, they produced a change in voltage potential, which can be captured by an electroencephalogram (EEG). The EEG recordings represent the time series that match up to neurological activity as a function of time. By analyzing the EEG recordings, we sought to evaluate the degree of underlining dynamical complexity prior to progression of seizure onset. Through the utilization of the dynamical measurements, it is possible to classify the state of the brain according to the underlying dynamical properties of EEG recordings. The results from two patients with temporal lobe epilepsy (TLE), the degree of complexity start converging to lower value prior to the epileptic seizures was observed from epileptic regions as well as non-epileptic regions. The dynamical measurements appear to reflect the changes of EEG's dynamical structure. We suggest that the nonlinear dynamical analysis can provide a useful information for detecting relative changes in brain dynamics, which cannot be detected by conventional linear analysis.

Antiepileptic drug intervention decouples electroencephalogram (EEG) signals: a case study in Unverricht-Lundborg Disease.

Change in severity of myoclonus as an outcome measure of antiepileptic drug (AED) treatment in patients with Unverricht-Lundborg Disease (ULD) has been estimated by utilizing the Unified Myoclonus Rating Scale (UMRS). In this study, we measure treatment effects through EEG analysis using mutual information approach to quantify interdependence/coupling strength among different electrode sites. Mutual information is known to have the ability to capture linear and non-linear dependencies between EEG time series with superior performance over the traditional linear measures. One subject with ULD participated in this study and 1-hour EEG recordings were acquired before and after treatment of AED. Our results indicate that the mutual information is significantly lower after taking the add-on AED for four weeks at least. This finding could lead to a new insight for developing a new outcome measure for patient with ULD, when UMRS could potentially fail to detect a significant difference.

Performance of a seizure warning algorithm based on the dynamics of intracranial EEG.

During the past decade, several studies have demonstrated experimental evidence that temporal lobe seizures are preceded by changes in dynamical properties (both spatial and temporal) of electroencephalograph (EEG) signals. In this study, we evaluate a method, based on chaos theory and global optimization techniques, for detecting pre-seizure states by monitoring the spatio-temporal changes in the dynamics of the EEG signal. The method employs the estimation of the short-term maximum Lyapunov exponent (STL(max)), a measure of the order (chaoticity) of a dynamical system, to quantify the EEG dynamics per electrode site. A global optimization technique is also employed to identify critical electrode sites that are involved in the seizure development. An important practical result of this study was the development of an automated seizure warning system (ASWS). The algorithm was tested in continuous, long-term EEG recordings, 3-14 days in duration, obtained from 10 patients with refractory temporal lobe epilepsy. In this analysis, for each patient, the EEG recordings were divided into training and testing datasets. We used the first portion of the data that contained half of the seizures to train the algorithm, where the algorithm achieved a sensitivity of 76.12% with an overall false prediction rate of 0.17h(-1). With the optimal parameter setting obtained from the training phase, the prediction performance of the algorithm during the testing phase achieved a sensitivity of 68.75% with an overall false prediction rate of 0.15h(-1). The results of this study confirm our previous observations from a smaller number of patients: the development of automated seizure warning devices for diagnostic and therapeutic purposes is feasible and practically useful.

Long-term prospective on-line real-time seizure prediction.

OBJECTIVE: Epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. In this study, we evaluate the performance of a prospective on-line real-time seizure prediction algorithm in two patients from a common database. METHODS: We previously demonstrated that measures of chaos and angular frequency, estimated from electroencephalographic (EEG) signals recorded at critical sites in the cerebral cortex, progressively converge (i.e. become dynamically entrained) as the epileptic brain transits from the asymptomatic interictal state to the ictal state (seizure) (Iasemidis et al., 2001, 2002a, 2003a). This observation suggested the possibility of developing algorithms to predict seizures well ahead of their occurrences. One of the central points in those investigations was the application of optimization theory, specifically quadratic zero-one programming, for the selection of the critical cortical sites. This current study combines that observation with a dynamical entrainment detection method to prospectively predict epileptic seizures. The algorithm was tested in two patients with long-term (107.54h) and multi-seizure EEG data B and C (Lehnertz and Litt, 2004). RESULTS: Analysis from the 2 test patients resulted in the prediction of up to 91.3% of the impending 23 seizures, about 89+/-15min prior to seizure onset, with an average false warning rate of one every 8.27h and an allowable prediction horizon of 3h. CONCLUSIONS: The algorithm provides warning of impending seizures prospectively and in real time, that is, it constitutes an on-line and real-time seizure prediction scheme. SIGNIFICANCE: These results suggest that the proposed seizure prediction algorithm could be used in novel diagnostic and therapeutic applications in epileptic patients.