Computational analysis in epilepsy neuroimaging: A survey of features and methods

A radiomics nomogram based on multiparametric MRI for diagnosing focal cortical dysplasia and initially identifying laterality

BACKGROUND

Focal cortical dysplasia (FCD) is the most common epileptogenic developmental malformation. The diagnosis of FCD is challenging. We generated a radiomics nomogram based on multiparametric magnetic resonance imaging (MRI) to diagnose FCD and identify laterality early.

METHODS

Forty-three patients treated between July 2017 and May 2022 with histopathologically confirmed FCD were retrospectively enrolled. The contralateral unaffected hemispheres were included as the control group. Therefore, 86 ROIs were finally included. Using January 2021 as the time cutoff, those admitted after January 2021 were included in the hold-out set (n = 20). The remaining patients were separated randomly (8:2 ratio) into training (n = 55) and validation (n = 11) sets. All preoperative and postoperative MR images, including T1-weighted (T1w), T2-weighted (T2w), fluid-attenuated inversion recovery (FLAIR), and combined (T1w + T2w + FLAIR) images, were included. The least absolute shrinkage and selection operator (LASSO) was used to select features. Multivariable logistic regression analysis was used to develop the diagnosis model. The performance of the radiomic nomogram was evaluated with an area under the curve (AUC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration and clinical utility.

RESULTS

The model-based radiomics features that were selected from combined sequences (T1w + T2w + FLAIR) had the highest performances in all models and showed better diagnostic performance than inexperienced radiologists in the training (AUCs: 0.847 VS. 0.664, p = 0.008), validation (AUC: 0.857 VS. 0.521, p = 0.155), and hold-out sets (AUCs: 0.828 VS. 0.571, p = 0.080). The positive values of NRI (0.402, 0.607, 0.424) and IDI (0.158, 0.264, 0.264) in the three sets indicated that the diagnostic performance of Model-Combined improved significantly. The radiomics nomogram fit well in calibration curves (p > 0.05), and decision curve analysis further confirmed the clinical usefulness of the nomogram. Additionally, the contrast (the radiomics feature) of the FCD lesions not only played a crucial role in the classifier but also had a significant correlation (r = -0.319, p < 0.05) with the duration of FCD.

CONCLUSION

The radiomics nomogram generated by logistic regression model-based multiparametric MRI represents an important advancement in FCD diagnosis and treatment.

AI in ECG: Validating an ambulatory semiology labeller and predictor

OBJECTIVES

Early prediction of epileptic seizures can help reduce morbidity and mortality. In this work, we explore using electrocardiographic (ECG) signal as input to a seizure prediction system and note that the performance can be improved by using selected signal processing techniques.

METHODS

We used frequency domain analysis with a deep neural network backend for all our experiments in this work. We further analysed the effect of the proposed system for different seizure semiologies and prediction horizons. We explored refining the signal using signal processing to enhance the system's performance.

RESULTS

Our final system using the Temple University Hospital's Seizure (TUHSZ) corpus gave an overall prediction accuracy of 84.02 %, sensitivity of 87.59 %, specificity of 81.9 %, and an area under the receiver operating characteristic curve (AUROC) of 0.9112. Notably, these results surpassed the state-of-the-art outcomes reported using the TUHSZ database; all findings are statistically significant. We also validated our study using the Siena scalp EEG database. Using the frequency domain data, our baseline system gave a performance of 75.17 %, 79.17 %, 70.04 % and 0.82 for prediction accuracy, sensitivity, specificity and AUROC, respectively. After selecting the optimal frequency band of 0.8-15 Hz, we obtained a performance of 80.49 %, 89.51 %, 75.23 % and 0.89 for prediction accuracy, sensitivity, specificity and AUROC, respectively which is an improvement of 5.32 %, 10.34 %, 5.19 % and 0.08 for prediction accuracy, sensitivity, specificity and AUROC, respectively.

CONCLUSIONS

The seizure information in ECG is concentrated in a narrow frequency band. Identifying and selecting that band can help improve the performance of seizure detection and prediction.

SIGNIFICANCE

EEG is susceptible to artefacts and is not preferred in a low-cost ambulatory device. ECG can be used in wearable devices (like chest bands) and is feasible for developing a low-cost ambulatory device for seizure prediction. Early seizure prediction can provide patients and clinicians with the required alert to take necessary precautions and prevent a fatality, significantly improving the patient's quality of life.

The use of automated and AI-driven algorithms for the detection of hippocampal sclerosis and focal cortical dysplasia

In drug-resistant epilepsy, magnetic resonance imaging (MRI) plays a central role in detecting lesions as it offers unmatched spatial resolution and whole-brain coverage. In addition, the last decade has witnessed continued developments in MRI-based computer-aided machine-learning techniques for improved diagnosis and prognosis. In this review, we focus on automated algorithms for the detection of hippocampal sclerosis and focal cortical dysplasia, particularly in cases deemed as MRI negative, with an emphasis on studies with histologically validated data. In addition, we discuss imaging-derived prognostic markers, including response to anti-seizure medication, post-surgical seizure outcome, and cognitive reserves. We also highlight the advantages and limitations of these approaches and discuss future directions toward person-centered care.

Evaluation of MRI post-processing methods combined with PET in detecting focal cortical dysplasia lesions for patients with MRI-negative epilepsy

OBJECTIVE

Accurate detection of focal cortical dysplasia (FCD) through magnetic resonance imaging (MRI) plays a pivotal role in the preoperative assessment of epilepsy. The integration of multimodal imaging has demonstrated substantial value in both diagnosing FCD and devising effective surgical strategies. This study aimed to enhance MRI post-processing by incorporating positron emission tomography (PET) analysis. We sought to compare the diagnostic efficacy of diverse image post-processing methodologies in patients presenting MRI-negative FCD.

METHODS

In this retrospective investigation, we assembled a cohort of patients with negative preoperative MRI results. T1-weighted volumetric sequences were subjected to morphometric analysis program (MAP) and composite parametric map (CPM) post-processing techniques. We independently co-registered images derived from various methods with PET scans. The alignment was subsequently evaluated, and its correlation was correlated with postoperative seizure outcomes.

RESULTS

A total of 41 patients were enrolled in the study. In the PET-MAP(p = 0.0189) and PET-CPM(p = 0.00041) groups, compared with the non-overlap group, the overlap group significantly associated with better postoperative outcomes. In PET(p = 0.234), CPM(p = 0.686) and MAP(p = 0.672), there is no statistical significance between overlap and seizure-free outcomes. The sensitivity of using the CPM alone outperformed the MAP (0.65 vs 0.46). The use of PET-CPM demonstrated superior sensitivity (0.96), positive predictive value (0.83), and negative predictive value (0.91), whereas the MAP displayed superior specificity (0.71).

CONCLUSIONS

Our findings suggested a superiority in sensitivity of CPM in detecting potential FCD lesions compared to MAP, especially when it is used in combination with PET for diagnosis of MRI-negative epilepsy patients. Moreover, we confirmed the superiority of synergizing metabolic imaging (PET) with quantitative maps derived from structural imaging (MAP or CPM) to enhance the identification of subtle epileptogenic zones (EZs). This study serves to illuminate the potential of integrated multimodal techniques in advancing our capability to pinpoint elusive pathological features in epilepsy cases.

Charting the Progress of Epilepsy Classification: Navigating a Shifting Landscape

Epilepsy, a neurological disorder characterized by recurrent seizures, has witnessed a remarkable transformation in its classification paradigm, driven by advances in clinical understanding, neuroimaging, and molecular genetics. This narrative review navigates the dynamic landscape of epilepsy classification, offering insights into recent developments, challenges, and the promising horizon. Historically, epilepsy classification relied heavily on clinical observations, categorizing seizures based on their phenomenology and presumed etiology. However, the field has profoundly shifted from a symptom-based approach to a more refined, multidimensional system. One pivotal aspect of this evolution is the integration of neuroimaging techniques, particularly magnetic resonance imaging (MRI) and functional imaging modalities. These tools have unveiled the intricate neural networks implicated in epilepsy, facilitating the identification of distinct brain abnormalities and the categorization of epilepsy subtypes based on structural and functional findings. Furthermore, the role of genetics has become increasingly prominent in epilepsy classification. Genetic discoveries have not only unraveled the molecular underpinnings of various epileptic syndromes but have also provided valuable diagnostic and prognostic insights. This narrative review delves into the expanding realm of genetic testing and its impact on tailoring treatment strategies to individual patients. As the classification landscape evolves, there are accompanying challenges. The narrative review underscores the transformative potential of artificial intelligence and machine learning in epilepsy classification. These technologies hold promise in automating the analysis of complex neuroimaging and genetic data, offering enhanced accuracy and efficiency in epilepsy diagnosis and classification. In conclusion, navigating the shifting landscape of epilepsy classification is a journey marked by progress, complexity, and the prospect of improved patient care. We are charting a course toward more precise diagnoses and tailored treatments by embracing advanced neuroimaging, genetics, and innovative technologies. As the field continues to evolve, collaborative efforts and a holistic understanding of epilepsy's diverse manifestations will be instrumental in harnessing the full potential of this dynamic landscape.

Remote effects of temporal lobe epilepsy surgery: Long-term morphological changes after surgical resection

OBJECTIVE

Epilepsy surgery is an effective treatment for drug-resistant patients. However, how different surgical approaches affect long-term brain structure remains poorly characterized. Here, we present a semiautomated method for quantifying structural changes after epilepsy surgery and compare the remote structural effects of two approaches, anterior temporal lobectomy (ATL), and selective amygdalohippocampectomy (SAH).

METHODS

We studied 36 temporal lobe epilepsy patients who underwent resective surgery (ATL = 22, SAH = 14). All patients received same-scanner MR imaging preoperatively and postoperatively (mean 2 years). To analyze postoperative structural changes, we segmented the resection zone and modified the Advanced Normalization Tools (ANTs) longitudinal cortical pipeline to account for resections. We compared global and regional annualized cortical thinning between surgical treatments.

RESULTS

Across procedures, there was significant cortical thinning in the ipsilateral insula, fusiform, pericalcarine, and several temporal lobe regions outside the resection zone as well as the contralateral hippocampus. Additionally, increased postoperative cortical thickness was seen in the supramarginal gyrus. Patients treated with ATL exhibited greater annualized cortical thinning compared with SAH cases (ATL: -0.08 ± 0.11 mm per year, SAH: -0.01 ± 0.02 mm per year, t = 2.99, P = 0.006). There were focal postoperative differences between the two treatment groups in the ipsilateral insula (P = 0.039, corrected). Annualized cortical thinning rates correlated with preoperative cortical thickness (r = 0.60, P < 0.001) and had weaker associations with age at surgery (r = -0.33, P = 0.051) and disease duration (r = -0.42, P = 0.058).

SIGNIFICANCE

Our evidence suggests that selective procedures are associated with less cortical thinning and that earlier surgical intervention may reduce long-term impacts on brain structure.

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.

Preoperative Detection of Subtle Focal Cortical Dysplasia in Children by Combined Arterial Spin Labeling, Voxel-Based Morphometry, Electroencephalography-Synchronized Functional MRI, Resting-State Regional Homogeneity, and 18F-fluorodeoxyglucose Positron Emission Tomography

BACKGROUND

Focal cortical dysplasia (FCD) causes drug-resistant epilepsy in children that can be cured surgically, but the lesions are often unseen by imaging.

OBJECTIVE

To assess the efficiency of arterial spin labeling (ASL), voxel-based-morphometry (VBM), fMRI electroencephalography (EEG), resting-state regional homogeneity (ReHo), 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET), and their combination in detecting pediatric FCD.

METHODS

We prospectively included 10 children for whom FCD was localized by surgical resection. They underwent 3T MR acquisition with concurrent EEG, including ASL perfusion, resting-state BOLD fMRI (allowing the processing of EEG-fMRI and ReHo), 3D T1-weighted images processed using VBM, and FDG PET-CT coregistered with MRI. Detection was assessed visually and by comparison with healthy controls (for ASL and VBM).

RESULTS

Eight children had normal MRI, and 2 had asymmetric sulci. Using MR techniques, FCD was accurately detected by ASL for 6/10, VBM for 5/10, EEG-fMRI for 5/8 (excluding 2 with uninterpretable results), and ReHo for 4/10 patients. The combination of ASL, VBM, and ReHo allowed correct FCD detection for 9/10 patients. FDG PET alone showed higher accuracy than the other techniques (7/9), and its combination with VBM allowed correct FCD detection for 8/9 patients. The detection efficiency was better for patients with asymmetric sulci (2/2 for all techniques), but advanced MR techniques and PET were useful for MR-negative patients (7/8).

CONCLUSION

A combination of multiple imaging techniques, including PET, ASL, and VBM analysis of T1-weighted images, is effective in detecting subtle FCD in children.

Surgery for pediatric drug resistant epilepsy: a narrative review of its history, surgical implications, and treatment strategies

BACKGROUND AND OBJECTIVE

Drug-resistant epilepsy (DRE), also known as medically refractory epilepsy, is a disorder of high prevalence and negatively impacts a patients quality of life, neurodevelopment, and life expectancy. Pediatric epilepsy surgery has been conducted since the late 1800s, and randomized controlled trials have demonstrated the marked effectiveness of surgery on seizure reduction and the potential for cure. Despite the strong evidence for pediatric epilepsy surgery, there is also strong evidence describing its underutilization. The objective of this narrative review is to describe the history, strength, and limitations in the evidence of surgery for pediatric drug resistant epilepsy.

METHODS

This narrative review was conducted utilizing standard search engines to include the relevant articles on the topic of surgery for drug resistant epilepsy in children, with main keywords including surgery in pediatric epilepsy and drug-refractory epilepsy.

KEY CONTENT AND FINDINGS

The first components describe the historical perspective of pediatric epilepsy surgery and the evidence that highlight the strengths and limitations of epilepsy surgery. We then highlight the importance of presurgical referral and evaluation, followed by a section detailing the surgical options for children with DRE. Lastly, we provide a perspective on the future of pediatric epilepsy surgery.

CONCLUSIONS

Evidence supports the role for surgery in pediatric medically refractory epilepsy in seizure frequency reduction, improved curative rates, and improvements in neurodevelopment and quality of life.

Multimodal combination of neuroimaging methods for localizing the epileptogenic zone in MR-negative epilepsy

The objective was to determine the optimal combination of multimodal imaging methods (IMs) for localizing the epileptogenic zone (EZ) in patients with MR-negative drug-resistant epilepsy. Data from 25 patients with MR-negative focal epilepsy (age 30 ± 10 years, 16M/9F) who underwent surgical resection of the EZ and from 110 healthy controls (age 31 ± 9 years; 56M/54F) were used to evaluate IMs based on 3T MRI, FDG-PET, HD-EEG, and SPECT. Patients with successful outcomes and/or positive histological findings were evaluated. From 38 IMs calculated per patient, 13 methods were selected by evaluating the mutual similarity of the methods and the accuracy of the EZ localization. The best results in postsurgical patients for EZ localization were found for ictal/ interictal SPECT (SISCOM), FDG-PET, arterial spin labeling (ASL), functional regional homogeneity (ReHo), gray matter volume (GMV), cortical thickness, HD electrical source imaging (ESI-HD), amplitude of low-frequency fluctuation (ALFF), diffusion tensor imaging, and kurtosis imaging. Combining IMs provides the method with the most accurate EZ identification in MR-negative epilepsy. The PET, SISCOM, and selected MRI-post-processing techniques are useful for EZ localization for surgical tailoring.

The changing landscape in epilepsy imaging: Unmasking subtle and unique entities

Dramatic changes have occurred recently in the field of epilepsy, including a fundamental shift in the etiology of epileptogenic substrates found at surgery. Hippocampal sclerosis is no longer the most common etiology found at epilepsy surgery and this decrease has been associated with an increase in the incidence of focal cortical dysplasia and encephaloceles. Significant advances have been made in molecular biology and genetics underlying the basis of malformations of cortical development, and our ability to detect epileptogenic abnormalities with MR imaging has markedly improved. This article begins with a discussion of these trends and reviews imaging techniques essential for detecting of subtle epilepsy findings. Representative examples of subtle imaging findings are presented, which are often overlooked but should not be missed. These include temporal lobe encephaloceles, malformations of cortical development (and especially focal cortical dysplasia), hippocampal sclerosis, hippocampal malformation (also known as HIMAL), ulegyria, autoimmune encephalitis, and Rasmussen's encephalitis. Recent findings on the pathophysiology and genetic underpinnings of several causes of localization-related epilepsy are incorporated. For instance, it has been recently found that focal cortical dysplasia IIb, tuberous sclerosis, hemimegalencephaly, and gangliogliomas are all the result of mutations of the mTOR pathway for cell growth.

The Role of MRI in the Treatment of Drug-Resistant Focal Epilepsy

BACKGROUND

Epilepsy is a prevalent chronic condition affecting about 50 million people worldwide. A third of patients with focal epilepsy suffer from seizures unresponsive to medication. Uncontrolled seizures damage the brain, are associated with cognitive decline, and have negative impact on well-being. For these patients, the surgical resection of the brain region that gives rise to seizures is the most effective treatment.

SUMMARY

Magnetic resonance imaging (MRI) plays a central role in detecting epileptogenic brain lesions. In this review, we critically discuss advances in neuroimaging acquisition, analytical post-acquisition techniques, and machine leaning methods for the detection of epileptogenic lesions, prediction of clinical outcomes, and identification of disease subtypes.

KEY MESSAGE

MRI is a mandatory investigation for diagnosis and treatment of epilepsy, particularly when surgery is being considered. Continuous progress in imaging techniques, combined with machine learning, will continue to push the boundaries of lesion visibility and provide increasingly precise predictors of clinical outcomes. Current efforts aiming at strengthening the competences of epileptologists in neuroimaging will ultimately reduce the need for invasive diagnostics.

Aerobic glycolysis imaging of epileptic foci during the inter-ictal period

BACKGROUND

In drug-resistant epilepsy, surgical resection of the epileptic focus can end seizures. However, success is dependent on the ability to identify foci locations and, unfortunately, current methods like electrophysiology and positron emission tomography can give contradictory results. During seizures, glucose is metabolized at epileptic foci through aerobic glycolysis, which can be imaged through the oxygen-glucose index (OGI) biomarker. However, inter-ictal (between seizures) OGI changes have not been studied, which has limited its application.

METHODS

18 healthy controls and 24 inter-ictal, temporal lobe epilepsy patients underwent simultaneous positron emission tomography (PET) and magnetic resonance imaging (MRI) scans. We used [18F]fluorodeoxyglucose-PET (FDG-PET) to detect cerebral glucose metabolism, and calibrated functional MRI to acquire relative oxygen consumption. With these data, we calculated relative OGI maps.

FINDINGS

While bilaterally symmetrical in healthy controls, we observed, in patients during the inter-ictal period, higher OGI ipsilateral to the epileptic focus than contralateral. While traditional FDG-PET results and temporal lobe OGI results usually both agreed with invasive electrophysiology, in cases where FDG-PET disagreed with electrophysiology, temporal lobe OGI agreed with electrophysiology, and vice-versa.

INTERPRETATION

As either our novel epilepsy biomarker or traditional approaches located foci in every case, our work provides promising insights into metabolic changes in epilepsy. Our method allows single-session OGI measurement which can be useful in other diseases.

FUNDING

This work was supported by ShanghaiTech University, the Shanghai Municipal Government, the National Natural Science Foundation of China Grant (No. 81950410637) and Shanghai Municipal Key Clinical Specialty (No. shslczdzk03403). F. H. and P. H. were supported by USA National Institute of Health grants (R01 NS-100106, R01 MH-067528).Z. W. was supported by the Key-Area Research and Development Program of Guangdong Province (2019B030335001), National Natural Science Foundation of China (No. 82151303), and National Key R&D Program of China (No. 2021ZD0204002).

MRI of focal cortical dysplasia

Focal cortical dysplasia (FCD) are histopathologically categorized in ILAE type I to III. Mild malformations of cortical development (mMCD) including those with oligodendroglial hyperplasia (MOGHE) are to be integrated into this classification yet. Only FCD type II have distinctive MRI and molecular genetics alterations so far. Subtle FCD including FCD type II located in the depth of a sulcus are often overlooked requiring the use of dedicated sequences (MP2RAGE, FLAWS, EDGE) and/or voxel (VBM)- or surface-based (SBM) postprocessing. The added value of 7 Tesla MRI has to be proven yet.

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.

Machine learning applications on neuroimaging for diagnosis and prognosis of epilepsy: A review

Machine learning is playing an increasingly important role in medical image analysis, spawning new advances in the clinical application of neuroimaging. There have been some reviews on machine learning and epilepsy before, and they mainly focused on electrophysiological signals such as electroencephalography (EEG) and stereo electroencephalography (SEEG), while neglecting the potential of neuroimaging in epilepsy research. Neuroimaging has its important advantages in confirming the range of the epileptic region, which is essential in presurgical evaluation and assessment after surgery. However, it is difficult for EEG to locate the accurate epilepsy lesion region in the brain. In this review, we emphasize the interaction between neuroimaging and machine learning in the context of epilepsy diagnosis and prognosis. We start with an overview of epilepsy and typical neuroimaging modalities used in epilepsy clinics, MRI, DWI, fMRI, and PET. Then, we elaborate two approaches in applying machine learning methods to neuroimaging data: (i) the conventional machine learning approach combining manual feature engineering and classifiers, (ii) the deep learning approach, such as the convolutional neural networks and autoencoders. Subsequently, the application of machine learning on epilepsy neuroimaging, such as segmentation, localization, and lateralization tasks, as well as tasks directly related to diagnosis and prognosis are looked into in detail. Finally, we discuss the current achievements, challenges, and potential future directions in this field, hoping to pave the way for computer-aided diagnosis and prognosis of epilepsy.

Seizure Outcome After Surgery for MRI-Diagnosed Focal Cortical Dysplasia: A Systematic Review and Meta-analysis

OBJECTIVE

Focal cortical dysplasia (FCD) has been associated with poorer post-surgical seizure outcomes compared to other pathologies. FCD surgical series have been assembled on the basis of a histological diagnosis, including patients with abnormal as well as normal pre-operative MRI. However, in clinical workflow, patient selection for surgery is based on pre-operative findings, including MRI. We performed a systematic review and meta-analysis of the literature to determine the rate and predictors of favorable seizure outcome after surgery for MRI-detected FCD.

METHODS

We devised our study protocol in accordance with PRISMA guidelines and registered the protocol with PROSPERO. We searched MEDLINE, EMBASE, and Web of Science for studies of patients followed for ≥12 months after resective surgery for drug-resistant epilepsy with MRI-detected FCD. Random-effects meta-analysis was used to calculate the proportion of patients attaining a favorable outcome, defined as Engel Class I, ILAE Classes 1-2, or "seizure-free" status. Meta-regression was performed to investigate sources of heterogeneity.

RESULTS

Our search identified 3,745 references. Of these, 35 studies (total of 1,353 patients) were included. Most studies (89%) followed patients for ≥24 months post-surgery. The overall post-surgical favorable outcome rate was 70% (95% CI: 64-75). There was high inter-study heterogeneity. Favorable outcome was associated with complete resection of the FCD lesion [risk ratio, RR=2.42 (95% CI: 1.55-3.76), p<0.001] and location of the FCD lesion in the temporal lobe [RR=1.38 (95% CI: 1.07-1.79), p=0013], but not lesion extent, intracranial EEG use, or FCD histological type. The number of FCD histological types included in the same study accounted for 7.6% of the observed heterogeneity.

CONCLUSIONS

70% of patients with drug-resistant epilepsy and MRI features of FCD attain a favorable seizure outcome following resective surgery. Our findings can be incorporated in routine pre-operative counselling and reinforce the importance of resecting completely the MRI-detected FCD where this is safe and feasible.

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

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.

Grey and white matter microstructure changes in epilepsy patients with vagus nerve stimulators

OBJECTIVES

Vagus nerve stimulation (VNS) has been widely used as an effective treatment for patients with drug-resistant epilepsy (DRE). However, little is known about grey matter (GM) and white matter (WM) microstructure changes caused by VNS. This study aimed to detect consistent GM and WM alterations in epilepsy patients with vagus nerve stimulators.

METHODS

The diffusion tensor imaging data was acquired from 15 patients who underwent VNS implantation. The voxel-based morphometry (VBM) and tract-based spatial statistics (TBSS) were used to detect group differences in GM and WM microstructure and explore their correlation with postoperative seizure reduction.

RESULTS

After 3 months of stimulation, GM density reduced in right cerebellum, left superior temporal gyrus, right inferior temporal gyrus and left thalamus, and increased in left cerebellum, left inferior parietal lobule, left middle occipital gyrus and left gyrus rectus. No significant volume changes had been found in 14 subcortical nuclei. The fractional anisotropy (FA) values reduced in left superior longitudinal fasciculus and left corticospinal tract, and increased in bilateral cingulum and body of corpus callosum. The mean diffusivity (MD) values reduced in right retrolenticular part of internal capsule, right posterior corona radiata and right superior longitudinal fasciculus. The seizure reduction had positive correlation trends with the volume reduction in left nucleus accumbens and right amygdala, and MD reduction in right medial lemniscus and right posterior corona radiata.

CONCLUSIONS

The results showed that VNS could cause changes of GM density, WM FA and MD values in epilepsy patients. The volume and MD reduction in some subcortical structures might participate in the seizure frequency reduction of VNS.

[Imaging in the presurgical evaluation of epilepsy]

Während zwei Drittel der PatientInnen mit Epilepsie durch Medikamente anfallsfrei werden, ist die Erkrankung bei 30 % pharmakoresistent. Bei pharmakoresistenter fokaler Epilepsie bietet die Epilepsiechirurgie eine etwa 65 %ige Chance auf Anfallsfreiheit. Vorab muss der Anfallsfokus exakt eingegrenzt werden, wofür bildgebende Methoden unverzichtbar sind. In den letzten Jahren hat sich in der Prächirurgie der Anteil von PatientInnen mit unauffälliger konventioneller Magnetresonanztomographie (MRT) erhöht. Allerdings konnte die Sensitivität der MRT durch spezielle Aufnahmesequenzen und Techniken der Postprozessierung gesteigert werden. Die Quellenlokalisation des Signals von Elektro- und Magnetenzephalographie (EEG und MEG) verortet den Ursprung iktaler und interiktaler epileptischer Aktivität im Gehirn. Nuklearmedizinische Untersuchungen wie die interiktale Positronen-Emissions-Tomographie (PET) und die iktale Einzelphotonen-Emissionscomputertomographie (SPECT) detektieren chronische oder akute anfallsbezogene Veränderungen des Hirnmetabolismus und können auch bei nichtlokalisierendem MRT auf den epileptogenen Fokus hinweisen. Alle Befunde zusammengenommen werden zur Planung eventueller invasiver EEG-Ableitungen und letztlich der chirurgischen Operation eingesetzt. Konkordante Befunde sind mit besseren chirurgischen Ergebnissen assoziiert und zeigen auch im Langzeitverlauf signifikant höhere Anfallsfreiheitsraten.

Alterations of structural connectivity and structural co-variance network in focal cortical dysplasia

Background

The aim of this study was to investigate alterations in structural connectivity and structural co-variance network in patients with focal cortical dysplasia (FCD).

Methods

We enrolled 37 patients with FCD and 35 healthy controls. All subjects underwent brain MRI with the same scanner and with the same protocol, which included diffusion tensor imaging (DTI) and T1-weighted imaging. We analyzed the structural connectivity based on DTI, and structural co-variance network based on the structural volume with T1-weighted imaging. We created a connectivity matrix and obtained network measures from the matrix using the graph theory. We tested the difference in network measure between patients with FCD and healthy controls.

Results

In the structural connectivity analysis, we found that the local efficiency in patients with FCD was significantly lower than in healthy controls (2.390 vs. 2.578, p = 0.031). Structural co-variance network analysis revealed that the mean clustering coefficient, global efficiency, local efficiency, and transitivity were significantly decreased in patients with FCD compared to those in healthy controls (0.527 vs. 0.635, p = 0.036; 0.545 vs. 0.648, p = 0.026; 2.699 vs. 3.801, p = 0.019; 0.791 vs. 0.954, p = 0.026, respectively).

Conclusions

We demonstrate that there are significant alterations in structural connectivity, based on DTI, and structural co-variance network, based on the structural volume, in patients with FCD compared to healthy controls. These findings suggest that focal lesions with FCD could affect the whole-brain network and that FCD is a network disease.

Brain injuries can set up an epileptogenic neuronal network

Development of epilepsy or epileptogenesis promotes recurrent seizures. As of today, there are no effective prophylactic therapies to prevent the onset of epilepsy. Contributing to this deficiency of preventive therapy is the lack of clarity in fundamental neurobiological mechanisms underlying epileptogenesis and lack of reliable biomarkers to identify patients at risk for developing epilepsy. This limits the development of prophylactic therapies in epilepsy. Here, neural network dysfunctions reflected by oscillopathies and microepileptiform activities, including neuronal hyperexcitability and hypersynchrony, drawn from both clinical and experimental epilepsy models, have been reviewed. This review suggests that epileptogenesis reflects a progressive and dynamic dysfunction of specific neuronal networks which recruit further interconnected groups of neurons, with this resultant pathological network mediating seizure occurrence, recurrence, and progression. In the future, combining spatial and temporal resolution of neuronal non-invasive recordings from patients at risk of developing epilepsy, together with analytics and computational tools, may contribute to determining whether the brain is undergoing epileptogenesis in asymptomatic patients following brain injury.

Volumetric glutamate imaging (GluCEST) using 7T MRI can lateralize nonlesional temporal lobe epilepsy: A preliminary study

INTRODUCTION

Drug-resistant epilepsy patients show worse outcomes after resection when standard neuroimaging is nonlesional, which occurs in one-third of patients. In prior work, we employed 2-D glutamate imaging, Glutamate Chemical Exchange Saturation Transfer (GluCEST), to lateralize seizure onset in nonlesional temporal lobe epilepsy (TLE) based on increased ipsilateral GluCEST signal in the total hippocampus and hippocampal head. We present a significant advancement to single-slice GluCEST imaging, allowing for three-dimensional analysis of brain glutamate networks.

METHODS

The study population consisted of four MRI-negative, nonlesional TLE patients (two male, two female) with electrographically identified left temporal onset seizures. Imaging was conducted on a Siemens 7T MRI scanner using the CEST method for glutamate, while the advanced normalization tools (ANTs) pipeline and the Automated Segmentation of the Hippocampal Subfields (ASHS) method were employed for image analysis.

RESULTS

Volumetric GluCEST imaging was validated in four nonlesional TLE patients showing increased glutamate lateralized to the hippocampus of seizure onset (p = .048, with a difference among ipsilateral to contralateral GluCEST signal percentage ranging from -0.05 to 1.37), as well as increased GluCEST signal in the ipsilateral subiculum (p = .034, with a difference among ipsilateral to contralateral GluCEST signal ranging from 0.13 to 1.57).

CONCLUSIONS

The ability of 3-D, volumetric GluCEST to localize seizure onset down to the hippocampal subfield in nonlesional TLE is an improvement upon our previous 2-D, single-slice GluCEST method. Eventually, we hope to expand volumetric GluCEST to whole-brain glutamate imaging, thus enabling noninvasive analysis of glutamate networks in epilepsy and potentially leading to improved clinical outcomes.

Automated fusion of multimodal imaging data for identifying epileptogenic lesions in patients with inconclusive magnetic resonance imaging

Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand-alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR-negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel-wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion-weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR-negative epilepsy patients.

The Most Common Lesions Detected by Neuroimaging as Causes of Epilepsy

Epilepsy is a common neurological disorder characterized by chronic, unprovoked and recurrent seizures, which are the result of rapid and excessive bioelectric discharges in nerve cells. Neuroimaging is used to detect underlying structural abnormalities which may be associated with epilepsy. This paper reviews the most common abnormalities, such as hippocampal sclerosis, malformations of cortical development and vascular malformation, detected by neuroimaging in patients with epilepsy to help understand the correlation between these changes and the course, treatment and prognosis of epilepsy. Magnetic resonance imaging (MRI) reveals structural changes in the brain which are described in this review. Recent studies indicate the usefulness of additional imaging techniques. The use of fluorodeoxyglucose positron emission tomography (FDG-PET) improves surgical outcomes in MRI-negative cases of focal cortical dysplasia. Some techniques, such as quantitative image analysis, magnetic resonance spectroscopy (MRS), functional MRI (fMRI), diffusion tensor imaging (DTI) and fibre tract reconstruction, can detect small malformations—which means that some of the epilepsies can be treated surgically. Quantitative susceptibility mapping may become the method of choice in vascular malformations. Neuroimaging determines appropriate diagnosis and treatment and helps to predict prognosis.

Automated detection and segmentation of focal cortical dysplasias (FCDs) with artificial intelligence: Presentation of a novel convolutional neural network and its prospective clinical validation

PURPOSE

Focal cortical dysplasias (FCDs) represent one of the most frequent causes of pharmaco-resistant focal epilepsies. Despite improved clinical imaging methods over the past years, FCD detection remains challenging, as FCDs vary in location, size, and shape and commonly blend into surrounding tissues without clear definable boundaries. We developed a novel convolutional neural network for FCD detection and segmentation and validated it prospectively on daily-routine MRIs.

MATERIAL AND METHODS

The neural network was trained on 201 T1 and FLAIR 3 T MRI volume sequences of 158 patients with mainly FCDs, regardless of type, and 7 focal PMG. Non-FCD/PMG MRIs, drawn from 100 normal MRIs and 50 MRIs with non-FCD/PMG pathologies, were added to the training. We applied the algorithm prospectively on 100 consecutive MRIs of patients with focal epilepsy from daily clinical practice. The results were compared with corresponding neuroradiological reports and morphometric MRI analyses evaluated by an experienced epileptologist.

RESULTS

Best training results reached a sensitivity (recall) of 70.1 % and a precision of 54.3 % for detecting FCDs. Applied on the daily-routine MRIs, 7 out of 9 FCDs were detected and segmented correctly with a sensitivity of 77.8 % and a specificity of 5.5 %. The results of conventional visual analyses were 33.3 % and 94.5 %, respectively (3/9 FCDs detected); the results of morphometric analyses with overall epileptologic evaluation were both 100 % (9/9 FCDs detected) and thus served as reference.

CONCLUSION

We developed a 3D convolutional neural network with autoencoder regularization for FCD detection and segmentation. Our algorithm employs the largest FCD training dataset to date with various types of FCDs and some focal PMG. It provided a higher sensitivity in detecting FCDs than conventional visual analyses. Despite its low specificity, the number of false positively predicted lesions per MRI was lower than with morphometric analysis. We consider our algorithm already useful for FCD pre-screening in everyday clinical practice.

Detection of covert lesions in focal epilepsy using computational analysis of multimodal magnetic resonance imaging data

Objective

To compare the location of suspect lesions detected by computational analysis of multimodal magnetic resonance imaging data with areas of seizure onset, early propagation, and interictal epileptiform discharges (IEDs) identified with stereoelectroencephalography (SEEG) in a cohort of patients with medically refractory focal epilepsy and radiologically normal magnetic resonance imaging (MRI) scans.

Methods

We developed a method of lesion detection using computational analysis of multimodal MRI data in a cohort of 62 control subjects, and 42 patients with focal epilepsy and MRI‐visible lesions. We then applied it to detect covert lesions in 27 focal epilepsy patients with radiologically normal MRI scans, comparing our findings with the areas of seizure onset, early propagation, and IEDs identified at SEEG.

Results

Seizure‐onset zones (SoZs) were identified at SEEG in 18 of the 27 patients (67%) with radiologically normal MRI scans. In 11 of these 18 cases (61%), concordant abnormalities were detected by our method. In the remaining seven cases, either early seizure propagation or IEDs were observed within the abnormalities detected, or there were additional areas of imaging abnormalities found by our method that were not sampled at SEEG. In one of the nine patients (11%) in whom SEEG was inconclusive, an abnormality, which may have been involved in seizures, was identified by our method and was not sampled at SEEG.

Significance

Computational analysis of multimodal MRI data revealed covert abnormalities in the majority of patients with refractory focal epilepsy and radiologically normal MRI that co‐located with SEEG defined zones of seizure onset. The method could help identify areas that should be targeted with SEEG when considering epilepsy surgery.

Distinguishing type II focal cortical dysplasias from normal cortex: A novel normative modeling approach

OBJECTIVE

Focal cortical dysplasias (FCDs) are a common cause of apparently non-lesional drug-resistant focal epilepsy. Visual detection of subtle FCDs on MRI is clinically important and often challenging. In this study, we implement a set of 3D local image filters adapted from computer vision applications to characterize the appearance of normal cortex surrounding the gray-white junction. We create a normative model to serve as the basis for a novel multivariate constrained outlier approach to automated FCD detection.

METHODS

Standardized MPRAGE, T₂ and FLAIR MR images were obtained in 15 patients with radiologically or histologically diagnosed FCDs and 30 healthy volunteers. Multiscale 3D local image filters were computed for each MR contrast then sampled onto the gray-white junction surface. Using an iterative Gaussianization procedure, we created a normative model of cortical variability in healthy volunteers, allowing for identification of outlier regions and estimates of similarity in normal cortex and FCD lesions. We used a constrained outlier approach following local normalization to automatically detect FCD lesions based on projection onto the mean FCD feature vector.

RESULTS

FCDs as well as some normal cortical regions such as primary sensorimotor and paralimbic regions appear as outliers. Regions such as the paralimbic regions and the anterior insula have similar features to FCDs. Our constrained outlier approach allows for automated FCD detection with 80% sensitivity and 70% specificity.

SIGNIFICANCE

A normative model using multiscale local image filters can be used to describe the normal cortical variability. Although FCDs appear similar to some cortical regions such as the anterior insula and paralimbic cortices, they can be identified using a constrained outlier detection approach. Our method for detecting outliers and estimating similarity is generic and could be extended to identification of other types of lesions or atypical cortical areas.

Automatic localization and segmentation of focal cortical dysplasia in FLAIR-negative patients using a convolutional neural network

Purpose

Focal cortical dysplasia (FCD) is a common cause of epilepsy; the only treatment is surgery. Therefore, detecting FCD using noninvasive imaging technology can help doctors determine whether surgical intervention is required. Since FCD lesions are small and not obvious, diagnosing FCD through visual evaluations of magnetic resonance imaging (MRI) scans is difficult. The purpose of this study is to detect and segment histologically confirmed FCD lesions in images of normal fluid‐attenuated inversion recovery (FLAIR)‐negative lesions using convolutional neural network (CNN) technology.

Methods

The technique involves training a six‐layer CNN named Net‐Pos, which consists of two convolutional layers (CLs); two pooling layers (PLs); and two fully connected (FC) layers, including 60 943 learning parameters. We employed activation maximization (AM) to optimize a series of pattern image blocks (PIBs) that were most similar to a lesion image block by using the trained Net‐Pos. We developed an AM and convolutional localization (AMCL) algorithm that employs the mean PIBs combined with convolution to locate and segment FCD lesions in FLAIR‐negative patients. Five evaluation indices, namely, recall, specificity, accuracy, precision, and the Dice coefficient, were applied to evaluate the localization and segmentation performance of the algorithm.

Results

The PIBs most similar to an FCD lesion image block were identified by the trained Net‐Pos as image blocks with brighter central areas and darker surrounding image blocks. The technique was evaluated using 18 FLAIR‐negative lesion images from 12 patients. The subject‐wise recall of the AMCL algorithm was 83.33% (15/18). The Dice coefficient for the segmentation performance was 52.68.

Conclusion

We developed a novel algorithm referred to as the AMCL algorithm with mean PIBs to effectively and automatically detect and segment FLAIR‐negative FCD lesions. This work is the first study to apply a CNN‐based model to detect and segment FCD lesions in images of FLAIR‐negative lesions.

Virtual resection predicts surgical outcome for drug-resistant epilepsy

Patients with drug-resistant epilepsy often require surgery to become seizure-free. While laser ablation and implantable stimulation devices have lowered the morbidity of these procedures, seizure-free rates have not dramatically improved, particularly for patients without focal lesions. This is in part because it is often unclear where to intervene in these cases. To address this clinical need, several research groups have published methods to map epileptic networks but applying them to improve patient care remains a challenge. In this study we advance clinical translation of these methods by: (i) presenting and sharing a robust pipeline to rigorously quantify the boundaries of the resection zone and determining which intracranial EEG electrodes lie within it; (ii) validating a brain network model on a retrospective cohort of 28 patients with drug-resistant epilepsy implanted with intracranial electrodes prior to surgical resection; and (iii) sharing all neuroimaging, annotated electrophysiology, and clinical metadata to facilitate future collaboration. Our network methods accurately forecast whether patients are likely to benefit from surgical intervention based on synchronizability of intracranial EEG (area under the receiver operating characteristic curve of 0.89) and provide novel information that traditional electrographic features do not. We further report that removing synchronizing brain regions is associated with improved clinical outcome, and postulate that sparing desynchronizing regions may further be beneficial. Our findings suggest that data-driven network-based methods can identify patients likely to benefit from resective or ablative therapy, and perhaps prevent invasive interventions in those unlikely to do so.

Detecting focal cortical dysplasia lesions from FLAIR-negative images based on cortical thickness

Background

Focal cortical dysplasia (FCD) is a neuronal migration disorder and is a major cause of drug-resistant epilepsy. However, many focal abnormalities remain undetected during routine visual inspection, and many patients with histologically confirmed FCD have normal fluid-attenuated inversion recovery (FLAIR-negative) images. The aim of this study was to quantitatively evaluate the changes in cortical thickness with magnetic resonance (MR) imaging of patients to identify FCD lesions from FLAIR-negative images.

Methods

We first used the three-dimensional (3D) Laplace method to calculate the cortical thickness for individuals and obtained the cortical thickness mean image and cortical thickness standard deviation (SD) image based on all 32 healthy controls. Then, a cortical thickness extension map was computed by subtracting the cortical thickness mean image from the cortical thickness image of each patient and dividing the result by the cortical thickness SD image. Finally, clusters of voxels larger than three were defined as the FCD lesion area from the cortical thickness extension map.

Results

The results showed that three of the four lesions that occurred in non-temporal areas were detected in three patients, but the detection failed in three patients with lesions that occurred in the temporal area. The quantitative analysis of the detected lesions in voxel-wise on images revealed the following: specificity (99.78%), accuracy (99.76%), recall (67.45%), precision (20.42%), Dice coefficient (30.01%), Youden index (67.23%) and area under the curve (AUC) (83.62%).

Conclusion

Our studies demonstrate an effective method to localize lesions in non-temporal lobe regions. This novel method automatically detected FCD lesions using only FLAIR-negative images from patients and was based only on cortical thickness feature. The method is noninvasive and more effective than a visual analysis for helping doctors make a diagnosis.

Detection of cortical malformations using enhanced synthetic contrast images derived from quantitative T1 maps

The detection of cortical malformations in conventional MR images can be challenging. Prominent examples are focal cortical dysplasias (FCD), the most common cause of drug-resistant focal epilepsy. The two main MRI hallmarks of cortical malformations are increased cortical thickness and blurring of the gray (GM) and white matter (WM) junction. The purpose of this study was to derive synthetic anatomies from quantitative T1 maps for the improved display of the above imaging characteristics in individual patients. On the basis of a T1 map, a mask comprising pixels with T1 values characteristic for GM is created from which the local cortical extent (CE) is determined. The local smoothness (SM) of the GM-WM junctions is derived from the T1 gradient. For display of cortical malformations, the resulting CE and SM maps serve to enhance local intensities in synthetic double inversion recovery (DIR) images calculated from the T1 map. The resulting CE- and/or SM-enhanced DIR images appear hyperintense at the site of cortical malformations, thus facilitating FCD detection in epilepsy patients. However, false positives may arise in areas with naturally elevated CE and/or SM, such as large GM structures and perivascular spaces. In summary, the proposed method facilitates the detection of cortical abnormalities such as cortical thickening and blurring of the GM-WM junction which are typical FCD markers. Still, subject motion artifacts, perivascular spaces, and large normal GM structures may also yield signal hyperintensity in the enhanced synthetic DIR images, requiring careful comparison with clinical MR images by an experienced neuroradiologist to exclude false positives.

A connectome-based mechanistic model of focal cortical dysplasia

Neuroimaging studies have consistently shown distributed brain anomalies in epilepsy syndromes associated with a focal structural lesion, particularly mesiotemporal sclerosis. Conversely, a system-level approach to focal cortical dysplasia has been rarely considered, likely due to methodological difficulties in addressing variable location and topography. Given the known heterogeneity in focal cortical dysplasia histopathology, we hypothesized that lesional connectivity consists of subtypes with distinct structural signatures. Furthermore, in light of mounting evidence for focal anomalies impacting whole-brain systems, we postulated that patterns of focal cortical dysplasia connectivity may exert differential downstream effects on global network topology. We studied a cohort of patients with histologically verified focal cortical dysplasia type II (n = 27), and age- and sex-matched healthy controls (n = 34). We subdivided each lesion into similarly sized parcels and computed their connectivity to large-scale canonical functional networks (or communities). We then dichotomized connectivity profiles of lesional parcels into those belonging to the same functional community as the focal cortical dysplasia (intra-community) and those adhering to other communities (inter-community). Applying hierarchical clustering to community-reconfigured connectome profiles identified three lesional classes with distinct patterns of functional connectivity: decreased intra- and inter-community connectivity, a selective decrease in intra-community connectivity, and increased intra- as well as inter-community connectivity. Hypo-connectivity classes were mainly composed of focal cortical dysplasia type IIB, while the hyperconnected lesions were type IIA. With respect to whole-brain networks, patients with hypoconnected focal cortical dysplasia and marked structural damage showed only mild imbalances, while those with hyperconnected subtle lesions had more pronounced topological alterations. Correcting for interictal epileptic discharges did not impact connectivity patterns. Multivariate structural equation analysis provided a mechanistic model of such complex, diverging interactions, whereby the focal cortical dysplasia structural makeup shapes its functional connectivity, which in turn modulates whole-brain network topology.

Visual analysis of automated segmentation in the diagnosis of focal cortical dysplasias with magnetic resonance imaging

Focal cortical dysplasias (FCDs) are a frequent cause of epilepsy. It has been reported that up to 40% of them cannot be visualized with conventional magnetic resonance imaging (MRI). The main objective of this work was to evaluate by means of a retrospective descriptive observational study whether the automated brain segmentation is useful for detecting FCD. One hundred and fifty-five patients, who underwent surgery between the years 2009 and 2016, were reviewed. Twenty patients with FCD confirmed by histology and a preoperative segmentation study, with ages ranging from 3 to 43 years (14 men), were analyzed. Three expert neuroradiologists visually analyzed conventional and advanced MRI with automated segmentation. They were classified into positive and negative concerning visualization of FCD by consensus. Of the 20 patients evaluated with conventional MRI, 12 were positive for FCD. Of the negative studies for FCD with conventional MRI, 2 (25%) were positive when they were analyzed with automated segmentation. In 13 of the 20 patients (with positive segmentation for FCD), cortical thickening was observed in 5 (38.5%), while pseudothickening was observed in the rest of patients (8, 61.5%) in the anatomical region of the brain corresponding to the dysplasia. This work demonstrated that automated brain segmentation helps to increase detection of FCDs that are unable to be visualized in conventional MRI images.

Structural neuroimaging

Characterizing the neuroanatomical correlates of brain development is essential in understanding brain-behavior relationships and neurodevelopmental disorders. Advances in brain MRI acquisition protocols and image processing techniques have made it possible to detect and track with great precision anatomical brain development and pediatric neurologic disorders. In this chapter, we provide a brief overview of the modern neuroimaging techniques for pediatric brain development and review key normal brain development studies. Characteristic disorders affecting neurodevelopment in childhood, such as prematurity, attention deficit hyperactivity disorder (ADHD), autism spectrum disorder (ASD), epilepsy, and brain cancer, and key neuroanatomical findings are described and then reviewed. Large datasets of typically developing children and children with various neurodevelopmental conditions are now being acquired to help provide the biomarkers of such impairments. While there are still several challenges in imaging brain structures specific to the pediatric populations, such as subject cooperation and tissues contrast variability, considerable imaging research is now being devoted to solving these problems and improving pediatric data analysis.

Regularized siamese neural network for unsupervised outlier detection on brain multiparametric magnetic resonance imaging: Application to epilepsy lesion screening

In this study, we propose a novel anomaly detection model targeting subtle brain lesions in multiparametric MRI. To compensate for the lack of annotated data adequately sampling the heterogeneity of such pathologies, we cast this problem as an outlier detection problem and introduce a novel configuration of unsupervised deep siamese networks to learn normal brain representations using a series of non-pathological brain scans. The proposed siamese network, composed of stacked convolutional autoencoders as subnetworks is designed to map patches extracted from healthy control scans only and centered at the same spatial localization to 'close' representations with respect to the chosen metric in a latent space. It is based on a novel loss function combining a similarity term and a regularization term compensating for the lack of dissimilar pairs. These latent representations are then fed into oc-SVM models at voxel-level to produce anomaly score maps. We evaluate the performance of our brain anomaly detection model to detect subtle epilepsy lesions in multiparametric (T1-weighted, FLAIR) MRI exams considered as normal (MRI-negative). Our detection model trained on 75 healthy subjects and validated on 21 epilepsy patients (with 18 MRI-negatives) achieves a maximum sensitivity of 61% on the MRI-negative lesions, identified among the 5 most suspicious detections on average. It is shown to outperform detection models based on the same architecture but with stacked convolutional or Wasserstein autoencoders as unsupervised feature extraction mechanisms.

Preprocessing surface EMG data removes voluntary muscle activity and enhances SPiQE fasciculation analysis

•

A novel preprocessing step removes the need for manual selection of relaxed surface EMG data.

•

SPiQE provides reliable fasciculation analysis from raw thirty-minute recordings in ALS.

•

This paves the way for clinical calibration of a potential novel biomarker of disease progression.

Objectives

Fasciculations are a clinical hallmark of amyotrophic lateral sclerosis (ALS). The Surface Potential Quantification Engine (SPiQE) is a novel analytical tool to identify fasciculation potentials from high-density surface electromyography (HDSEMG). This method was accurate on relaxed recordings amidst fluctuating noise levels. To avoid time-consuming manual exclusion of voluntary muscle activity, we developed a method capable of rapidly excluding voluntary potentials and integrating with the established SPiQE pipeline.

Methods

Six ALS patients, one patient with benign fasciculation syndrome and one patient with multifocal motor neuropathy underwent monthly thirty-minute HDSEMG from biceps and gastrocnemius. In MATLAB, we developed and compared the performance of four Active Voluntary IDentification (AVID) strategies, producing a decision aid for optimal selection.

Results

Assessment of 601 one-minute recordings permitted the development of sensitive, specific and screening strategies to exclude voluntary potentials. Exclusion times (0.2–13.1 minutes), processing times (10.7–49.5 seconds) and fasciculation frequencies (27.4–71.1 per minute) for 165 thirty-minute recordings were compared. The overall median fasciculation frequency was 40.5 per minute (10.6–79.4 IQR).

Conclusion

We hereby introduce AVID as a flexible, targeted approach to exclude voluntary muscle activity from HDSEMG recordings.

Significance

Longitudinal quantification of fasciculations in ALS could provide unique insight into motor neuron health.

Recommendations of the Russian League Against Epilepsy (RLAE) on the use of magnetic resonance imaging in the diagnosis of epilepsy

Introduction. The MRI method has revolutionized the diagnosis of epilepsy. However, the widespread adoption of MRI in clinical practice is slowed by an insufficient number of high-field MRI scanners, a shortage of trained specialists, and the lack of standard examination protocols. The aim of this article is to present the Recommendations of the Russian League Against Epilepsy (RLAE) on the use of magnetic resonance imaging in the diagnosis of epilepsy.

Materials and methods. As a structural element of the International League Against Epilepsy (ILAE), the RLAE considers it important to adapt the Protocol developed by ILAE for specialists in Russia and EAEU countries. The working group analyzed and generalized the clinical practice existing in the Russian Federation, the Republic of Kazakhstan, the Republic of Belarus and the Republic of Uzbekistan. These recommendations are intended for doctors in specialized centers of epilepsy surgery, and for doctors in general medical centers. The recommendations are applicable primarily to adult patients, but the general principles are relevant to children as well.

Results. In all patients with convulsive seizures shortly after the first seizure, or patients diagnosed with epilepsy who have an unexplained increase in the frequency of seizures, rapid decrease in cognitive functions or the appearance / worsening of neuropsychiatric symptoms, the RLAE recommends using a unified MR protocol for the neuroimaging of structural sequences in epilepsy with three-dimensional pulse sequences T1 and T2 FLAIR with isotropic voxel 1 × 1 × 1 mm3 and two-dimensional T2- weighted pulse sequences with a pixel size of 1 × 1 mm2 or less. The MRI examination should be combined with EEG or EEG-video monitoring. Using this protocol allows one to set a unified standard for examining patients with epilepsy in order to detect (with high sensitivity) brain lesions playing a key role in the occurrence of seizures. Here, all 13 recommendations are presented.

Conclusion. Implementation of these recommendations in clinical practice will improve the access to high-tech medical care and optimize health care costs. 

Recommendations for the use of structural magnetic resonance imaging in the care of patients with epilepsy: A consensus report from the International League Against Epilepsy Neuroimaging Task Force

Structural magnetic resonance imaging (MRI) is of fundamental importance to the diagnosis and treatment of epilepsy, particularly when surgery is being considered. Despite previous recommendations and guidelines, practices for the use of MRI are variable worldwide and may not harness the full potential of recent technological advances for the benefit of people with epilepsy. The International League Against Epilepsy Diagnostic Methods Commission has thus charged the 2013-2017 Neuroimaging Task Force to develop a set of recommendations addressing the following questions: (1) Who should have an MRI? (2) What are the minimum requirements for an MRI epilepsy protocol? (3) How should magnetic resonance (MR) images be evaluated? (4) How to optimize lesion detection? These recommendations target clinicians in established epilepsy centers and neurologists in general/district hospitals. They endorse routine structural imaging in new onset generalized and focal epilepsy alike and describe the range of situations when detailed assessment is indicated. The Neuroimaging Task Force identified a set of sequences, with three-dimensional acquisitions at its core, the harmonized neuroimaging of epilepsy structural sequences-HARNESS-MRI protocol. As these sequences are available on most MR scanners, the HARNESS-MRI protocol is generalizable, regardless of the clinical setting and country. The Neuroimaging Task Force also endorses the use of computer-aided image postprocessing methods to provide an objective account of an individual's brain anatomy and pathology. By discussing the breadth and depth of scope of MRI, this report emphasizes the unique role of this noninvasive investigation in the care of people with epilepsy.

Relationships Between Morphologic and Functional Patterns in the Polymicrogyric Cortex

Polymicrogyria is a malformation of cortical folding and layering underlying different cognitive and neurological manifestations. The polymicrogyric cortex has heterogeneous morphofunctional patterns, qualitatively described at magnetic resonance imaging (MRI) by variable severity gradients and functional activations. We investigated the link between abnormal cortical folding and cortical function in order to improve surgical planning for patients with polymicrogyria and intractable epilepsy. We performed structural and functional MRI on 14 patients with perisylvian polymicrogyria and adopted surface-based methods to detect alterations of cortical thickness (CT) and local gyrification index (LGI) compared with normal cortex (30 age-matched subjects). We quantitatively assessed the grade of anatomic disruption of the polymicrogyric cortex and defined its relationship with decreased cortical function. We observed a good matching between visual analysis and morphometric measurements. CT maps revealed sparse clusters of thickening, while LGI maps disclosed circumscribed regions of maximal alteration with a uniformly decreasing centrifugal gradient. In polymicrogyric areas in which gyral and sulcal patterns were preserved, functional activation maintained the expected location, but was reduced in extent. Morphofunctional correlations, evaluated along cortico-cortical paths between maximum morphologic alterations and significant activations, identified an interindividual threshold for LGI (z-value = -1.09) beyond which functional activations were no longer identifiable.

Clinical Value of Machine Learning in the Automated Detection of Focal Cortical Dysplasia Using Quantitative Multimodal Surface-Based Features

Objective: To automatically detect focal cortical dysplasia (FCD) lesion by combining quantitative multimodal surface-based features with machine learning and to assess its clinical value.

Methods: Neuroimaging data and clinical information for 74 participants (40 with histologically proven FCD type II) was retrospectively included. The morphology, intensity and function-based features characterizing FCD lesions were calculated vertex-wise on each cortical surface and fed to an artificial neural network. The classifier performance was quantitatively and qualitatively assessed by performing statistical analysis and conventional visual analysis.

Results: The accuracy, sensitivity, specificity of the neural network classifier based on multimodal surface-based features were 70.5%, 70.0%, and 69.9%, respectively, which outperformed the unimodal classifier. There was no significant difference in the detection rate of FCD subtypes (Pearson’s Chi-Square = 0.001, p = 0.970). Cohen’s kappa score between automated detection outcomes and post-surgical resection region was 0.385 (considered as fair).

Conclusion: Automated machine learning with multimodal surface features can provide objective and intelligent detection of FCD lesion in pre-surgical evaluation and can assist the surgical strategy. Furthermore, the optimal parameters, appropriate surface features and efficient algorithm are worth exploring.

Clinical validation of automated hippocampal segmentation in temporal lobe epilepsy

OBJECTIVE

To provide a multi-atlas framework for automated hippocampus segmentation in temporal lobe epilepsy (TLE) and clinically validate the results with respect to surgical lateralization and post-surgical outcome.

METHODS

We retrospectively identified 47 TLE patients who underwent surgical resection and 12 healthy controls. T1-weighted 3 T MRI scans were acquired for all subjects, and patients were identified by a neuroradiologist with regards to lateralization and degree of hippocampal sclerosis (HS). Automated segmentation was implemented through the Joint Label Fusion/Corrective Learning (JLF/CL) method. Gold standard lateralization was determined from the surgically resected side in Engel I (seizure-free) patients at the two-year timepoint. ROC curves were used to identify appropriate thresholds for hippocampal asymmetry ratios, which were then used to analyze JLF/CL lateralization.

RESULTS

The optimal template atlas based on subject images with varying appearances, from normal-appearing to severe HS, was demonstrated to be composed entirely of normal-appearing subjects, with good agreement between automated and manual segmentations. In applying this atlas to 26 surgically resected seizure-free patients at a two-year timepoint, JLF/CL lateralized seizure onset 92% of the time. In comparison, neuroradiology reads lateralized 65% of patients, but correctly lateralized seizure onset in these patients 100% of the time. When compared to lateralized neuroradiology reads, JLF/CL was in agreement and correctly lateralized all 17 patients. When compared to nonlateralized radiology reads, JLF/CL correctly lateralized 78% of the nine patients.

SIGNIFICANCE

While a neuroradiologist's interpretation of MR imaging is a key, albeit imperfect, diagnostic tool for seizure localization in medically-refractory TLE patients, automated hippocampal segmentation may provide more efficient and accurate epileptic foci localization. These promising findings demonstrate the clinical utility of automated segmentation in the TLE MR imaging pipeline prior to surgical resection, and suggest that further investigation into JLF/CL-assisted MRI reading could improve clinical outcomes. Our JLF/CL software is publicly available at https://www.nitrc.org/projects/ashs/.

Quantitative positron emission tomography-guided magnetic resonance imaging postprocessing in magnetic resonance imaging-negative epilepsies

OBJECTIVE

Detection of focal cortical dysplasia (FCD) is of paramount importance in epilepsy presurgical evaluation. Our study aims at utilizing quantitative positron emission tomography (QPET) analysis to complement magnetic resonance imaging (MRI) postprocessing by a morphometric analysis program (MAP) to facilitate automated identification of subtle FCD.

METHODS

We retrospectively included a consecutive cohort of surgical patients who had a negative preoperative MRI by radiology report. MAP was performed on T1-weighted volumetric sequence and QPET was performed on PET/computed tomographic data, both with comparison to scanner-specific normal databases. Concordance between MAP and QPET was assessed at a lobar level, and the significance of concordant QPET-MAP⁺ abnormalities was confirmed by postresective seizure outcome and histopathology. QPET thresholds of standard deviations (SDs) of -1, -2, -3, and -4 were evaluated to identify the optimal threshold for QPET-MAP analysis.

RESULTS

A total of 104 patients were included. When QPET thresholds of SD = -1, -2, and -3 were used, complete resection of the QPET-MAP⁺ region was significantly associated with seizure-free outcome when compared with the partial resection group (P = 0.023, P < 0.001, P = 0.006) or the no resection group (P = 0.002, P < 0.001, P = 0.001). The SD threshold of -2 showed the best combination of positive rate (55%), sensitivity (0.68), specificity (0.88), positive predictive value (0.88), and negative predictive value (0.69). Surgical pathology of the resected QPET-MAP⁺ areas revealed mainly FCD type I. Multiple QPET-MAP⁺ regions were present in 12% of the patients at SD = -2.

SIGNIFICANCE

Our study demonstrates a practical and effective approach to combine quantitative analyses of functional (QPET) and structural (MAP) imaging data to improve identification of subtle epileptic abnormalities. This approach can be readily adopted by epilepsy centers to improve postresective seizure outcomes for patients without apparent lesions on MRI.

Gray Matter and White Matter Abnormalities in Temporal Lobe Epilepsy Patients with and without Hippocampal Sclerosis

The presentation and distribution of gray matter (GM) and white matter (WM) abnormalities in temporal lobe epilepsy (TLE) have been widely studied. Here, we investigated the GM and WM abnormalities in TLE patients with and without hippocampal sclerosis (HS) in five groups of participants: healthy controls (HCs) (n = 28), right TLE patients with HS (n = 26), right TLE patients without HS (n = 30), left TLE patients with HS (n = 25), and left TLE patients without HS (n = 27). We performed a flexible factorial statistical test in a whole-brain voxel-based morphometry analysis to identify significant GM and WM abnormalities and analysis of variance of hippocampal and amygdala regions among the five groups using the FreeSurfer procedure. Furthermore, we conducted multiple regression analysis to assess regional GM and WM changes with disease duration. We observed significant ipsilateral mesiotemporal GM and WM volume reductions in TLE patients with HS compared with HCs. We also observed a slight GM amygdala swelling in right TLE patients without HS. The regression analysis revealed significant negative GM and WM changes with disease duration specifically in left TLE patients with HS. The observed GM and WM abnormalities may contribute to our understanding of the root of epilepsy mechanisms.

Integrity of the corpus callosum in patients with periventricular nodular heterotopia related epilepsy by FLNA mutation

Objective

To investigate the quantitative diffusion properties of the corpus callosum (CC) in a large group of patients with periventricular nodular heterotopia (PNH) related epilepsy and to further investigate the effect of Filamin A (FLNA) mutation on these properties.

Methods

Patients with PNH (n = 34), subdivided into FLNA-mutated (n = 11) and FLNA-nonmutated patients (n = 23) and healthy controls (n = 34), underwent 3.0 T structural MRI and diffusion imaging scan (64 direction). Fractional anisotropy (FA) and mean diffusivity (MD) were measured in the three major subdivisions of the CC (genu, body and splenium). Correlations between DTI metric changes and clinical parameters were also evaluated. Furthermore, the effect of FLNA mutation on structural integrity of the corpus callosum was examined.

Results

Patients with PNH and epilepsy had significant reductions in FA for the genu and splenium of the CC, accompanied by increases in MD for the splenium, as compared to healthy controls. There were no correlations between clinical parameters of epilepsy and MD. The FA value in the splenium negatively correlated with epilepsy duration. Interestingly, FLNA-mutated patients showed significantly decreased FA for all three major subdivisions of the CC, and increased MD for the genu and splenium, as compared to HCs and FLNA-nonmutated patients.

Conclusions

These findings support the conclusion that patients with epilepsy secondary to PNH present widespread microstructural changes found in the corpus callosum that extend beyond the macroscopic MRI-visible lesions. This study also indicates that FLNA may affect white matter integrity in this disorder.

•

PNH patients presented diffusion abnormality in splenium segment of the CC.

•

Only the FA value for the splenium negatively correlated with epilepsy duration.

•

In PNH, DTI changes of CC differentiate FLNA-mutated from nonmutated subjects.

Perilesional and contralateral white matter evolution and integrity in patients with periventricular nodular heterotopia and epilepsy: a longitudinal diffusion tensor imaging study

BACKGROUND AND PURPOSE

This study aimed to assess the evolution of perinodular and contralateral white matter abnormalities in patients with periventricular nodular heterotopia (PNH) and epilepsy.

METHODS

Diffusion tensor imaging (DTI) (64 directions) and 3 T structural magnetic resonance imaging were performed in 29 PNH patients (mean age 27.3 years), and 16 patients underwent a second scan (average time between the two scans 1.1 years). Fractional anisotropy and mean diffusivity were measured within the perilesional and contralateral white matter.

RESULTS

Longitudinal analysis showed that white matter located 10 mm from the focal nodule displayed characteristics intermediate to tissue 5 mm away, and normal-appearing white matter (NAWM) also established evolution profiles of perinodular white matter in different cortical lobes. Compared to 29 age- and sex-matched healthy controls, significant decreased fractional anisotropy and elevated mean diffusivity values were observed in regions 5 and 10 mm from nodules (P < 0.01), whilst DTI metrics of the remaining NAWM did not differ significantly from controls. Additionally, normal DTI metrics were shown in the contralateral region in patients with unilateral PNH.

CONCLUSIONS

Periventricular nodular heterotopia is associated with microstructural abnormalities within the perilesional white matter and the extent decreases with increasing distance from the nodule. In the homologous contralateral region, white matter diffusion metrics were unchanged in unilateral PNH. These findings have clinical implications with respect to the medical and surgical interventions of PNH-related epilepsy.

Local Directional Probability Optimization for Quantification of Blurred Gray/White Matter Junction in Magnetic Resonance Image

The blurred gray/white matter junction is an important feature of focal cortical dysplasia (FCD) lesions. FCD is the main cause of epilepsy and can be detected through magnetic resonance (MR) imaging. Several earlier studies have focused on computing the gradient magnitude of the MR image and used the resulting map to model the blurred gray/white matter junction. However, gradient magnitude cannot quantify the blurred gray/white matter junction. Therefore, we proposed a novel algorithm called local directional probability optimization (LDPO) for detecting and quantifying the width of the gray/white matter boundary (GWB) within the lesional areas. The proposed LDPO method mainly consists of the following three stages: (1) introduction of a hidden Markov random field-expectation-maximization algorithm to compute the probability images of brain tissues in order to obtain the GWB region; (2) generation of local directions from gray matter (GM) to white matter (WM) passing through the GWB, considering the GWB to be an electric potential field; (3) determination of the optimal local directions for any given voxel of GWB, based on iterative searching of the neighborhood. This was then used to measure the width of the GWB. The proposed LDPO method was tested on real MR images of patients with FCD lesions. The results indicated that the LDPO method could quantify the GWB width. On the GWB width map, the width of the blurred GWB in the lesional region was observed to be greater than that in the non-lesional regions. The proposed GWB width map produced higher F-scores in terms of detecting the blurred GWB within the FCD lesional region as compared to that of FCD feature maps, indicating better trade-off between precision and recall.