Deep learning resting state fMRI lateralization of temporal lobe epilepsy

Epileptic brain network mechanisms and neuroimaging techniques for the brain network

Epilepsy can be defined as a dysfunction of the brain network, and each type of epilepsy involves different brain-network changes that are implicated differently in the control and propagation of interictal or ictal discharges. Gaining more detailed information on brain network alterations can help us to further understand the mechanisms of epilepsy and pave the way for brain network-based precise therapeutic approaches in clinical practice. An increasing number of advanced neuroimaging techniques and electrophysiological techniques such as diffusion tensor imaging-based fiber tractography, diffusion kurtosis imaging-based fiber tractography, fiber ball imaging-based tractography, electroencephalography, functional magnetic resonance imaging, magnetoencephalography, positron emission tomography, molecular imaging, and functional ultrasound imaging have been extensively used to delineate epileptic networks. In this review, we summarize the relevant neuroimaging and neuroelectrophysiological techniques for assessing structural and functional brain networks in patients with epilepsy, and extensively analyze the imaging mechanisms, advantages, limitations, and clinical application ranges of each technique. A greater focus on emerging advanced technologies, new data analysis software, a combination of multiple techniques, and the construction of personalized virtual epilepsy models can provide a theoretical basis to better understand the brain network mechanisms of epilepsy and make surgical decisions.

A DEEP LEARNING FRAMEWORK TO CHARACTERIZE NOISY LABELS IN EPILEPTOGENIC ZONE LOCALIZATION USING FUNCTIONAL CONNECTIVITY

Resting-sate fMRI (rs-fMRI) has emerged as a viable tool to localize the epileptogenic zone (EZ) in medication refractory focal epilepsy patients. However, due to clinical protocol, datasets with reliable labels for the EZ are scarce. Some studies have used the entire resection area from post-operative structural T1 scans to act as the ground truth EZ labels during training and testing. These labels are subject to noise, as usually the resection area will be larger than the actual EZ tissue. We develop a mathematical framework for characterizing noisy labels in EZ localization. We use a multi-task deep learning framework to identify both the probability of a noisy label as well as the localization prediction for each ROI. We train our framework on a simulated dataset derived from the Human Connectome Project and evaluate it on both the simulated and a clinical epilepsy dataset. We show superior localization performance in our method against published localization networks on both the real and simulated dataset.

The expert's knowledge combined with AI outperforms AI alone in seizure onset zone localization using resting state fMRI

We evaluated whether integration of expert guidance on seizure onset zone (SOZ) identification from resting state functional MRI (rs-fMRI) connectomics combined with deep learning (DL) techniques enhances the SOZ delineation in patients with refractory epilepsy (RE), compared to utilizing DL alone. Rs-fMRI was collected from 52 children with RE who had subsequently undergone ic-EEG and then, if indicated, surgery for seizure control (n = 25). The resting state functional connectomics data were previously independently classified by two expert epileptologists, as indicative of measurement noise, typical resting state network connectivity, or SOZ. An expert knowledge integrated deep network was trained on functional connectomics data to identify SOZ. Expert knowledge integrated with DL showed a SOZ localization accuracy of 84.8 ± 4.5% and F1 score, harmonic mean of positive predictive value and sensitivity, of 91.7 ± 2.6%. Conversely, a DL only model yielded an accuracy of <50% (F1 score 63%). Activations that initiate in gray matter, extend through white matter, and end in vascular regions are seen as the most discriminative expert-identified SOZ characteristics. Integration of expert knowledge of functional connectomics can not only enhance the performance of DL in localizing SOZ in RE but also lead toward potentially useful explanations of prevalent co-activation patterns in SOZ. RE with surgical outcomes and preoperative rs-fMRI studies can yield expert knowledge most salient for SOZ identification.

Imaging and Stereotactic Electroencephalography Functional Networks to Guide Epilepsy Surgery

Epilepsy surgery is a potentially curative treatment of drug-resistant epilepsy that has remained underutilized both due to inadequate referrals and incomplete localization hypotheses. The complexity of patients evaluated for epilepsy surgery has increased, thus new approaches are necessary to treat these patients. The paradigm of epilepsy surgery has evolved to match this challenge, now considering the entire seizure network with the goal of disrupting it through resection, ablation, neuromodulation, or a combination. The network paradigm has the potential to aid in identification of the seizure network as well as treatment selection.

Using Explainable Artificial Intelligence to Obtain Efficient Seizure-Detection Models Based on Electroencephalography Signals

Epilepsy is a condition that affects 50 million individuals globally, significantly impacting their quality of life. Epileptic seizures, a transient occurrence, are characterized by a spectrum of manifestations, including alterations in motor function and consciousness. These events impose restrictions on the daily lives of those affected, frequently resulting in social isolation and psychological distress. In response, numerous efforts have been directed towards the detection and prevention of epileptic seizures through EEG signal analysis, employing machine learning and deep learning methodologies. This study presents a methodology that reduces the number of features and channels required by simpler classifiers, leveraging Explainable Artificial Intelligence (XAI) for the detection of epileptic seizures. The proposed approach achieves performance metrics exceeding 95% in accuracy, precision, recall, and F1-score by utilizing merely six features and five channels in a temporal domain analysis, with a time window of 1 s. The model demonstrates robust generalization across the patient cohort included in the database, suggesting that feature reduction in simpler models-without resorting to deep learning-is adequate for seizure detection. The research underscores the potential for substantial reductions in the number of attributes and channels, advocating for the training of models with strategically selected electrodes, and thereby supporting the development of effective mobile applications for epileptic seizure detection.

Machine Learning and Artificial Intelligence Applications to Epilepsy: a Review for the Practicing Epileptologist

PURPOSE OF REVIEW

Machine Learning (ML) and Artificial Intelligence (AI) are data-driven techniques to translate raw data into applicable and interpretable insights that can assist in clinical decision making. Some of these tools have extremely promising initial results, earning both great excitement and creating hype. This non-technical article reviews recent developments in ML/AI in epilepsy to assist the current practicing epileptologist in understanding both the benefits and limitations of integrating ML/AI tools into their clinical practice.

RECENT FINDINGS

ML/AI tools have been developed to assist clinicians in almost every clinical decision including (1) predicting future epilepsy in people at risk, (2) detecting and monitoring for seizures, (3) differentiating epilepsy from mimics, (4) using data to improve neuroanatomic localization and lateralization, and (5) tracking and predicting response to medical and surgical treatments. We also discuss practical, ethical, and equity considerations in the development and application of ML/AI tools including chatbots based on Large Language Models (e.g., ChatGPT). ML/AI tools will change how clinical medicine is practiced, but, with rare exceptions, the transferability to other centers, effectiveness, and safety of these approaches have not yet been established rigorously. In the future, ML/AI will not replace epileptologists, but epileptologists with ML/AI will replace epileptologists without ML/AI.

Predicting Antiseizure Medication Treatment in Children with Rare Tuberous Sclerosis Complex-Related Epilepsy Using Deep Learning

BACKGROUND AND PURPOSE

Tuberous sclerosis complex disease is a rare, multisystem genetic disease, but appropriate drug treatment allows many pediatric patients to have positive outcomes. The purpose of this study was to predict the effectiveness of antiseizure medication treatment in children with tuberous sclerosis complex-related epilepsy.

MATERIALS AND METHODS

We conducted a retrospective study involving 300 children with tuberous sclerosis complex-related epilepsy. The study included the analysis of clinical data and T2WI and FLAIR images. The clinical data consisted of sex, age of onset, age at imaging, infantile spasms, and antiseizure medication numbers. To forecast antiseizure medication treatment, we developed a multitechnique deep learning method called WAE-Net. This method used multicontrast MR imaging and clinical data. The T2WI and FLAIR images were combined as FLAIR3 to enhance the contrast between tuberous sclerosis complex lesions and normal brain tissues. We trained a clinical data-based model using a fully connected network with the above-mentioned variables. After that, a weighted-average ensemble network built from the ResNet3D architecture was created as the final model.

RESULTS

The experiments had shown that age of onset, age at imaging, infantile spasms, and antiseizure medication numbers were significantly different between the 2 drug-treatment outcomes (P < .05). The hybrid technique of FLAIR3 could accurately localize tuberous sclerosis complex lesions, and the proposed method achieved the best performance (area under the curve = 0.908 and accuracy of 0.847) in the testing cohort among the compared methods.

CONCLUSIONS

The proposed method could predict antiseizure medication treatment of children with rare tuberous sclerosis complex-related epilepsy and could be a strong baseline for future studies.

Automatic diagnosis of schizophrenia and attention deficit hyperactivity disorder in rs-fMRI modality using convolutional autoencoder model and interval type-2 fuzzy regression

Nowadays, many people worldwide suffer from brain disorders, and their health is in danger. So far, numerous methods have been proposed for the diagnosis of Schizophrenia (SZ) and attention deficit hyperactivity disorder (ADHD), among which functional magnetic resonance imaging (fMRI) modalities are known as a popular method among physicians. This paper presents an SZ and ADHD intelligent detection method of resting-state fMRI (rs-fMRI) modality using a new deep learning method. The University of California Los Angeles dataset, which contains the rs-fMRI modalities of SZ and ADHD patients, has been used for experiments. The FMRIB software library toolbox first performed preprocessing on rs-fMRI data. Then, a convolutional Autoencoder model with the proposed number of layers is used to extract features from rs-fMRI data. In the classification step, a new fuzzy method called interval type-2 fuzzy regression (IT2FR) is introduced and then optimized by genetic algorithm, particle swarm optimization, and gray wolf optimization (GWO) techniques. Also, the results of IT2FR methods are compared with multilayer perceptron, k-nearest neighbors, support vector machine, random forest, and decision tree, and adaptive neuro-fuzzy inference system methods. The experiment results show that the IT2FR method with the GWO optimization algorithm has achieved satisfactory results compared to other classifier methods. Finally, the proposed classification technique was able to provide 72.71% accuracy.

Enhanced Dynamic Laterality Based on Functional Subnetworks in Patients with Bipolar Disorder

An ocean of studies have pointed to abnormal brain laterality changes in patients with bipolar disorder (BD). Determining the altered brain lateralization will help us to explore the pathogenesis of BD. Our study will fill the gap in the study of the dynamic changes of brain laterality in BD patients and thus provide new insights into BD research. In this work, we used fMRI data from 48 BD patients and 48 normal controls (NC). We constructed the dynamic laterality time series by extracting the dynamic laterality index (DLI) at each sliding window. We then used k-means clustering to partition the laterality states and the Arenas-Fernandez-Gomez (AFG) community detection algorithm to determine the number of states. We characterized subjects' laterality characteristics using the mean laterality index (MLI) and laterality fluctuation (LF). Compared with NC, in all windows and state 1, BD patients showed higher MLI in the attention network (AN) of the right hemisphere, and AN in the left hemisphere showed more frequent laterality fluctuations. AN in the left hemisphere of BD patients showed higher MLI in all windows and state 3 compared to NC. In addition, in the AN of the right hemisphere in state 1, higher MLI in BD patients was significantly associated with patient symptoms. Our study provides new insights into the understanding of BD neuropathology in terms of brain dynamic laterality.

Deep learning in neuroimaging of epilepsy

In recent years, artificial intelligence, particularly deep learning (DL), has demonstrated utility in diverse areas of medicine. DL uses neural networks to automatically learn features from the raw data while this is not possible with conventional machine learning. It is helpful for the assessment of patients with epilepsy and whilst most published studies have been aimed at the automatic detection and prediction of seizures from electroencephalographic records, there is a growing number of investigations that use neuroimaging modalities (structural and functional magnetic resonance imaging, diffusion-weighted imaging and positron emission tomography) as input data. We review the application of DL to neuroimaging (sMRI, fMRI, DWI and PET) of focal epilepsy, specifically presurgical evaluation of drug-refractory epilepsy. First, a brief theoretical overview of artificial neural networks and deep learning is presented. Next, we review applications of deep learning to neuroimaging of epilepsy: diagnosis and lateralization, automated detection of lesion, presurgical evaluation and prediction of postsurgical outcome. Finally, the limitations, challenges and possible future directions in the application of these methods in the study of epilepsies are discussed. This approach could become an essential tool in clinical practice, particularly in the evaluation of images considered negative by visual inspection, in individualized treatments, and in the approach to epilepsy as a network disorder. However, greater multicenter collaboration is required to achieve the collection of sufficient data with the required quality together with the open access availability of the developed codes and tools.

A DEEP LEARNING FRAMEWORK TO LOCALIZE THE EPILEPTOGENIC ZONE FROM DYNAMIC FUNCTIONAL CONNECTIVITY USING A COMBINED GRAPH CONVOLUTIONAL AND TRANSFORMER NETWORK

Localizing the epileptogenic zone (EZ) is a critical step in the treatment of medically refractory epilepsy. Resting-state fMRI (rs-fMRI) offers a new window into this task by capturing dynamically evolving co-activation patterns, also known as connectivity, in the brain. In this work, we present the first automated framework that uses dynamic functional connectivity from rs-fMRI to localize the EZ across a heterogeneous epilepsy cohort. Our framework uses a graph convolutional network for feature extraction, followed by a transformer network, whose attention mechanism learns which time points of the rs-fMRI scan are important for EZ localization. We train our framework on augmented data derived from the Human Connectome Project and evaluate it on a clinical epilepsy dataset. Our results demonstrate the clear advantages of our convolutional + transformer combination and data augmentation procedure over ablated and comparison models.

Functional anomaly mapping lateralizes temporal lobe epilepsy with high accuracy in individual patients

Mesial temporal lobe epilepsy (mTLE) is associated with variable dysfunction beyond the temporal lobe. We used functional anomaly mapping (FAM), a multivariate machine learning approach to resting state fMRI analysis to measure subcortical and cortical functional aberrations in patients with mTLE. We also examined the value of individual FAM in lateralizing the hemisphere of seizure onset in mTLE patients. Methods: Patients and controls were selected from an existing imaging and clinical database. After standard preprocessing of resting state fMRI, time-series were extracted from 400 cortical and 32 subcortical regions of interest (ROIs) defined by atlases derived from functional brain organization. Group-level aberrations were measured by contrasting right (RTLE) and left (LTLE) patient groups to controls in a support vector regression models, and tested for statistical reliability using permutation analysis. Individualized functional anomaly maps (FAMs) were generated by contrasting individual patients to the control group. Half of patients were used for training a classification model, and the other half for estimating the accuracy to lateralize mTLE based on individual FAMs. Results: Thirty-two right and 14 left mTLE patients (33 with evidence of hippocampal sclerosis on MRI) and 94 controls were included. At group levels, cortical regions affiliated with limbic and somatomotor networks were prominent in distinguishing RTLE and LTLE from controls. At individual levels, most TLE patients had high anomaly in bilateral mesial temporal and medial parietooccipital default mode regions. A linear support vector machine trained on 50% of patients could accurately lateralize mTLE in remaining patients (median AUC =1.0 [range 0.97-1.0], median accuracy = 96.87% [85.71-100Significance: Functional anomaly mapping confirms widespread aberrations in function, and accurately lateralizes mTLE from resting state fMRI. Future studies will evaluate FAM as a non-invasive localization method in larger datasets, and explore possible correlations with clinical characteristics and disease course.

Automated seizure onset zone locator from resting-state functional MRI in drug-resistant epilepsy

OBJECTIVE

Accurate localization of a seizure onset zone (SOZ) from independent components (IC) of resting-state functional magnetic resonance imaging (rs-fMRI) improves surgical outcomes in children with drug-resistant epilepsy (DRE). Automated IC sorting has limited success in identifying SOZ localizing ICs in adult normal rs-fMRI or uncategorized epilepsy. Children face unique challenges due to the developing brain and its associated surgical risks. This study proposes a novel SOZ localization algorithm (EPIK) for children with DRE.

METHODS

EPIK is developed in a phased approach, where fMRI noise-related biomarkers are used through high-fidelity image processing techniques to eliminate noise ICs. Then, the SOZ markers are used through a maximum likelihood-based classifier to determine SOZ localizing ICs. The performance of EPIK was evaluated on a unique pediatric DRE dataset (n = 52). A total of 24 children underwent surgical resection or ablation of an rs-fMRI identified SOZ, concurrently evaluated with an EEG and anatomical MRI. Two state-of-art techniques were used for comparison: (a) least squares support-vector machine and (b) convolutional neural networks. The performance was benchmarked against expert IC sorting and Engel outcomes for surgical SOZ resection or ablation. The analysis was stratified across age and sex.

RESULTS

EPIK outperformed state-of-art techniques for SOZ localizing IC identification with a mean accuracy of 84.7% (4% higher), a precision of 74.1% (22% higher), a specificity of 81.9% (3.2% higher), and a sensitivity of 88.6% (16.5% higher). EPIK showed consistent performance across age and sex with the best performance in those < 5 years of age. It helped achieve a ~5-fold reduction in the number of ICs to be potentially analyzed during pre-surgical screening.

SIGNIFICANCE

Automated SOZ localization from rs-fMRI, validated against surgical outcomes, indicates the potential for clinical feasibility. It eliminates the need for expert sorting, outperforms prior automated methods, and is consistent across age and sex.