Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia

Focal cortical dysplasia detection by artificial intelligence using MRI: A systematic review and meta-analysis

PURPOSE

Focal cortical dysplasia (FCD) is a common cause of pharmacoresistant epilepsy. However, it can be challenging to detect FCD using MRI alone. This study aimed to review and analyze studies that used machine learning and artificial neural networks (ANN) methods as an additional tool to enhance MRI findings in FCD patients.

METHODS

A systematic search was conducted in four databases (Embase, PubMed, Scopus, and Web of Science). The quality of the studies was assessed using QUADAS-AI, and a bivariate random-effects model was used for analysis. The main outcome analyzed was the sensitivity and specificity of patient-wise outcomes. Heterogeneity among studies was assessed using I2.

RESULTS

A total of 41 studies met the inclusion criteria, including 24 ANN-based studies and 17 machine learning studies. Meta-analysis of internal validation datasets showed a pooled sensitivity of 0.81 and specificity of 0.92 for AI-based models in detecting FCD lesions. Meta-analysis of external validation datasets yielded a pooled sensitivity of 0.73 and specificity of 0.66. There was moderate heterogeneity among studies in the external validation dataset, but no significant publication bias was found.

CONCLUSION

Although there is an increasing number of machine learning and ANN-based models for FCD detection, their clinical applicability remains limited. Further refinement and optimization, along with longitudinal studies, are needed to ensure their integration into clinical practice. Addressing the identified limitations and intensifying research efforts will improve their relevance and reliability in real medical scenarios.

Harmonization of MRI sequences across ERN EpiCARE centers

Neuroimaging investigations are fundamental in the diagnosis of patients with epilepsy. The International League Against Epilepsy (ILAE) harmonized neuroimaging of epilepsy structural sequences (HARNESS-MRI) protocol was intended as a generalizable structural MRI protocol. The European Reference Network for Rare and Complex Epilepsies, EpiCARE, includes 50 centers, across 26 countries, with expertise in epilepsy. We investigated adherence to the HARNESS-MRI protocol across EpiCARE. A survey on the clinical use of imaging and postprocessing methods in epilepsy patients was distributed among the centers. A descriptive analysis was performed, and results were compared to existing guidelines, as well as a previous survey in 2016. 79% of centers were adhering to the HARNESS-MRI protocol in all epilepsy patients. All centers were acquiring 3D T1-weighted sequences, 90% were acquiring 3D FLAIR and 87% were acquiring high in-plane 2D coronal T2 MRI sequences in all epilepsy patients. In comparison, in 2016, only 50% of centers were following MRI recommendations at the time. Across European expert epilepsy centers, there has been increased harmonization of MRI sequences since the introduction of the HARNESS-MRI protocol. This standardization supports optimal radiological review at individual centers as well as enabling harmonization of multicenter datasets for research. PLAIN LANGUAGE SUMMARY: Neuroimaging investigations are a fundamental component of epilepsy diagnosis. The International League Against Epilepsy (ILAE) has created guidelines about what MRI images to obtain in all epilepsy patients. In this study, we assessed the adherence of expert European epilepsy centers to these guidelines and found that 79% are acquiring the minimum set of MRI scans in all epilepsy patients. Standardization of MRI imaging serves to improve epilepsy diagnosis across Europe.

Detection of focal cortical dysplasia: Development and multicentric evaluation of artificial intelligence models

OBJECTIVE

Focal cortical dysplasia (FCD) is a common cause of drug-resistant focal epilepsy but can be challenging to detect visually on magnetic resonance imaging. Three artificial intelligence models for automated FCD detection are publicly available (MAP18, deepFCD, MELD) but have only been compared on single-center data. Our first objective is to compare them on independent multicenter test data. Additionally, we train and compare three new models and make them publicly available.

METHODS

We retrospectively collected FCD cases from four epilepsy centers. We chose three novel models that take two-dimensional (2D) slices (2D-nnUNet), 2.5D slices (FastSurferCNN), and large 3D patches (3D-nnUNet) as inputs and trained them on a subset of Bonn data. As core evaluation metrics, we used voxel-level Dice similarity coefficient (DSC), cluster-level F1 score, subject-level detection rate, and specificity.

RESULTS

We collected 329 subjects, 244 diagnosed with FCD (27.7 ± 14.4 years old, 54% male) and 85 healthy controls (7.1 ± 2.4 years old, 51% female). We used 118 subjects for model training and kept the remaining subjects as an independent test set. 3D-nnUNet achieved the highest F1 score of .58, the highest DSC of .36 (95% confidence interval [CI] = .30-.41), a detection rate of 55%, and a specificity of 86%. deepFCD showed the highest detection rate (82%) but had the lowest specificity (0%) and cluster-level precision (.03, 95% CI = .03-.04, F1 score = .07). MELD showed the least performance variation across centers, with detection rates between 46% and 54%.

SIGNIFICANCE

This study shows the variance in performance for FCD detection models in a multicenter dataset. The two models with 3D input data showed the highest sensitivity. The 2D models performed worse than all other models, suggesting that FCD detection requires 3D data. The greatly improved precision of 3D-nnUNet may make it a sensible choice to aid FCD detection.

Voxel-based and surface-based cortical morphometric MRI applications for identifying the epileptogenic zone: A narrative review

Approximately 40% of patients with drug-resistant epilepsy referred for surgical evaluation have no epileptogenic lesion on MRI (MRI-negative). MRI-negative epilepsy is associated with poorer seizure freedom prognosis and has therefore motivated the development of structural post-processing methods to "convert" MRI-negative to MRI-positive cases. In this article, we review the principles, advances, and challenges of voxel- and surface-based cortical morphometric MRI techniques in detecting the epileptogenic zone. The ground truth for the presumed epileptogenic zone in imaging studies can be classified into lesion-based (MRI lesion mask or histopathology) or epileptogenicity-based ground truth (anatomical-electroclinical correlations or resections that lead to seizure freedom). Voxel-based techniques are reported to have a 13%-97% concordance rate, while surface-based techniques have 67%-92% compared to lesion-based ground truths. Epileptogenicity-based ground truth may be more relevant in the case of MRI-negative cases; however, the sensitivity and concordance rate (voxel-based technique 7.1%-66.7%, and surface-based technique 62%) are limited by the reliance on scalp EEG and qualitative analysis of seizure-onset pattern. The use of stereo-EEG and quantitative EEG analysis may fill this gap to evaluate the correlation between cortical morphometry results and electrophysiological epileptogenic biomarkers of the epileptogenic zone and help improve the yield of structural post-processing tools. PLAIN LANGUAGE SUMMARY: Locating the epileptogenic zone (the brain area that is responsible for seizure generation) is important to diagnose and plan epilepsy treatments. An abnormal brain imaging (MRI) result can help clinical decision-making; however, around 40% of patients have normal MRI results (MRI-negative). We are reviewing the potential of two advanced MRI methods (voxel- and surface-based cortical morphometry) to localize the epileptogenic zone in the presence or absence of visible MRI abnormalities. We also describe the current challenge of applying the above methods in daily clinical practice and propose using advanced brain recording analysis to aid this translation process.

ILAE neuroimaging task force highlight: The utility of multimodal neuroimaging in diagnostic and presurgical workup of drug-resistant focal epilepsy

The ILAE Neuroimaging Task Force publishes educational case reports that highlight basic aspects of neuroimaging in epilepsy, consistent with ILAE's educational mission. In patients with drug-resistant focal epilepsy who are candidates for surgical intervention, the identification of structural abnormalities is a strong predictor of favorable postoperative seizure outcomes. When conventional imaging is insufficient, the integration of multimodal neuroimaging data with structural, metabolic, and functional imaging modalities is often helpful. The following two illustrative cases from two different centers highlight the challenges and needs to integrate the information from multiple imaging modalities for a more accurate diagnosis and resection planning of drug-resistant focal epilepsies. This approach can increase the number of patients eligible for surgery while minimizing the risk of postoperative deficits.

Three-branch feature enhancement and fusion network for focal cortical dysplasia lesions segmentation using multimodal imaging

OBJECTIVE

Conventional multimodal imaging, including MRI and fluorodeoxyglucose positron emission tomography (FDG-PET), has difficulty in accurately detecting subtle or blurred focal cortical dysplasia (FCD) lesions. Morphometric maps assist localization by highlighting abnormal regions, whereas wavelet-filtered images emphasize texture and edge details. Therefore, we propose a three-branch feature enhancement and fusion network (TBFEF-Net) that integrates conventional multimodal imaging, morphometric maps, and wavelet-filtered images to enhance the accuracy of FCD localization.

METHODS

The proposed TBFEF-Net comprises a semantic segmentation backbone, a cross-branch feature enhancement (CFE) module, and a multi-feature fusion (MFF) module. In the semantic segmentation backbone, three UNet-based branches separately extract semantic features from conventional multimodal imaging, morphometric maps, and wavelet-filtered images. In the encoding stage, the CFE incorporates a residual-based convolutional block attention module (CBAM) to aggregate features from all branches, enhancing the feature representation of FCD lesions. While in the decoding stage, the MFF integrates edge detail features from the wavelet-filtered imaging branch into the conventional multimodal imaging branch, enhancing the ability to capture lesion edges. As a result, this approach enables more precise segmentation.

RESULTS

Experimental results show that TBFEF-Net surpasses several state-of-the-art methods in FCD segmentation. In the primary cohort, the Dice and sensitivity reached 59.73 % and 67.13 %, respectively, while in the open cohort, the Dice and sensitivity were 54.67 % and 54.81 %, respectively.

SIGNIFICANCE

We introduced wavelet-filtered images for the first time in FCD segmentation, offering a novel approach and perspective for FCD lesions localization.

Detection of Epileptogenic Focal Cortical Dysplasia Using Graph Neural Networks: A MELD Study

Importance

A leading cause of surgically remediable, drug-resistant focal epilepsy is focal cortical dysplasia (FCD). FCD is challenging to visualize and often considered magnetic resonance imaging (MRI) negative. Existing automated methods for FCD detection are limited by high numbers of false-positive predictions, hampering their clinical utility.

Objective

To evaluate the efficacy and interpretability of graph neural networks in automatically detecting FCD lesions on MRI scans.

Design, Setting, and Participants

In this multicenter diagnostic study, retrospective MRI data were collated from 23 epilepsy centers worldwide between 2018 and 2022, as part of the Multicenter Epilepsy Lesion Detection (MELD) Project, and analyzed in 2023. Data from 20 centers were split equally into training and testing cohorts, with data from 3 centers withheld for site-independent testing. A graph neural network (MELD Graph) was trained to identify FCD on surface-based features. Network performance was compared with an existing algorithm. Feature analysis, saliencies, and confidence scores were used to interpret network predictions. In total, 34 surface-based MRI features and manual lesion masks were collated from participants, 703 patients with FCD-related epilepsy and 482 controls, and 57 participants were excluded during MRI quality control.

Main Outcomes and Measures

Sensitivity, specificity, and positive predictive value (PPV) of automatically identified lesions.

Results

In the test dataset, the MELD Graph had a sensitivity of 81.6% in histopathologically confirmed patients seizure-free 1 year after surgery and 63.7% in MRI-negative patients with FCD. The PPV of putative lesions from the 260 patients in the test dataset (125 female [48%] and 135 male [52%]; mean age, 18.0 [IQR, 11.0-29.0] years) was 67% (70% sensitivity; 60% specificity), compared with 39% (67% sensitivity; 54% specificity) using an existing baseline algorithm. In the independent test cohort (116 patients; 62 female [53%] and 54 male [47%]; mean age, 22.5 [IQR, 13.5-27.5] years), the PPV was 76% (72% sensitivity; 56% specificity), compared with 46% (77% sensitivity; 47% specificity) using the baseline algorithm. Interpretable reports characterize lesion location, size, confidence, and salient features.

Conclusions and Relevance

In this study, the MELD Graph represented a state-of-the-art, openly available, and interpretable tool for FCD detection on MRI scans with significant improvements in PPV. Its clinical implementation holds promise for early diagnosis and improved management of focal epilepsy, potentially leading to better patient outcomes.

Lateralizing Value of Artificial Intelligence-Based Segmentation Software in MRI-Negative Focal Epilepsy

Background and Purpose

The magnetic resonance images (MRIs) ability of lesion detection in epilepsy is crucial for a diagnosis and surgical outcome. Using automated artificial intelligence (AI)-based tools for measuring cortical thickness and brain volume originally developed for dementia, we aimed to identify whether it could lateralize epilepsy with normal MRIs.

Methods

Non-lesional 3-Tesla MRIs of 428 patients diagnosed with focal epilepsy, based on semiology and electroencephalography findings, were analyzed. AI-based segmentation/volumetry software measured the cortical thickness and the hippocampal volume. The laterality index (LI) was calculated.

Results

We classified into temporal lobe epilepsy (TLE, n=294), frontal lobe epilepsy (FLE, n=86), occipital lobe epilepsy (OLE, n=29), and parietal lobe epilepsy (PLE, n=22). Onset age and MRI age were 24.0±16.6 (0-84) and 35.6±14.8 (16-84) years old. In FLE, the LI of frontal thickness was significantly different between the left and right FLE groups, with LIs of the right FLE group being right-shifted and those of the left FLE group being left-shifted, indicating that the lesion side was thinner than the non-lesion side (p=0.01). The discriminable group, which included the patients with left FLE and a LI lower than minus one standard deviation, as well as the patients with right FLE and a LI higher than one standard deviation, showed a longer duration of epilepsy than the non-discriminable group (12.7±9.9 vs. 8.3±7.7 years; p=0.03). Specifically, the LI of individual regions of interest showed that the rostral middle frontal cortex was significantly different in FLE. However, the TLE, PLE, OLE, and LIs were not significantly different.

Conclusions

AI-based brain segmentation software can be helpful to decide the laterality of non-lesional FLE especially with longer duration of disease.

Big data research is everyone's research-Making epilepsy data science accessible to the global community: Report of the ILAE big data commission

Epilepsy care generates multiple sources of high-dimensional data, including clinical, imaging, electroencephalographic, genomic, and neuropsychological information, that are collected routinely to establish the diagnosis and guide management. Thanks to high-performance computing, sophisticated graphics processing units, and advanced analytics, we are now on the cusp of being able to use these data to significantly improve individualized care for people with epilepsy. Despite this, many clinicians, health care providers, and people with epilepsy are apprehensive about implementing Big Data and accompanying technologies such as artificial intelligence (AI). Practical, ethical, privacy, and climate issues represent real and enduring concerns that have yet to be completely resolved. Similarly, Big Data and AI-related biases have the potential to exacerbate local and global disparities. These are highly germane concerns to the field of epilepsy, given its high burden in developing nations and areas of socioeconomic deprivation. This educational paper from the International League Against Epilepsy's (ILAE) Big Data Commission aims to help clinicians caring for people with epilepsy become familiar with how Big Data is collected and processed, how they are applied to studies using AI, and outline the immense potential positive impact Big Data can have on diagnosis and management.

Application of preoperative MRI lesion identification algorithm in pediatric and young adult focal cortical dysplasia-related epilepsy

OBJECTIVE

The purpose of this study was to evaluate the performance and generalizability of an automated, interpretable surface-based MRI classifier for the detection of focal cortical dysplasia.

METHODS

This was a retrospective cohort incorporating MRIs from the epilepsy surgery (FCD and MRI-negative) and neuroimaging (healthy controls) databases at Children's National Hospital (CNH), and a publicly-available FCD Type II dataset from Bonn, Germany. Clinical characteristics and outcomes were abstracted from patient records and/or existing databases. Subjects were included if they had 3T epilepsy-protocol MRI. Manually-segmented FCD masks were compared to the automated masks generated by the Multi-centre Epilepsy Lesion Detection (MELD) FCD detection algorithm. Sensitivity/specificity were calculated.

RESULTS

From CNH, 39 FCD pharmacoresistant epilepsy (PRE) patients, 19 healthy controls, and 19 MRI-negative patients were included. From Bonn, 85 FCD Type II were included, of which 68 passed preprocessing. MELD had varying performance (sensitivity) in these datasets: CNH FCD-PRE (54 %); Bonn (68 %); MRI-negative (44 %). In multivariate regression, FCD Type IIB pathology predicted higher chance of MELD automated lesion detection. All four patients who underwent resection/ablation of MELD-identified clusters achieved Engel I outcome.

SIGNIFICANCE

We validate the performance of MELD automated, interpretable FCD classifier in a diverse pediatric cohort with FCD-PRE. We also demonstrate the classifier has relatively good performance in an independent FCD Type II cohort with pediatric-onset epilepsy, as well as simulated real-world value in a pediatric population with MRI-negative PRE.

Frontal Lobe Epilepsy: Bermuda's Triangle

Despite great progress in imaging, genetics, surgery, and therapeutics, frontal lobe epilepsy (FLE) continues to be a challenge for neurologists and epileptologists. This manuscript summarizes the latest advancements in FLE discussed at the 2023 Epilepsy Specialist Symposium during the American Epilepsy Society Annual meeting. Correlation between stereoelectroencephalography and clinical symptoms has reinvigorated symptomatology literature in FLE, allowing for more precise aura anatomical localization. Neuropsychological assessments permit the identification of different FLE cognitive phenotypes, with language being the most prominent domain-specific impairment. These tests can help develop psychotherapeutic and cognitive support systems for these patients. Genetic and molecular studies have uncovered specific genes associated with FLE susceptibility, offering prospects for targeted therapies. Advanced neuroimaging techniques such as high field magnetic resonance imaging (MRI), functional MRI (fMRI), magnetoencephalography and colocalization of multiple imaging techniques have led to more precise localization of the epileptogenic zone providing insights into the dynamic neural networks underlying frontal lobe seizures. This has facilitated guided therapeutic surgical interventions that can be employed around the world, expanding access of these technologies to multiple populations. Despite many advances, prognosis of FLE remains poor for some patients. The biggest determinant for poor prognosis continues to be nonlesional FLE. Newer technological advancements aim to pass these barriers and offer FLE patients a better quality of life with lower seizure burden and higher cognitive outcomes.

Focal cortical dysplasia lesion segmentation using multiscale transformer

OBJECTIVES

Accurate segmentation of focal cortical dysplasia (FCD) lesions from MR images plays an important role in surgical planning and decision but is still challenging for radiologists and clinicians. In this study, we introduce a novel transformer-based model, designed for the end-to-end segmentation of FCD lesions from multi-channel MR images.

METHODS

The core innovation of our proposed model is the integration of a convolutional neural network-based encoder-decoder structure with a multiscale transformer to augment the feature representation of lesions in the global field of view. Transformer pathways, composed of memory- and computation-efficient dual-self-attention modules, leverage feature maps from varying depths of the encoder to discern long-range interdependencies among feature positions and channels, thereby emphasizing areas and channels relevant to lesions. The proposed model was trained and evaluated on a public-open dataset including MR images of 85 patients using both subject-level and voxel-level metrics.

RESULTS

Experimental results indicate that our model offers superior performance both quantitatively and qualitatively. It successfully identified lesions in 82.4% of patients, with a low false-positive lesion cluster rate of 0.176 ± 0.381 per patient. Furthermore, the model achieved an average Dice coefficient of 0.410 ± 0.288, outperforming five established methods.

CONCLUSION

Integration of the transformer could enhance the feature presentation and segmentation performance of FCD lesions. The proposed model has the potential to serve as a valuable assistive tool for physicians, enabling rapid and accurate identification of FCD lesions. The source code and pre-trained model weights are available at https://github.com/zhangxd0530/MS-DSA-NET .

CRITICAL RELEVANCE STATEMENT

This multiscale transformer-based model performs segmentation of focal cortical dysplasia lesions, aiming to help radiologists and clinicians make accurate and efficient preoperative evaluations of focal cortical dysplasia patients from MR images.

KEY POINTS

The first transformer-based model was built to explore focal cortical dysplasia lesion segmentation. Integration of global and local features enhances the segmentation performance of lesions. A valuable benchmark for model development and comparative analyses was provided.

WONOEP 2022: Neurotechnology for the diagnosis of epilepsy

Epilepsy's myriad causes and clinical presentations ensure that accurate diagnoses and targeted treatments remain a challenge. Advanced neurotechnologies are needed to better characterize individual patients across multiple modalities and analytical techniques. At the XVIth Workshop on Neurobiology of Epilepsy: Early Onset Epilepsies: Neurobiology and Novel Therapeutic Strategies (WONOEP 2022), the session on "advanced tools" highlighted a range of approaches, from molecular phenotyping of genetic epilepsy models and resected tissue samples to imaging-guided localization of epileptogenic tissue for surgical resection of focal malformations. These tools integrate cutting edge research, clinical data acquisition, and advanced computational methods to leverage the rich information contained within increasingly large datasets. A number of common challenges and opportunities emerged, including the need for multidisciplinary collaboration, multimodal integration, potential ethical challenges, and the multistage path to clinical translation. Despite these challenges, advanced epilepsy neurotechnologies offer the potential to improve our understanding of the underlying causes of epilepsy and our capacity to provide patient-specific treatment.

Identification and treatment of surgically-remediable causes of infantile epileptic spasms syndrome

INTRODUCTION

Infantile epileptic spasms syndrome (IESS) is a common developmental and epileptic encephalopathy with poor long-term outcomes. A substantial proportion of patients with IESS have a potentially surgically remediable etiology. Despite this, epilepsy surgery is underutilized in this patient group. Some surgically remediable etiologies, such as focal cortical dysplasia and malformation of cortical development with oligodendroglial hyperplasia in epilepsy (MOGHE), are under-diagnosed in infants and young children. Even when a surgically remediable etiology is recognised, for example, tuberous sclerosis or focal encephalomalacia, epilepsy surgery may be delayed or not considered due to diffuse EEG changes, unclear surgical boundaries, or concerns about operating in this age group.

AREAS COVERED

In this review, the authors discuss the common surgically remediable etiologies of IESS, their clinical and EEG features, and the imaging techniques that can aid in their diagnosis. They then describe the surgical approaches used in this patient group, and the beneficial impact that early epilepsy surgery can have on developing brain networks.

EXPERT OPINION

Epilepsy surgery remains underutilized even when a potentially surgically remediable cause is recognized. Overcoming the barriers that result in under-recognition of surgical candidates and underutilization of epilepsy surgery in IESS will improve long-term seizure and developmental outcomes.

The new era of artificial intelligence in neuroradiology: current research and promising tools

Radiology has a number of characteristics that make it an especially suitable medical discipline for early artificial intelligence (AI) adoption. These include having a well-established digital workflow, standardized protocols for image storage, and numerous well-defined interpretive activities. The more than 200 commercial radiologic AI-based products recently approved by the Food and Drug Administration (FDA) to assist radiologists in a number of narrow image-analysis tasks such as image enhancement, workflow triage, and quantification, corroborate this observation. However, in order to leverage AI to boost efficacy and efficiency, and to overcome substantial obstacles to widespread successful clinical use of these products, radiologists should become familiarized with the emerging applications in their particular areas of expertise. In light of this, in this article we survey the existing literature on the application of AI-based techniques in neuroradiology, focusing on conditions such as vascular diseases, epilepsy, and demyelinating and neurodegenerative conditions. We also introduce some of the algorithms behind the applications, briefly discuss a few of the challenges of generalization in the use of AI models in neuroradiology, and skate over the most relevant commercially available solutions adopted in clinical practice. If well designed, AI algorithms have the potential to radically improve radiology, strengthening image analysis, enhancing the value of quantitative imaging techniques, and mitigating diagnostic errors.

Artificial intelligence in epilepsy - applications and pathways to the clinic

Artificial intelligence (AI) is rapidly transforming health care, and its applications in epilepsy have increased exponentially over the past decade. Integration of AI into epilepsy management promises to revolutionize the diagnosis and treatment of this complex disorder. However, translation of AI into neurology clinical practice has not yet been successful, emphasizing the need to consider progress to date and assess challenges and limitations of AI. In this Review, we provide an overview of AI applications that have been developed in epilepsy using a variety of data modalities: neuroimaging, electroencephalography, electronic health records, medical devices and multimodal data integration. For each, we consider potential applications, including seizure detection and prediction, seizure lateralization, localization of the seizure-onset zone and assessment for surgical or neurostimulation interventions, and review the performance of AI tools developed to date. We also discuss methodological considerations and challenges that must be addressed to successfully integrate AI into clinical practice. Our goal is to provide an overview of the current state of the field and provide guidance for leveraging AI in future to improve management of epilepsy.

Development and prospective clinical validation of a convolutional neural network for automated detection and segmentation of focal cortical dysplasias

PURPOSE

Focal cortical dysplasias (FCDs) are a leading cause of drug-resistant epilepsy. Early detection and resection of FCDs have favorable prognostic implications for postoperative seizure freedom. Despite advancements in imaging methods, FCD detection remains challenging. House et al. (2021) introduced a convolutional neural network (CNN) for automated FCD detection and segmentation, achieving a sensitivity of 77.8%. However, its clinical applicability was limited due to a low specificity of 5.5%. The objective of this study was to improve the CNN's performance through data-driven training and algorithm optimization, followed by a prospective validation on daily-routine MRIs.

MATERIAL AND METHODS

A dataset of 300 3 T MRIs from daily clinical practice, including 3D T1 and FLAIR sequences, was prospectively compiled. The MRIs were visually evaluated by two neuroradiologists and underwent morphometric assessment by two epileptologists. The dataset included 30 FCD cases (11 female, mean age: 28.1 ± 10.1 years) and a control group of 150 normal cases (97 female, mean age: 32.8 ± 14.9 years), along with 120 non-FCD pathological cases (64 female, mean age: 38.4 ± 18.4 years). The dataset was divided into three subsets, each analyzed by the CNN. Subsequently, the CNN underwent a two-phase-training process, incorporating subset MRIs and expert-labeled FCD maps. This training employed both classical and continual learning techniques. The CNN's performance was validated by comparing the baseline model with the trained models at two training levels.

RESULTS

In prospective validation, the best model trained using continual learning achieved a sensitivity of 90.0%, specificity of 70.0%, and accuracy of 72.0%, with an average of 0.41 false positive clusters detected per MRI. For FCD segmentation, an average Dice coefficient of 0.56 was attained. The model's performance improved in each training phase while maintaining a high level of sensitivity. Continual learning outperformed classical learning in this regard.

CONCLUSIONS

Our study presents a promising CNN for FCD detection and segmentation, exhibiting both high sensitivity and specificity. Furthermore, the model demonstrates continuous improvement with the inclusion of more clinical MRI data. We consider our CNN a valuable tool for automated, examiner-independent FCD detection in daily clinical practice, potentially addressing the underutilization of epilepsy surgery in drug-resistant focal epilepsy and thereby improving patient outcomes.

[18F]SynVesT-1 and [18F]FDG quantitative PET imaging in the presurgical evaluation of MRI-negative children with focal cortical dysplasia type II

PURPOSE

MRI-negative children with focal cortical dysplasia type II (FCD II) are one of the most challenging cases in surgical epilepsy management. We aimed to utilize quantitative positron emission tomography (QPET) analysis to complement [18F]SynVesT-1 and [18F]FDG PET imaging and facilitate the localization of epileptogenic foci in pediatric MRI-negative FCD II patients.

METHODS

We prospectively enrolled 17 MRI-negative children with FCD II who underwent [18F]SynVesT-1 and [18F]FDG PET before surgical resection. The QPET scans were analyzed using statistical parametric mapping (SPM) with respect to healthy controls. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC) of [18F]SynVesT-1 PET, [18F]FDG PET, [18F]SynVesT-1 QPET, and [18F]FDG QPET in the localization of epileptogenic foci were assessed. Additionally, we developed a multivariate prediction model based on dual trace PET/QPET assessment.

RESULTS

The AUC values of [18F]FDG PET and [18F]SynVesT-1 PET were 0.861 (sensitivity = 94.1%, specificity = 78.2%, PPV = 38.1%, NPV = 98.9%) and 0.908 (sensitivity = 82.4%, specificity = 99.2%, PPV = 93.3%, NPV = 97.5%), respectively. [18F]FDG QPET showed lower sensitivity (76.5%) and NPV (96.6%) but higher specificity (95.0%) and PPV (68.4%) than visual assessment, while [18F]SynVesT-1 QPET exhibited higher sensitivity (94.1%) and NPV (99.1%) but lower specificity (97.5%) and PPV (84.2%). The multivariate prediction model had the highest AUC value (AUC = 0.996, sensitivity = 100.0%, specificity = 96.6%, PPV = 81.0%, NPV = 100%).

CONCLUSIONS

The multivariate prediction model based on [18F]SynVesT-1 and [18F]FDG PET/QPET assessments holds promise in noninvasively identifying epileptogenic regions in MRI-negative children with FCD II. Furthermore, the combination of visual assessment and QPET may improve the sensitivity and specificity of diagnostic tests in localizing epileptogenic foci and achieving a preferable surgical outcome in MRI-negative FCD II.

Deep learning-based automated lesion segmentation on pediatric focal cortical dysplasia II preoperative MRI: a reliable approach

OBJECTIVES

Focal cortical dysplasia (FCD) represents one of the most common causes of refractory epilepsy in children. Deep learning demonstrates great power in tissue discrimination by analyzing MRI data. A prediction model was built and verified using 3D full-resolution nnU-Net for automatic lesion detection and segmentation of children with FCD II.

METHODS

High-resolution brain MRI structure data from 65 patients, confirmed with FCD II by pathology, were retrospectively studied. Experienced neuroradiologists segmented and labeled the lesions as the ground truth. Also, we used 3D full-resolution nnU-Net to segment lesions automatically, generating detection maps. The algorithm was trained using fivefold cross-validation, with data partitioned into training (N = 200) and testing (N = 15). To evaluate performance, detection maps were compared to expert manual labels. The Dice-Sørensen coefficient (DSC) and sensitivity were used to assess the algorithm performance.

RESULTS

The 3D nnU-Net showed a good performance for FCD lesion detection at the voxel level, with a sensitivity of 0.73. The best segmentation model achieved a mean DSC score of 0.57 on the testing dataset.

CONCLUSION

This pilot study confirmed that 3D full-resolution nnU-Net can automatically segment FCD lesions with reliable outcomes. This provides a novel approach to FCD lesion detection.

CRITICAL RELEVANCE STATEMENT

Our fully automatic models could process the 3D T1-MPRAGE data and segment FCD II lesions with reliable outcomes.

KEY POINTS

• Simplified image processing promotes the DL model implemented in clinical practice. • The histopathological confirmed lesion masks enhance the clinical credibility of the AI model. • The voxel-level evaluation metrics benefit lesion detection and clinical decisions.

Combining OPM and lesion mapping data for epilepsy surgery planning: a simulation study

When planning for epilepsy surgery, multiple potential sites for resection may be identified through anatomical imaging. Magnetoencephalography (MEG) using optically pumped sensors (OP-MEG) is a non-invasive functional neuroimaging technique which could be used to help identify the epileptogenic zone from these candidate regions. Here we test the utility of a-priori information from anatomical imaging for differentiating potential lesion sites with OP-MEG. We investigate a number of scenarios: whether to use rigid or flexible sensor arrays, with or without a-priori source information and with or without source modelling errors. We simulated OP-MEG recordings for 1309 potential lesion sites identified from anatomical images in the Multi-centre Epilepsy Lesion Detection (MELD) project. To localise the simulated data, we used three source inversion schemes: unconstrained, prior source locations at centre of the candidate sites, and prior source locations within a volume around the lesion location. We found that prior knowledge of the candidate lesion zones made the inversion robust to errors in sensor gain, orientation and even location. When the reconstruction was too highly restricted and the source assumptions were inaccurate, the utility of this a-priori information was undermined. Overall, we found that constraining the reconstruction to the region including and around the participant's potential lesion sites provided the best compromise of robustness against modelling or measurement error.

18F-FDG-PET/CT for Localizing the Epileptogenic Focus in Patients with Different Types of Focal Cortical Dysplasia

Purpose

To determine the diagnostic and localization value of 18F-fluorodeoxyglucose-positron emission tomography (PET)/computed tomography (CT) in patients with focal cortical dysplasia (FCD) who underwent epilepsy surgery.

Methods

One hundred and eight patients with pathologically proven FCD who underwent surgery for refractory epilepsy were retrospectively analyzed. All patients underwent magnetic resonance imaging (MRI), 18F-FDG-PET/CT, and video electroencephalography. An MRI diagnosis of FCD was defined as MRI+. A PET/CT diagnosis of FCD was defined as PET/CT+.

Results

MRI and PET/CT detected FCD in 20.37% and 93.52% of patients, respectively. The difference was significant. Twenty-one patients were MRI+/PET+, 80 were MRI-/PET+, six were MRI-/PET-, and one was MRI+/PET-. The MRI positivity rate was lowest in patients with FCD type IIIa (5.6%, P < 0.05). Prevalence of MRI-/PET+ was highest in patients with FCD type IIIa (88.89%, P < 0.05).

Conclusion

PET/CT is superior to MRI in detecting FCD. FCD type IIIa was more likely than other types to show MRI-/PET+. This suggests that PET/CT has particular diagnostic value for FCD type IIIa patients with negative MRI findings.

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.

Identification of different MRI atrophy progression trajectories in epilepsy by subtype and stage inference

Artificial intelligence (AI)-based tools are widely employed, but their use for diagnosis and prognosis of neurological disorders is still evolving. Here we analyse a cross-sectional multicentre structural MRI dataset of 696 people with epilepsy and 118 control subjects. We use an innovative machine-learning algorithm, Subtype and Stage Inference, to develop a novel data-driven disease taxonomy, whereby epilepsy subtypes correspond to distinct patterns of spatiotemporal progression of brain atrophy.In a discovery cohort of 814 individuals, we identify two subtypes common to focal and idiopathic generalized epilepsies, characterized by progression of grey matter atrophy driven by the cortex or the basal ganglia. A third subtype, only detected in focal epilepsies, was characterized by hippocampal atrophy. We corroborate external validity via an independent cohort of 254 people and confirm that the basal ganglia subtype is associated with the most severe epilepsy.Our findings suggest fundamental processes underlying the progression of epilepsy-related brain atrophy. We deliver a novel MRI- and AI-guided epilepsy taxonomy, which could be used for individualized prognostics and targeted therapeutics.

Diagnostic Accuracy of Epilepsy-dedicated MRI with Post-processing

PURPOSE

To evaluate the diagnostic accuracy of epilepsy-dedicated 3 Tesla MRI including post-processing by correlating MRI, histopathology, and postsurgical seizure outcomes.

METHODS

3 Tesla-MRI including a magnetization-prepared two rapid acquisition gradient echo (MP2RAGE) sequence for post-processing using the morphometric analysis program MAP was acquired in 116 consecutive patients with drug-resistant focal epilepsy undergoing resection surgery. The MRI, histopathology reports and postsurgical seizure outcomes were recorded from the patient's charts.

RESULTS

The MRI and histopathology were concordant in 101 and discordant in 15 patients, 3 no hippocampal sclerosis/gliosis only lesions were missed on MRI and 1 of 28 focal cortical dysplasia (FCD) type II associated with a glial scar was considered a glial scar only on MRI. In another five patients, MRI was suggestive of FCD, the histopathology was uneventful but patients were seizure-free following surgery. The MRI and histopathology were concordant in 20 of 21 glioneuronal tumors, 6 cavernomas, and 7 glial scars. Histopathology was negative in 10 patients with temporal lobe epilepsy, 4 of them had anteroinferior meningoencephaloceles. Engel class IA outcome was reached in 71% of patients.

CONCLUSION

The proposed MRI protocol is highly accurate. No hippocampal sclerosis/gliosis only lesions are typically MRI negative. Small MRI positive FCD can be histopathologically missed, most likely due to sampling errors resulting from insufficient harvesting of tissue.

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.

Automatic Detection of Focal Cortical Dysplasia Using MRI: A Systematic Review

Focal cortical dysplasia (FCD) is a congenital brain malformation that is closely associated with epilepsy. Early and accurate diagnosis is essential for effectively treating and managing FCD. Magnetic resonance imaging (MRI)-one of the most commonly used non-invasive neuroimaging methods for evaluating the structure of the brain-is often implemented along with automatic methods to diagnose FCD. In this review, we define three categories for FCD identification based on MRI: visual, semi-automatic, and fully automatic methods. By conducting a systematic review following the PRISMA statement, we identified 65 relevant papers that have contributed to our understanding of automatic FCD identification techniques. The results of this review present a comprehensive overview of the current state-of-the-art in the field of automatic FCD identification and highlight the progress made and challenges ahead in developing reliable, efficient methods for automatic FCD diagnosis using MRI images. Future developments in this area will most likely lead to the integration of these automatic identification tools into medical image-viewing software, providing neurologists and radiologists with enhanced diagnostic capabilities. Moreover, new MRI sequences and higher-field-strength scanners will offer improved resolution and anatomical detail for precise FCD characterization. This review summarizes the current state of automatic FCD identification, thereby contributing to a deeper understanding and the advancement of FCD diagnosis and management.

Multimodal mapping of regional brain vulnerability to focal cortical dysplasia

Focal cortical dysplasia (FCD) type II is a highly epileptogenic developmental malformation and a common cause of surgically treated drug-resistant epilepsy. While clinical observations suggest frequent occurrence in the frontal lobe, mechanisms for such propensity remain unexplored. Here, we hypothesized that cortex-wide spatial associations of FCD distribution with cortical cytoarchitecture, gene expression and organizational axes may offer complementary insights into processes that predispose given cortical regions to harbour FCD. We mapped the cortex-wide MRI distribution of FCDs in 337 patients collected from 13 sites worldwide. We then determined its associations with (i) cytoarchitectural features using histological atlases by Von Economo and Koskinas and BigBrain; (ii) whole-brain gene expression and spatiotemporal dynamics from prenatal to adulthood stages using the Allen Human Brain Atlas and PsychENCODE BrainSpan; and (iii) macroscale developmental axes of cortical organization. FCD lesions were preferentially located in the prefrontal and fronto-limbic cortices typified by low neuron density, large soma and thick grey matter. Transcriptomic associations with FCD distribution uncovered a prenatal component related to neuroglial proliferation and differentiation, likely accounting for the dysplastic makeup, and a postnatal component related to synaptogenesis and circuit organization, possibly contributing to circuit-level hyperexcitability. FCD distribution showed a strong association with the anterior region of the antero-posterior axis derived from heritability analysis of interregional structural covariance of cortical thickness, but not with structural and functional hierarchical axes. Reliability of all results was confirmed through resampling techniques. Multimodal associations with cytoarchitecture, gene expression and axes of cortical organization indicate that prenatal neurogenesis and postnatal synaptogenesis may be key points of developmental vulnerability of the frontal lobe to FCD. Concordant with a causal role of atypical neuroglial proliferation and growth, our results indicate that FCD-vulnerable cortices display properties indicative of earlier termination of neurogenesis and initiation of cell growth. They also suggest a potential contribution of aberrant postnatal synaptogenesis and circuit development to FCD epileptogenicity.

An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II

Automated detection of lesions using artificial intelligence creates new standards in medical imaging. For people with epilepsy, automated detection of focal cortical dysplasias (FCDs) is widely used because subtle FCDs often escape conventional neuroradiological diagnosis. Accurate recognition of FCDs, however, is of outstanding importance for affected people, as surgical resection of the dysplastic cortex is associated with a high chance of postsurgical seizure freedom. Here, we make publicly available a dataset of 85 people affected by epilepsy due to FCD type II and 85 healthy control persons. We publish 3D-T1 and 3D-FLAIR, manually labeled regions of interest, and carefully selected clinical features. The open presurgery MRI dataset may be used to validate existing automated algorithms of FCD detection as well as to create new approaches. Most importantly, it will enable comparability of already existing approaches and support a more widespread use of automated lesion detection tools.

Multi-tensor diffusion abnormalities of gray matter in an animal model of cortical dysplasia

Focal cortical dysplasias are a type of malformations of cortical development that are a common cause of drug-resistant focal epilepsy. Surgical treatment is a viable option for some of these patients, with their outcome being highly related to complete surgical resection of lesions visible in magnetic resonance imaging (MRI). However, subtle lesions often go undetected on conventional imaging. Several methods to analyze MRI have been proposed, with the common goal of rendering subtle cortical lesions visible. However, most image-processing methods are targeted to detect the macroscopic characteristics of cortical dysplasias, which do not always correspond to the microstructural disarrangement of these cortical malformations. Quantitative analysis of diffusion-weighted MRI (dMRI) enables the inference of tissue characteristics, and novel methods provide valuable microstructural features of complex tissue, including gray matter. We investigated the ability of advanced dMRI descriptors to detect diffusion abnormalities in an animal model of cortical dysplasia. For this purpose, we induced cortical dysplasia in 18 animals that were scanned at 30 postnatal days (along with 19 control animals). We obtained multi-shell dMRI, to which we fitted single and multi-tensor representations. Quantitative dMRI parameters derived from these methods were queried using a curvilinear coordinate system to sample the cortical mantle, providing inter-subject anatomical correspondence. We found region- and layer-specific diffusion abnormalities in experimental animals. Moreover, we were able to distinguish diffusion abnormalities related to altered intra-cortical tangential fibers from those associated with radial cortical fibers. Histological examinations revealed myelo-architectural abnormalities that explain the alterations observed through dMRI. The methods for dMRI acquisition and analysis used here are available in clinical settings and our work shows their clinical relevance to detect subtle cortical dysplasias through analysis of their microstructural properties.

Review of Machine Learning and Artificial Intelligence (ML/AI) for the Pediatric Neurologist

Artificial intelligence (AI) and a popular branch of AI known as machine learning (ML) are increasingly being utilized in medicine and to inform medical research. This review provides an overview of AI and ML (AI/ML), including definitions of common terms. We discuss the history of AI and provide instances of how AI/ML can be applied to pediatric neurology. Examples include imaging in neuro-oncology, autism diagnosis, diagnosis from charts, epilepsy, cerebral palsy, and neonatal neurology. Topics such as supervised learning, unsupervised learning, and reinforcement learning are discussed.

A deep learning-based histopathology classifier for Focal Cortical Dysplasia

A light microscopy-based histopathology diagnosis of human brain specimens obtained from epilepsy surgery remains the gold standard to confirm the underlying cause of a patient’s focal epilepsy and further inform postsurgical patient management. The differential diagnosis of neocortical specimens in the realm of epilepsy surgery remains, however, challenging. Herein, we developed an open access, deep learning-based classifier to histopathologically assess whole slide microscopy images (WSI) and to automatically recognize various subtypes of Focal Cortical Dysplasia (FCD), according to the ILAE consensus classification update of 2022. We trained a convolutional neuronal network (CNN) with fully digitalized WSI of hematoxylin–eosin stainings obtained from 125 patients covering the spectrum of mild malformation of cortical development (mMCD), mMCD with oligodendroglial hyperplasia in epilepsy (MOGHE), FCD ILAE Type 1a, 2a and 2b using 414 formalin-fixed and paraffin-embedded archival tissue blocks. An additional series of 198 postmortem tissue blocks from 59 patients without neurological disorders served as control to train the CNN for homotypic frontal, temporal and occipital areas and heterotypic Brodmann areas 4 and 17, entorhinal cortex and dentate gyrus. Special stains and immunohistochemical reactions were used to comprehensively annotate the region of interest. We then programmed a novel tile extraction pipeline and graphical dashboard to visualize all areas on the WSI recognized by the CNN. Our deep learning-based classifier is able to compute 1000 × 1000 µm large tiles and recognizes 25 anatomical regions and FCD categories with an accuracy of 98.8% (F1 score = 0.82). Microscopic review of regions predicted by the network confirmed these results. This deep learning-based classifier will be made available as online web application to support the differential histopathology diagnosis in neocortical human brain specimens obtained from epilepsy surgery. It will also serve as blueprint to build a digital histopathology slide suite addressing all major brain diseases encountered in patients with surgically amenable focal epilepsy.

Interpretable surface-based detection of focal cortical dysplasias: a Multi-centre Epilepsy Lesion Detection study

One outstanding challenge for machine learning in diagnostic biomedical imaging is algorithm interpretability. A key application is the identification of subtle epileptogenic focal cortical dysplasias (FCDs) from structural MRI. FCDs are difficult to visualize on structural MRI but are often amenable to surgical resection. We aimed to develop an open-source, interpretable, surface-based machine-learning algorithm to automatically identify FCDs on heterogeneous structural MRI data from epilepsy surgery centres worldwide. The Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonized a retrospective MRI cohort of 1015 participants, 618 patients with focal FCD-related epilepsy and 397 controls, from 22 epilepsy centres worldwide. We created a neural network for FCD detection based on 33 surface-based features. The network was trained and cross-validated on 50% of the total cohort and tested on the remaining 50% as well as on 2 independent test sites. Multidimensional feature analysis and integrated gradient saliencies were used to interrogate network performance. Our pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. On a restricted 'gold-standard' subcohort of seizure-free patients with FCD type IIB who had T1 and fluid-attenuated inversion recovery MRI data, the MELD FCD surface-based algorithm had a sensitivity of 85%. Across the entire withheld test cohort the sensitivity was 59% and specificity was 54%. After including a border zone around lesions, to account for uncertainty around the borders of manually delineated lesion masks, the sensitivity was 67%. This multicentre, multinational study with open access protocols and code has developed a robust and interpretable machine-learning algorithm for automated detection of focal cortical dysplasias, giving physicians greater confidence in the identification of subtle MRI lesions in individuals with epilepsy.

Multi-Scale Deep Learning of Clinically Acquired Multi-Modal MRI Improves the Localization of Seizure Onset Zone in Children With Drug-Resistant Epilepsy

The present study investigates the effectiveness of a deep learning neural network for non-invasively localizing the seizure onset zone (SOZ) using multi-modal MRI data that are clinically acquired from children with drug-resistant epilepsy. A cortical parcellation was applied to localize the SOZ in cortical nodes of the epileptogenic hemisphere. At each node, the laminar surface analysis was followed to sample 1) the relative intensity of gray matter and white matter in multi-modal MRI and 2) the neighboring white matter connectivity using diffusion tractography edge strengths. A cross-validation was employed to train and test all layers of a multi-scale residual neural network (msResNet) that can classify SOZ node in an end-to-end fashion. A prediction probability of a given node belonging to the SOZ class was proposed as a non-invasive MRI marker of seizure onset likelihood. In an independent validation cohort, the proposed MRI marker provided a very large effect size of Cohen's d = 1.21 between SOZ and non-SOZ, and classified SOZ with a balanced accuracy of 0.75 in lesional and 0.67 in non-lesional MRI groups. The subsequent multi-variate logistic regression found the incorporation of the proposed MRI marker into interictal intracranial EEG (iEEG) markers further improves the differentiation between the epileptogenic focus (defined as SOZ resected during surgery) and non-epileptogenic sites (i.e., non-SOZ sites preserved during surgery) up to 15 % in non-lesional MRI group, suggesting that the proposed MRI marker could improve the localization of epileptogenic foci for successful pediatric epilepsy surgery.

Computerized application for epilepsy in China: Does the era of artificial intelligence comes?

Epilepsy, one of the most common neurological diseases in China, is notorious for its spontaneous, unprovoked and recurrent seizures. The etiology of epilepsy varies among individual patients, including congenital gene mutation, traumatic injury, infections, etc. This heterogeneity partly hampered the accurate diagnosis and choice of appropriate treatments. Encouragingly, great achievements have been achieved in computational science, making it become a key player in medical fields gradually and bringing new hope for rapid and accurate diagnosis as well as targeted therapies in epilepsy. Here, we historically review the advances of computerized applications in epilepsy-especially those tremendous findings achieved in China-for different purposes including seizure prediction, localization of epileptogenic zone, post-surgical prognosis, etc. Special attentions are paid to the great progress based on artificial intelligence (AI), which is more "sensitive", "smart" and "in-depth" than human capacities. At last, we give a comprehensive discussion about the disadvantages and limitations of current computerized applications for epilepsy and propose some future directions as further stepping stones to embrace "the era of AI" in epilepsy.

Sage Against the Machine: Promise and Challenge of Artificial Intelligence in Epilepsy

Multicenter Validation of a Deep Learning Detection Algorithm for Focal Cortical Dysplasia

Gill RS, Lee HM, Caldairou B, et al. Neurology. 2021 Oct 19;97(16):e1571-e1582. doi:10.1212/WNL.0000000000012698. Epub 2021 Sep 14. PMID: 34521691; PMCID: PMC8548962.

Background and Objective:

To test the hypothesis that a multicenter-validated computer deep learning algorithm detects MRI-negative focal cortical dysplasia (FCD).

Methods:

We used clinically acquired 3-dimensional (3D) T1-weighted and 3D fluid-attenuated inversion recovery MRI of 148 patients (median age 23 years [range 2-55 years]; 47% female) with histologically verified FCD at 9 centers to train a deep convolutional neural network (CNN) classifier. Images were initially deemed MRI-negative in 51% of patients, in whom intracranial EEG determined the focus. For risk stratification, the CNN incorporated bayesian uncertainty estimation as a measure of confidence. To evaluate performance, detection maps were compared to expert FCD manual labels. Sensitivity was tested in an independent cohort of 23 cases with FCD (13 ± 10 years). Applying the algorithm to 42 healthy controls and 89 controls with temporal lobe epilepsy disease tested specificity.

Results:

Overall sensitivity was 93% (137 of 148 FCD detected) using a leave-one-site-out cross-validation, with an average of 6 false positives per patient. Sensitivity in MRI-negative FCD was 85%. In 73% of patients, the FCD was among the clusters with the highest confidence; in half, it ranked the highest. Sensitivity in the independent cohort was 83% (19 of 23; average of 5 false positives per patient). Specificity was 89% in healthy and disease controls.

Discussion:

This first multicenter-validated deep learning detection algorithm yields the highest sensitivity to date in MRI-negative FCD. By pairing predictions with risk stratification, this classifier may assist clinicians in adjusting hypotheses relative to other tests, increasing diagnostic confidence. Moreover, generalizability across age and MRI hardware makes this approach ideal for presurgical evaluation of MRI-negative epilepsy. Classification of evidence: This study provides Class III evidence that deep learning on multimodal MRI accurately identifies FCD in patients with epilepsy initially diagnosed as MRI negative.

Focal cortical dysplasia links to sleep-related epilepsy in symptomatic focal epilepsy

OBJECTIVE

In sleep-related epilepsy (SRE), epileptic seizures predominantly occur during sleep, but the clinical characteristics of SRE remain elusive. We aimed to identify the clinical features associated with the occurrence of SRE in a large cohort of symptomatic focal epilepsy.

METHODS

We retrospectively included patients with four etiologies, including focal cortical dysplasia (FCD), low-grade tumors (LGT), temporal lobe epilepsy with hippocampal sclerosis (TLE-HS), and encephalomalacia. SRE was defined as more than 70% of seizures occurring during sleep according to the seizure diary. The correlation between SRE and other clinical variables, such as etiology of epilepsy, pharmacoresistance, seizure frequency, history of bilateral tonic-clonic seizures, and seizure localization was analyzed.

RESULTS

A total of 376 patients were included. Among them 95 (25.3%) were classified as SRE and the other 281(74.7%) as non-SRE. The incidence of SRE was 53.5% in the FCD group, which was significantly higher than the other three groups (LGT: 19.0%; TLE-HS: 9.9%; encephalomalacia: 16.7%; P < 0.001). The etiology of FCD (p < 0.001) was significantly associated with SRE (OR: 9.71, 95% CI: 3.35-28.14) as an independent risk factor. In addition, small lesion size (p = 0.009) of FCD further increased the risk of SRE (OR: 3.18, 95% CI: 1.33-7.62) in the FCD group.

SIGNIFICANCE

Our data highlight that FCD markedly increased the risk of sleep-related epilepsy independently of seizure localization. A small lesion of FCD further increased the risk of sleep-related epilepsy by 2.18 times in the FCD group.

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.

Fully automated detection of focal cortical dysplasia: Comparison of MPRAGE and MP2RAGE sequences

OBJECTIVE

The detection of focal cortical dysplasia (FCD) in magnetic resonance imaging is challenging. Voxel-based morphometric analysis and automated FCD detection using an artificial neural network (ANN) integrated into the Morphometric Analysis Program (MAP18) have been shown to facilitate FCD detection. This study aimed to evaluate whether the detection of FCD can be further improved by feeding this approach with magnetization prepared two rapid acquisition gradient echoes (MP2RAGE) instead of magnetization-prepared rapid acquisition gradient echo (MPRAGE) datasets.

METHODS

MPRAGE and MP2RAGE datasets were acquired in a consecutive sample of 32 patients with FCD and postprocessed using MAP18. Visual analysis and, if available, histopathology served as the gold standard for assessing the sensitivity and specificity of FCD detection. Out-of-sample specificity was evaluated in a cohort of 32 healthy controls.

RESULTS

The sensitivity and specificity of FCD detection were 82.4% and 62.5% for the MPRAGE and 97.1% and 34.4% for the MP2RAGE sequences, respectively. Median volumes of true-positive voxel clusters were .16 ml for the MPRAGE and .52 ml for the MP2RAGE sequences compared to .08- and .04-ml volumes of false-positive clusters. With regard to cluster volumes, FCD detection was substantially improved for the MP2RAGE data when the estimated optimal threshold of .23 ml was applied (sensitivity = 72.9%, specificity = 83.0%). In contrast, the estimated optimal threshold of .37 ml for the MPRAGE data did not improve FCD lesion detection (sensitivity = 42.9%, specificity = 79.5%).

SIGNIFICANCE

In this study, the sensitivity of FCD detection by morphometric analysis and an ANN integrated into MAP18 was higher for MP2RAGE than for MPRAGE sequences. Additional usage of cluster volume information helped to discriminate between true- and false-positive MP2RAGE results.