Extent of piriform cortex resection in children with temporal lobe epilepsy.

OBJECTIVE: A greater extent of resection of the temporal portion of the piriform cortex (PC) has been shown to be associated with higher likelihood of seizure freedom in adults undergoing anterior temporal lobe resection (ATLR) for drug-resistant temporal lobe epilepsy (TLE). There have been no such studies in children, therefore this study aimed to investigate this association in a pediatric cohort. METHODS: A retrospective, neuroimaging cohort study of children with TLE who underwent ATLR between 2012 and 2021 was undertaken. The PC, hippocampal and amygdala volumes were measured on the preoperative and postoperative T1-weighted MRI. Using these volumes, the extent of resection per region was compared between the seizure-free and not seizure-free groups. RESULTS: In 50 children (median age 9.5 years) there was no significant difference between the extent of resection of the temporal PC in the seizure-free (median = 50%, n = 33/50) versus not seizure-free (median = 40%, n = 17/50) groups (p = 0.26). In a sub-group of 19 with ipsilateral hippocampal atrophy (quantitatively defined by ipsilateral-to-contralateral asymmetry), the median extent of temporal PC resection was greater in children who were seizure-free (53%) versus those not seizure-free (19%) (p = 0.009). INTERPRETATION: This is the first study demonstrating that, in children with TLE and hippocampal atrophy, more extensive temporal PC resection is associated with a greater chance of seizure freedom-compatible with an adult series in which 85% of patients had hippocampal sclerosis. In a combined group of children with and without hippocampal atrophy, the extent of PC resection was not associated with seizure outcome, suggesting different epileptogenic networks within this cohort.

Predicting seizure outcome after epilepsy surgery: Do we need more complex models, larger samples, or better data?

OBJECTIVE: The accurate prediction of seizure freedom after epilepsy surgery remains challenging. We investigated if (1) training more complex models, (2) recruiting larger sample sizes, or (3) using data-driven selection of clinical predictors would improve our ability to predict postoperative seizure outcome using clinical features. We also conducted the first substantial external validation of a machine learning model trained to predict postoperative seizure outcome. METHODS: We performed a retrospective cohort study of 797 children who had undergone resective or disconnective epilepsy surgery at a tertiary center. We extracted patient information from medical records and trained three models-a logistic regression, a multilayer perceptron, and an XGBoost model-to predict 1-year postoperative seizure outcome on our data set. We evaluated the performance of a recently published XGBoost model on the same patients. We further investigated the impact of sample size on model performance, using learning curve analysis to estimate performance at samples up to N = 2000. Finally, we examined the impact of predictor selection on model performance. RESULTS: Our logistic regression achieved an accuracy of 72% (95% confidence interval [CI] = 68%-75%, area under the curve [AUC] = .72), whereas our multilayer perceptron and XGBoost both achieved accuracies of 71% (95% CIMLP = 67%-74%, AUCMLP = .70; 95% CIXGBoost own = 68%-75%, AUCXGBoost own = .70). There was no significant difference in performance between our three models (all p > .4) and they all performed better than the external XGBoost, which achieved an accuracy of 63% (95% CI = 59%-67%, AUC = .62; pLR = .005, pMLP = .01, pXGBoost own = .01) on our data. All models showed improved performance with increasing sample size, but limited improvements beyond our current sample. The best model performance was achieved with data-driven feature selection. SIGNIFICANCE: We show that neither the deployment of complex machine learning models nor the assembly of thousands of patients alone is likely to generate significant improvements in our ability to predict postoperative seizure freedom. We instead propose that improved feature selection alongside collaboration, data standardization, and model sharing is required to advance the field.

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.

Simultaneous proton density, T1 , T2 , and flip-angle mapping of the brain at 7 T using multiparametric 3D SSFP imaging and parallel-transmission universal pulses.

PURPOSE: Performing simultaneous quantitative MRI at ultrahigh field is challenging, as B0 and B1+ heterogeneities as well as specific absorption rate increase. Too large deviations of flip angle from the target can induce biases and impair SNR in the quantification process. In this work, we use calibration-free parallel transmission, a dedicated pulse-sequence parameter optimization and signal fitting to recover 3D proton density, flip angle, T1 , and T2 maps over the whole brain, in a clinically suitable time. METHODS: Eleven optimized contrasts were acquired with an unbalanced SSFP sequence by varying flip-angle amplitude and RF phase-cycling increment, at a 1.0 × 1.0 × 3.0 mm3 resolution. Acquisition time was 16 minutes 36 seconds for the whole brain. Parallel transmission and universal pulses were used to mitigate B1+ heterogeneity, to improve the results' reliability over 6 healthy volunteers (3 females/3 males, age 22.6 ± 2.7 years old). Quantification of the physical parameters was performed by fitting the acquired contrasts to the simulated ones using the Bloch-Torrey equations with a realistic diffusion coefficient. RESULTS: Whole-brain 3D maps of effective flip angle, proton density, and relaxation times were estimated. Parallel transmission improved the robustness of the results at 7 T. Results were in accordance with literature and with measurements from standard methods. CONCLUSION: These preliminary results show robust proton density, flip angle, T1 , and T2 map retrieval. Other parameters, such as ADC, could be assessed. With further optimization in the acquisition, scan time could be reduced and spatial resolution increased to bring this multiparametric quantification method to clinical research routine at 7 T.

3D variable-density SPARKLING trajectories for high-resolution T2*-weighted magnetic resonance imaging.

We have recently proposed a new optimization algorithm called SPARKLING (Spreading Projection Algorithm for Rapid K-space sampLING) to design efficient compressive sampling patterns for magnetic resonance imaging (MRI). This method has a few advantages over conventional non-Cartesian trajectories such as radial lines or spirals: i) it allows to sample the k-space along any arbitrary density while the other two are restricted to radial densities and ii) it optimizes the gradient waveforms for a given readout time. Here, we introduce an extension of the SPARKLING method for 3D imaging by considering both stacks-of-SPARKLING and fully 3D SPARKLING trajectories. Our method allowed to achieve an isotropic resolution of 600 µm in just 45 seconds for T2∗-weighted ex vivo brain imaging at 7 Tesla over a field-of-view of 200 × 200 × 140 mm3 . Preliminary in vivo human brain data shows that a stack-of-SPARKLING is less subject to off-resonance artifacts than a stack-of-spirals.