Search

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., (© The Author(s) 2022. Published by Oxford University Press on behalf of the Guarantors of Brain.)

Objective: Drug-resistant focal epilepsy is often caused by focal cortical dysplasias (FCDs). The distribution of these lesions across the cerebral cortex and the impact of lesion location on clinical presentation and surgical outcome are largely unknown. We created a neuroimaging cohort of patients with individually mapped FCDs to determine factors associated with lesion location and predictors of postsurgical outcome., Methods: The MELD (Multi-centre Epilepsy Lesion Detection) project collated a retrospective cohort of 580 patients with epilepsy attributed to FCD from 20 epilepsy centers worldwide. Magnetic resonance imaging-based maps of individual FCDs with accompanying demographic, clinical, and surgical information were collected. We mapped the distribution of FCDs, examined for associations between clinical factors and lesion location, and developed a predictive model of postsurgical seizure freedom., Results: FCDs were nonuniformly distributed, concentrating in the superior frontal sulcus, frontal pole, and temporal pole. Epilepsy onset was typically before the age of 10 years. Earlier epilepsy onset was associated with lesions in primary sensory areas, whereas later epilepsy onset was associated with lesions in association cortices. Lesions in temporal and occipital lobes tended to be larger than frontal lobe lesions. Seizure freedom rates varied with FCD location, from around 30% in visual, motor, and premotor areas to 75% in superior temporal and frontal gyri. The predictive model of postsurgical seizure freedom had a positive predictive value of 70% and negative predictive value of 61%., Significance: FCD location is an important determinant of its size, the age at epilepsy onset, and the likelihood of seizure freedom postsurgery. Our atlas of lesion locations can be used to guide the radiological search for subtle lesions in individual patients. Our atlas of regional seizure freedom rates and associated predictive model can be used to estimate individual likelihoods of postsurgical seizure freedom. Data-driven atlases and predictive models are essential for evidence-based, precision medicine and risk counseling in epilepsy., (© 2021 The Authors. Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.)

Background: We investigated whether model-based indices of cerebral autoregulation (CA) are associated with outcomes after pediatric traumatic brain injury., Methods: This was a retrospective analysis of a prospective clinical database of 56 pediatric patients with traumatic brain injury undergoing intracranial pressure monitoring. CA indices were calculated, including pressure reactivity index (PRx), wavelet pressure reactivity index (wPRx), pulse amplitude index (PAx), and correlation coefficient between intracranial pressure pulse amplitude and cerebral perfusion pressure (RAC). Each CA index was used to compute optimal cerebral perfusion pressure (CPP). Time of CPP below lower limit of autoregulation (LLA) or above upper limit of autoregulation (ULA) were computed for each index. Demographic, physiologic, and neuroimaging data were collected. Primary outcome was determined using Pediatric Glasgow Outcome Scale Extended (GOSE-Peds) at 12 months, with higher scores being suggestive of unfavorable outcome. Univariate and multiple linear regression with guided stepwise variable selection was used to find combinations of risk factors that can best explain the variability of GOSE-Peds scores, and the best fit model was applied to the age strata. We hypothesized that higher GOSE-Peds scores were associated with higher CA values and more time below LLA or above ULA for each index., Results: At the univariate level, CPP, dose of intracranial hypertension, PRx, PAx, wPRx, RAC, percent time more than ULA derived for PAx, and percent time less than LLA derived for PRx, PAx, wPRx, and RAC were all associated with GOSE-Peds scores. The best subset model selection on all pediatric patients identified that when accounting for CPP, increased dose of intracranial hypertension and percent time less than LLA derived for wPRx were independently associated with higher GOSE-Peds scores. Age stratification of the best fit model identified that in children less than 2 years of age or 8 years of age or more, percent time less than LLA derived for wPRx represented the sole independent predictor of higher GOSE-Peds scores when accounting for CPP and dose of intracranial hypertension. For children 2 years or younger to less than 8 years of age, dose of intracranial hypertension was identified as the sole independent predictor of higher GOSE-Peds scores when accounting for CPP and percent time less than LLA derived for wPRx., Conclusions: Increased dose of intracranial hypertension, PRx, wPRx, PAx, and RAC values and increased percentage time less than LLA based on PRx, wPRx, PAx, and RAC are associated with higher GOSE-Peds scores, suggestive of unfavorable outcome. Reducing intracranial hypertension and maintaining CPP more than LLA based on wPRx may improve outcomes and warrants prospective investigation., (© 2021. Springer Science+Business Media, LLC, part of Springer Nature and Neurocritical Care Society.)

Background: Acute necrotizing encephalopathy (ANE) is a rare condition associated with rapid progression to coma and high incidence of morbidity and mortality., Methods: Clinical, electroencephalographic (EEG), and brain magnetic resonance imaging (MRI) characteristics and immunomodulatory therapy timing were retrospectively analyzed in children with ANE. ANE severity scores (ANE-SS) and MRI scores were also assessed. The associations of patient characteristics with 6-month modified Rankin scale (mRS) and length of hospitalization were determined using either univariate linear regression or one-way analysis of variance., Results: 7 children were retrospectively evaluated. Normal EEG sleep spindles ( P = .024) and early treatment ( R 2 = .57, P = .030) were associated with improved outcomes (ie, decreased mRS). Higher ANE-SS ( R 2 = .79, P = .011), higher age ( R 2 = .62, P = .038), and presence of brainstem lesions ( P = .015) were associated with longer length of hospitalization. Other patient characteristics were not significantly associated with mRS or length of hospitalization., Conclusion: Early immunomodulatory therapy and normal sleep spindles are associated with better functional outcome in children with ANE.

Background: Management after cerebral arteriovenous malformation (AVM) rupture aims toward preventing hemorrhagic expansion while maintaining cerebral perfusion to avoid secondary injury. We investigated associations of model-based indices of cerebral autoregulation (CA) and autonomic function (AF) with outcomes after pediatric cerebral AVM rupture., Methods: Multimodal neurologic monitoring data from the initial 3 days after cerebral AVM rupture were retrospectively analyzed in children (< 18 years). AF indices included standard deviation of heart rate (HRsd), root-mean-square of successive differences in heart rate (HRrmssd), low-high frequency ratio (LHF), and baroreflex sensitivity (BRS). CA indices include pressure reactivity index (PRx), wavelet pressure reactivity indices (wPRx and wPRx-thr), pulse amplitude index (PAx), and correlation coefficient between intracranial pressure pulse amplitude and cerebral perfusion pressure (RAC). Percent time of cerebral perfusion pressure (CPP) below lower limits of autoregulation (LLA) was also computed for each CA index. Primary outcomes were determined using Pediatric Glasgow Outcome Score Extended-Pediatrics (GOSE-PEDs) at 12 months and acquired epilepsy. Association of biomarkers with outcomes was investigated using linear regression, Wilcoxon signed-rank, or Chi-square., Results: Fourteen children were analyzed. Lower AF indices were associated with poor outcomes (BRS [p = 0.04], HRsd [p = 0.04], and HRrmssd [p = 0.00]; and acquired epilepsy (LHF [p = 0.027]). Higher CA indices were associated with poor outcomes (PRx [p = 0.00], wPRx [p = 0.00], and wPRx-thr [p = 0.01]), and acquired epilepsy (PRx [p = 0.02] and wPRx [p = 0.00]). Increased time below LLA was associated with poor outcome (percent time below LLA based on PRx [p = 0.00], PAx [p = 0.04], wPRx-thr [p = 0.03], and RAC [p = 0.01]; and acquired epilepsy (PRx [p = 0.00], PAx [p = 0.00], wPRx-thr [p = 0.03], and RAC [p = 0.01])., Conclusions: After pediatric cerebral AVM rupture, poor outcomes are associated with AF and CA when applying various neurophysiologic model-based indices. Prospective work is needed to assess these indices of CA and AF in clinical decision support.

Objectives: Electroencephalography is used in neurocritical care for detection of seizures and assessment of cortical function. Due to limited resolution from scalp electroencephalography, important abnormalities may not be readily detectable. We aimed to identify whether intracranial electroencephalography allows for improved methods of monitoring cortical function in children with severe traumatic brain injury., Design: This is a retrospective cohort study from a prospectively collected clinical database. We investigated the occurrence rate of epileptiform abnormalities detected on intracranial electroencephalography when compared with scalp electroencephalography. We also investigated the strength of association of quantitative electroencephalographic parameters and cerebral perfusion pressure between both intracranial and scalp electroencephalography., Setting: This is a single-institution study performed in the Phoenix Children's Hospital PICU., Patients: Eleven children with severe traumatic brain injury requiring invasive neuromonitoring underwent implantation of a six-contact intracranial electrode as well as continuous surface electroencephalography., Interventions: None., Measurements and Main Results: Visual detection of epileptiform abnormalities was performed by pediatric epileptologists. Association of intracranial and scalp electroencephalography total power, alpha percentage, and alpha-delta power ratio to cerebral perfusion pressure was performed using univariate dynamic structural equations modeling. Demographic data were assessed by retrospective analysis. Intracranial and scalp electroencephalography was performed in 11 children. Three of 11 children had observed epileptiform abnormalities on intracranial electroencephalography. Two patients had epileptiform abnormalities identified exclusively on intracranial electroencephalography, and one patient had seizures initiating on intracranial electroencephalography before arising on scalp electroencephalography. Identification of epileptiform abnormalities was associated with subsequent identification of stroke or malignant cerebral edema. We observed statistically significant positive associations between intracranial alpha-delta power ratio to cerebral perfusion pressure in nine of 11 patients with increased strength of association on intracranial compared with scalp recordings., Conclusions: These findings suggest that intracranial electroencephalography may be useful for detection of secondary insult development in children with traumatic brain injury.

Traumatic brain injury (TBI) is a leading cause of morbidity and mortality in children. Improved methods of monitoring real-time cerebral physiology are needed to better understand when secondary brain injury develops and what treatment strategies may alleviate or prevent such injury. In this review, we discuss emerging technologies that exist to better understand intracranial pressure (ICP), cerebral blood flow, metabolism, oxygenation and electrical activity. We also discuss approaches to integrating these data as part of a multimodality monitoring strategy to improve patient care., (Copyright © 2019 Appavu, Burrows, Foldes and Adelson.)

Objective: Brain-computer interface (BCI) technology aims to provide individuals with paralysis a means to restore function. Electrocorticography (ECoG) uses disc electrodes placed on either the surface of the dura or the cortex to record field potential activity. ECoG has been proposed as a viable neural recording modality for BCI systems, potentially providing stable, long-term recordings of cortical activity with high spatial and temporal resolution. Previously we have demonstrated that a subject with spinal cord injury (SCI) could control an ECoG-based BCI system with up to three degrees of freedom (Wang et al 2013 PLoS One). Here, we expand upon these findings by including brain-control results from two additional subjects with upper-limb paralysis due to amyotrophic lateral sclerosis and brachial plexus injury, and investigate the potential of motor and somatosensory cortical areas to enable BCI control., Approach: Individuals were implanted with high-density ECoG electrode grids over sensorimotor cortical areas for less than 30 d. Subjects were trained to control a BCI by employing a somatotopic control strategy where high-gamma activity from attempted arm and hand movements drove the velocity of a cursor., Main Results: Participants were capable of generating robust cortical modulation that was differentiable across attempted arm and hand movements of their paralyzed limb. Furthermore, all subjects were capable of voluntarily modulating this activity to control movement of a computer cursor with up to three degrees of freedom using the somatotopic control strategy. Additionally, for those subjects with electrode coverage of somatosensory cortex, we found that somatosensory cortex was capable of supporting ECoG-based BCI control., Significance: These results demonstrate the feasibility of ECoG-based BCI systems for individuals with paralysis as well as highlight some of the key challenges that must be overcome before such systems are translated to the clinical realm. ClinicalTrials.gov Identifier: NCT01393444.

A brain-computer interface (BCI) system transforms neural activity into control signals for external devices in real time. A BCI user needs to learn to generate specific cortical activity patterns to control external devices effectively. We call this process BCI learning, and it often requires significant effort and time. Therefore, it is important to study this process and develop novel and efficient approaches to accelerate BCI learning. This article reviews major approaches that have been used for BCI learning, including computer-assisted learning, co-adaptive learning, operant conditioning, and sensory feedback. We focus on BCIs based on electrocorticography and intracortical microelectrode arrays for restoring motor function. This article also explores the possibility of brain modulation techniques in promoting BCI learning, such as electrical cortical stimulation, transcranial magnetic stimulation, and optogenetics. Furthermore, as proposed by recent BCI studies, we suggest that BCI learning is in many ways analogous to motor and cognitive skill learning, and therefore skill learning should be a useful metaphor to model BCI learning.

Context: Spinal cord injury (SCI) results in a loss of function and sensation below the level of the lesion. Neuroprosthetic technology has been developed to help restore motor and autonomic functions as well as to provide sensory feedback., Findings: This paper provides an overview of neuroprosthetic technology that aims to address the priorities for functional restoration as defined by individuals with SCI. We describe neuroprostheses that are in various stages of preclinical development, clinical testing, and commercialization including functional electrical stimulators, epidural and intraspinal microstimulation, bladder neuroprosthesis, and cortical stimulation for restoring sensation. We also discuss neural recording technologies that may provide command or feedback signals for neuroprosthetic devices., Conclusion/clinical Relevance: Neuroprostheses have begun to address the priorities of individuals with SCI, although there remains room for improvement. In addition to continued technological improvements, closing the loop between the technology and the user may help provide intuitive device control with high levels of performance.

Paralyzed individuals can control the movement of an assistive device using changes in electroencephalographic (EEG) power resulting from attempted movements. Simultaneous, proportional control of two-dimensional (2D) device movements can be achieved with the concurrent modulation of brain activity that is associated with the attempted movement and rest of two independent body parts. Movement control may be improved by spatial filtering methods that recombine raw EEGs to form new signals with more focused information about the underlying brain activity. This study compared spatial filters offline for improving simultaneous proportional 2D movement commands from EEGs. Filtering options evaluated were common average referencing, Laplacian, independent component analysis, principle component analysis, and two novel ways of applying common spatial pattern (CSP) analysis. CSP analysis is a supervised algorithm that optimally recombines EEGs collected under two known conditions. Both CSP options resulted in more accurate movement prediction than the other filtering options. CSP was particularly advantageous when separating EEGs associated with neighboring or overlapping areas on the motor homunculus. Finally, CSP performed well using smaller subsets of filtered signals, thus making CSP practical and efficient for simultaneous 2D control. A 2D online cursor control example using CSP filtering is included to show CSP's utility.

Movement-related field potentials can be extracted and processed in real-time with magnetoencephalography (MEG) and used for brain machine interfacing (BMI). However, due to its immense sensitivity to magnetic fields, MEG is prone to a low signal to noise ratio. It is therefore important to collect enough initial data to appropriately characterize motor-related activity and to ensure that decoders can be built to adequately translate brain activity into BMI-device commands. This is of particular importance for therapeutic BMI applications where less time spent collecting initial open-loop data means more time for performing neurofeedback training which could potentially promote cortical plasticity and rehabilitation. This study evaluated the amount of hand-grasp movement and rest data needed to characterize sensorimotor modulation depth and build classifier functions to decode brain states in real-time. It was determined that with only five minutes of initial open-loop MEG data, decoders can be built to classify brain activity as grasp or rest in real-time with an accuracy of 84 ± 6%.

How an "emergency" is defined by an internist and an emergency physician is the focus of this paper, which originated in a study of nonemergency use of two urban hospital emergency departments by Medicaid, uninsured, and commercially insured patients. Retrospective medical record reviews of 219 patients conducted independently by these two physicians revealed agreement on clinical impressions but dramatic divergence regarding the designation of visits as "emergencies" and the appropriate treatment location. Subsequent interviews with each physician suggested that the divergence of opinion regarding the definition of a true emergency is ideologically motivated and specialty related. Considered in the context of ED studies, which show enormous variations in the percentage of cases judged to be "emergencies," defining an "emergency" may be more a matter of physician training, specialty, and beliefs than of science. Further analysis revealed no correlation between patients' perceptions and either physician's judgments concerning what constitutes an "emergency," suggesting that neither specialty's assumptions are sensitive to patients' experience of the physical pain and anxiety that frequently lead them to present to the ED.