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.
When planning for epilepsy surgery, multiple potential sites for resection may be identified through anatomical imaging. Magnetoencephalography (MEG) using optically pumped sensors (OP-MEG) is a ...non-invasive functional neuroimaging technique which could be used to help identify the epileptogenic zone from these candidate regions. Here we test the utility of a-priori information from anatomical imaging for differentiating potential lesion sites with OP-MEG. We investigate a number of scenarios: whether to use rigid or flexible sensor arrays, with or without a-priori source information and with or without source modelling errors. We simulated OP-MEG recordings for 1309 potential lesion sites identified from anatomical images in the Multi-centre Epilepsy Lesion Detection (MELD) project. To localise the simulated data, we used three source inversion schemes: unconstrained, prior source locations at centre of the candidate sites, and prior source locations within a volume around the lesion location. We found that prior knowledge of the candidate lesion zones made the inversion robust to errors in sensor gain, orientation and even location. When the reconstruction was too highly restricted and the source assumptions were inaccurate, the utility of this a-priori information was undermined. Overall, we found that constraining the reconstruction to the region including and around the participant's potential lesion sites provided the best compromise of robustness against modelling or measurement error.
Objective. Histopathological examinations will diminish as minimally invasive epilepsy surgery increasingly replaces open surgery. The objective of this study was to test if visual and computer-aided ...quantitative analyses of presurgical high-quality 3 Tesla MRIs complying with the International League Against Epilepsy (ILAE) Neuroimaging Task Force recommendations can inform on histopathological diagnosis. Methods. Ninety-two patients from Copenhagen and Oslo University Hospitals fulfilled patient-, imaging-, and histopathological inclusion criteria: 69 patients were diagnosed with hippocampal sclerosis (HS) ILAE type 1 or 2, and 23 patients had normal appearing hippocampi or other histopathology than HS (no-HS). MRIs from 52 healthy controls (HC) were included. Image processing was performed in FreeSurfer v.6.0 with the built-in cross-sectional hippocampal subfield segmentation tool and multimodal MRI input. Volume outputs were used to calculate volume asymmetry ratios (VARs) for whole hippocampus (WH) and subfields. Results. HS patients had significantly larger WH VARs compared to no-HS patients and HC, with a sensitivity=0.93 and specificity=1.0 for histopathological HS diagnosis. Visual MRI assessment yielded a sensitivity=0.90 and specificity=0.96 for histopathological HS diagnosis. CA1 and CA4 VARs and the number of seizure-free patients were not significantly different in HS ILAE type 1 compared to type 2 patients. Significance. FreeSurfer analyses of presurgical MRIs are excellent at separating patients histopathologically diagnosed with HS from patients with other pathology or normal appearing hippocampi. Using the FreeSurfer hippocampal subfield segmentation tool did not allow for separating HS ILAE subtypes.
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.
Objective
The purpose of this study was to evaluate if focal cortical dysplasia (FCD) co‐localization to cortical functional networks is associated with the temporal distribution of epilepsy onset in ...FCD.
Methods
International (20 center), retrospective cohort from the Multi‐Centre Epilepsy Lesion Detection (MELD) project. Patients included if >3 years old, had 3D pre‐operative T1 magnetic resonance imaging (MRI; 1.5 or 3 T) with radiologic or histopathologic FCD after surgery. Images processed using the MELD protocol, masked with 3D regions‐of‐interest (ROI), and co‐registered to fsaverage_sym (symmetric template). FCDs were then co‐localized to 1 of 7 distributed functional cortical networks. Negative binomial regression evaluated effect of FCD size, network, histology, and sulcal depth on age of epilepsy onset. From this model, predictive age of epilepsy onset was calculated for each network.
Results
Three hundred eighty‐eight patients had median age seizure onset 5 years (interquartile range IQR = 3–11 years), median age at pre‐operative scan 18 years (IQR = 11–28 years). FCDs co‐localized to the following networks: limbic (90), default mode (87), somatomotor (65), front parietal control (52), ventral attention (32), dorsal attention (31), and visual (31). Larger lesions were associated with younger age of onset (p = 0.01); age of epilepsy onset was associated with dominant network (p = 0.04) but not sulcal depth or histology. Sensorimotor networks had youngest onset; the limbic network had oldest age of onset (p values <0.05).
Interpretation
FCD co‐localization to distributed functional cortical networks is associated with age of epilepsy onset: sensory neural networks (somatomotor and visual) with earlier onset, and limbic latest onset. These variations may reflect developmental differences in synaptic/white matter maturation or network activation and may provide a biological basis for age‐dependent epilepsy onset expression. ANN NEUROL 2022;92:503–511