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.

Funder: National Institute for Health Research (NIHR) GOSH BRC, 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.

IntroductionOne 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 visualise 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.MethodsThe Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonised 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.ResultsOur pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. Overall, after including a border-zone around lesions, the developed MELD FCD surface-based algorithm had a sensitivity of 67% and a specificity of 54% on the withheld test cohort, and a sensitivity of 85% on a restricted subcohort of seizure free patients with FCD type IIB who had T1 and FLAIR MRI data.ConclusionsThis 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.HighlightsThis large, multi-centre, multi-scanner neuroimaging cohort captures the heterogeneity of histopathological subtypes and imaging features of patients with FCD.We developed a robust and interpretable surface-based algorithm which detects FCDs with a sensitivity of 67% and a specificity of 54%.The algorithm generates individual patient reports that “open the AI black-box” highlighting predicted lesion locations, alongside the imaging features and their relative saliency to the classifier.

After an acute ischemic stroke, patients with a large CT perfusion (CTP) predicted infarct core (pIC) have poor clinical outcome. However, previous research suggests that this relationship may be relevant for subgroups of patients determined by pretreatment and treatment-related variables while negligible for others. We aimed to identify these variables.We included a cohort of 828 patients with acute proximal carotid arterial occlusions imaged with a whole-brain CTP within 8 h from stroke onset. pIC was computed on CTP Maps (cerebral blood flow30%), and poor clinical outcome was defined as a 90-day modified Rankin Scale score2. Potential mediators of the association between pIC and clinical outcome were evaluated through first-order and advanced interaction analyses in the derivation cohort (n = 654) for obtaining a prediction model. The derived model was further validated in an independent cohort (n = 174).The volume of pIC was significantly associated with poor clinical outcome (OR = 2.19, 95% CI = 1.73 - 2.78, p0.001). The strength of this association depended on baseline National Institute of Health Stroke Scale, glucose levels, the use of thrombectomy, and the interaction of age with thrombectomy. The model combining these variables showed good discrimination for predicting clinical outcome in both the derivation cohort and validation cohorts (area under the receiver operating characteristic curve 0.780 (95% CI = 0.746-0.815) and 0.782 (95% CI = 0.715-0.850), respectively).In patients imaged within 8 h from stroke onset, the association between pIC and clinical outcome is significantly modified by baseline and therapeutic variables. These variables deserve consideration when evaluating the prognostic relevance of pIC.•The volume of CT perfusion (CTP) predicted infarct core (pIC) is associated with poor clinical outcome in acute ischemic stroke imaged within 8 h of onset. •The relationship between pIC and clinical outcome may be modified by baseline clinical severity, glucose levels, thrombectomy use, and the interaction of age with thrombectomy. •CTP pIC should be evaluated in an individual basis for predicting clinical outcome in patients imaged within 8 h from stroke onset.