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.

Identifying a structural brain lesion on MRI has important implications in epilepsy and is the most important correlate to seizure freedom after surgery in patients with drug-resistant focal onset epilepsy. However, at conventional magnetic field strengths (1.5 and 3T) only around 60-85% of MRI examinations reveal such lesions. Over the last decade, studies have demonstrated the added value of 7T MRI in patients with and without known epileptogenic lesions from 1.5 and/or 3T. However, translation of 7T MRI to clinical practice is still challenging, particularly in centers new to 7T, and there is a need for practical recommendations on targeted use of 7T MRI in the clinical management of patients with epilepsy. The 7T Epilepsy Task Force - an international group representing 21 7T MRI centers with experience from scanning over 2000 patients with epilepsy – would hereby like to share its experience with the neurology community regarding the appropriate clinical indications, patient selection and preparation, acquisition protocols and setup, technical challenges, and radiological guidelines for 7T MRI in epilepsy patients. This article mainly addresses structural imaging, but also presents multiple non-structural MRI techniques that benefit from 7T and hold promise as future directions in epilepsy. Answering to the increased availability of 7T MRI as an approved tool for diagnostic purposes, this article aims to give guidance on clinical 7T MRI epilepsy management by giving recommendations on referral, suitable 7T MRI protocols and image interpretation.