Normalization enhances brain network features that predict individual intelligence in children with epilepsy

Using graph theory as a common language to combine neural structure and function in models of healthy cognitive performance

Graph theory has been used in cognitive neuroscience to understand how organisational properties of structural and functional brain networks relate to cognitive function. Graph theory may bridge the gap in integration of structural and functional connectivity by introducing common measures of network characteristics. However, the explanatory and predictive value of combined structural and functional graph theory have not been investigated in modelling of cognitive performance of healthy adults. In this work, a Principal Component Regression approach with embedded Step-Wise Regression was used to fit multiple regression models of Executive Function, Self-regulation, Language, Encoding and Sequence Processing with a collection of 20 different graph theoretic measures of structural and functional network organisation used as regressors. The predictive ability of graph theory-based models was compared to that of connectivity-based models. The present work shows that using combinations of graph theory metrics to predict cognition in healthy populations does not produce a consistent benefit relative to making predictions based on structural and functional connectivity values directly.

Localizing targets for neuromodulation in drug-resistant epilepsy using intracranial EEG and computational model

Neuromodulation has emerged as a promising technique for the treatment of epilepsy. The target for neuromodulation is critical for the effectiveness of seizure control. About 30% of patients with drug-resistant epilepsy (DRE) fail to achieve seizure freedom after surgical intervention. It is difficult to find effective brain targets for neuromodulation in these patients because brain regions are damaged during surgery. In this study, we propose a novel approach for localizing neuromodulatory targets, which uses intracranial EEG and multi-unit computational models to simulate the dynamic behavior of epileptic networks through external stimulation. First, we validate our method on a multivariate autoregressive model and compare nine different methods of constructing brain networks. Our results show that the directed transfer function with surrogate analysis achieves the best performance. Intracranial EEGs of 11 DRE patients are further analyzed. These patients all underwent surgery. In three seizure-free patients, the localized targets are concordant with the resected regions. For the eight patients without seizure-free outcome, the localized targets in three of them are outside the resected regions. Finally, we provide candidate targets for neuromodulation in these patients without seizure-free outcome based on virtual resected epileptic network. We demonstrate the ability of our approach to locate optimal targets for neuromodulation. We hope that our approach can provide a new tool for localizing patient-specific targets for neuromodulation therapy in DRE.

Individual-specific networks for prediction modelling – A scoping review of methods

Background

Recent advances in biotechnology enable the acquisition of high-dimensional data on individuals, posing challenges for prediction models which traditionally use covariates such as clinical patient characteristics. Alternative forms of covariate representations for the features derived from these modern data modalities should be considered that can utilize their intrinsic interconnection. The connectivity information between these features can be represented as an individual-specific network defined by a set of nodes and edges, the strength of which can vary from individual to individual. Global or local graph-theoretical features describing the network may constitute potential prognostic biomarkers instead of or in addition to traditional covariates and may replace the often unsuccessful search for individual biomarkers in a high-dimensional predictor space.

Methods

We conducted a scoping review to identify, collate and critically appraise the state-of-art in the use of individual-specific networks for prediction modelling in medicine and applied health research, published during 2000–2020 in the electronic databases PubMed, Scopus and Embase.

Results

Our scoping review revealed the main application areas namely neurology and pathopsychology, followed by cancer research, cardiology and pathology (N = 148). Network construction was mainly based on Pearson correlation coefficients of repeated measurements, but also alternative approaches (e.g. partial correlation, visibility graphs) were found. For covariates measured only once per individual, network construction was mostly based on quantifying an individual’s contribution to the overall group-level structure. Despite the multitude of identified methodological approaches for individual-specific network inference, the number of studies that were intended to enable the prediction of clinical outcomes for future individuals was quite limited, and most of the models served as proof of concept that network characteristics can in principle be useful for prediction.

Conclusion

The current body of research clearly demonstrates the value of individual-specific network analysis for prediction modelling, but it has not yet been considered as a general tool outside the current areas of application. More methodological research is still needed on well-founded strategies for network inference, especially on adequate network sparsification and outcome-guided graph-theoretical feature extraction and selection, and on how networks can be exploited efficiently for prediction modelling.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-022-01544-6.

Artificial Intelligence Applications in the Imaging of Epilepsy and Its Comorbidities: Present and Future

Artificial intelligence (AI) is increasingly used in medical image analysis and has accelerated scientific discoveries across fields of medicine. In this review, we highlight how AI has been applied to neuroimaging in patients with epilepsy to enhance classification of clinical diagnosis, prediction of treatment outcomes, and the understanding of cognitive comorbidities. We outline the strengths and shortcomings of current AI research and the need for future studies using large datasets that test the reproducibility and generalizability of current findings, as well as studies that test the clinical utility of AI approaches.

Principles and open questions in functional brain network reconstruction

Graph theory is now becoming a standard tool in system-level neuroscience. However, endowing observed brain anatomy and dynamics with a complex network representation involves often covert theoretical assumptions and methodological choices which affect the way networks are reconstructed from experimental data, and ultimately the resulting network properties and their interpretation. Here, we review some fundamental conceptual underpinnings and technical issues associated with brain network reconstruction, and discuss how their mutual influence concurs in clarifying the organization of brain function.

Diffuse white matter abnormality in very preterm infants at term reflects reduced brain network efficiency

•

Most preterm infants exhibit regions of high signal intensity on T2 MRI at term.

•

Debate remains as to whether this signal (DWMA) is pathological.

•

We quantified DWMA and used graph theory to measure brain network efficiency.

•

Whole-brain and regional network efficiency at term decreased with greater DWMA.

•

DWMA in very preterm infants is associated with reduced brain efficiency at term.

Between 50 and 80% of very preterm infants (<32 weeks gestational age) exhibit increased white matter signal intensity on T2-weighted MRI at term-equivalent age, known as diffuse white matter abnormality (DWMA). A few studies have linked DWMA with microstructural abnormalities, but the exact relationship remains poorly understood. We related DWMA extent to graph theory measures of network efficiency at term in a representative cohort of 343 very preterm infants. We performed anatomic and diffusion MRI at term and quantified DWMA volume with our novel, semi-automated algorithm. From diffusion-weighted structural connectomes, we calculated the graph theory metrics local efficiency and clustering coefficient, which measure the ability of groups of nodes to perform specialized processing, and global efficiency, which assesses the ability of brain regions to efficiently combine information. We computed partial correlations between these measures and DWMA volume, adjusted for confounders. Increasing DWMA volume was associated with decreased global efficiency of the entire very preterm brain and decreased local efficiency and clustering coefficient in a variety of regions supporting cognitive, linguistic, and motor function. We show that DWMA is associated with widespread decreased brain network efficiency, suggesting that it is pathologic and likely has adverse developmental consequences.

Clinical Application of Machine Learning Models for Brain Imaging in Epilepsy: A Review

Epilepsy is a common neurological disorder characterized by recurrent and disabling seizures. An increasing number of clinical and experimental applications of machine learning (ML) methods for epilepsy and other neurological and psychiatric disorders are available. ML methods have the potential to provide a reliable and optimal performance for clinical diagnoses, prediction, and personalized medicine by using mathematical algorithms and computational approaches. There are now several applications of ML for epilepsy, including neuroimaging analyses. For precise and reliable clinical applications in epilepsy and neuroimaging, the diverse ML methodologies should be examined and validated. We review the clinical applications of ML models for brain imaging in epilepsy obtained from a PubMed database search in February 2021. We first present an overview of typical neuroimaging modalities and ML models used in the epilepsy studies and then focus on the existing applications of ML models for brain imaging in epilepsy based on the following clinical aspects: (i) distinguishing individuals with epilepsy from healthy controls, (ii) lateralization of the temporal lobe epilepsy focus, (iii) the identification of epileptogenic foci, (iv) the prediction of clinical outcomes, and (v) brain-age prediction. We address the practical problems and challenges described in the literature and suggest some future research directions.

Localization of epileptic seizure focus by computerized analysis of fMRI recordings

By computerized analysis of cortical activity recorded via fMRI for pediatric epilepsy patients, we implement algorithmic localization of epileptic seizure focus within one of eight cortical lobes. Our innovative machine learning techniques involve intensive analysis of large matrices of mutual information coefficients between pairs of anatomically identified cortical regions. Drastic selection of pairs of regions with biologically significant inter-connectivity provides efficient inputs for our multi-layer perceptron (MLP) classifier. By imposing rigorous parameter parsimony to avoid overfitting, we construct a small-size MLP with very good percentages of successful classification.

Effects of unilateral cortical resection of the visual cortex on bilateral human white matter

Children with unilateral resections of ventral occipito-temporal cortex (VOTC) typically do not evince visual perceptual impairments, even when relatively large swathes of VOTC are resected. In search of possible explanations for this behavioral competence, we evaluated white matter microstructure and connectivity in eight pediatric epilepsy patients following unilateral cortical resection and 15 age-matched controls. To uncover both local and broader resection-induced effects, we analyzed tractography data using two complementary approaches. First, the microstructural properties were measured in the inferior longitudinal and the inferior fronto-occipital fasciculi, the major VOTC association tracts. Group differences were only evident in the ipsilesional, and not in the contralesional, hemisphere, and single-subject analyses revealed that these differences were limited to the site of the resection. Second, graph theory was used to characterize the connectivity of the contralesional occipito-temporal regions. There were no changes to the network properties in patients with left VOTC resections nor in patients with resections outside the VOTC, but altered network efficiency was observed in two cases with right VOTC resections. These results suggest that, in many, although perhaps not all, cases of unilateral VOTC resections in childhood, the white matter profile in the preserved contralesional hemisphere along with residual neural activity might be sufficient for normal visual perception.