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

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

Atlas of lesion locations and postsurgical seizure freedom in focal cortical dysplasia: A MELD study

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.

Association of Outcomes with Model-Based Indices of Cerebral Autoregulation After Pediatric Traumatic Brain Injury

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.

Treatment Timing, EEG, Neuroimaging, and Outcomes After Acute Necrotizing Encephalopathy in Children

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 (R² = .57, P = .030) were associated with improved outcomes (ie, decreased mRS). Higher ANE-SS (R² = .79, P = .011), higher age (R² = .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.

Multimodal Assessment of Cerebral Autoregulation and Autonomic Function After Pediatric Cerebral Arteriovenous Malformation Rupture

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.

Approaches to Multimodality Monitoring in Pediatric 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.

Remapping cortical modulation for electrocorticographic brain-computer interfaces: a somatotopy-based approach in individuals with upper-limb paralysis

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.

Brain computer interface learning for systems based on electrocorticography and intracortical microelectrode arrays

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.

Neuroprosthetic technology for individuals with spinal cord injury

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.