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.

Background and purpose Magnetic resonance imaging (MRI) is essential in the diagnosis of pharmacoresistant epilepsy (PRE), because patients with lesions detected by MRI have a better prognosis after surgery. Focal cortical dysplasia (FCD) is one of the most frequent etiologies of PRE but can be difficult to identify by MRI. Voxel-based morphometric analysis programs, like the Morphometric Analysis Program (MAP), have been developed to help improve MRI detection. Our objective was to evaluate the clinical usefulness of MAP in patients with PRE and an apparently normal MRI. Methods We studied 70 patients with focal PRE and a nonlesional MRI. The 3DT1 sequence was processed with MAP, obtaining three z-score maps. Patients were classified as MAP+ if one or more z-score maps showed a suspicious area of brightness, and MAP- if the z-score maps did not show any suspicious areas. For MAP+ cases, a second-look MRI was performed with a dedicated inspection based on the MAP findings. The MAP results were correlated with the epileptogenic zone. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Results Thirty-one percent of patients were classified as MAP+ and 69% were MAP-. Results showed a sensitivity of 0.57, specificity of 0.8, PPV of 0.91, and NPV of 0.35. In 19% of patients, an FCD was found in the second-look MRI after MAP. Conclusions MAP was helpful in the detection of lesions in PRE patients with a nonlesional MRI, which could have important repercussions for the clinical management and postoperative prognosis of these patients.

Objectives Unilateral spatial neglect (USN) is the incapacity to respond to stimuli presented opposite to a dysfunctional cerebral hemisphere. It is usually caused by non-dominant hemisphere lesions, leads to poorer prognosis and might be underdiagnosed. The objectives of the study were to ascertain the presence of USN in acute stroke patients and analyze the possible degree of underdiagnosis in a Stroke Unit. Materials and methods Prospective study of consecutive non-dominant hemisphere stroke patients within a period of 21 months. "Line Bisection" and "Triangles Cancellation" tests were used for USN screening and "Circle Gap Detection Task" to confirm the USN. The results were compared with routine Stroke Unit assessment using the NIHSS to determine the possible degree of underdiagnosis. Results A total of 62 subjects, 38 women (61.29%), mean age of 74.05 (SD 10.5) years, were included. USN was diagnosed in 25 cases (40.3%) but 56% of them were not detected in routine evaluation using the NIHSS. Conclusions Unilateral spatial neglect, a common cognitive deficit after acute stroke, is greatly underdiagnosed in routine Stroke Unit assessment. The use of simple USN-specific screening tools would improve diagnosis and therefore the possibility of implementing appropriate rehabilitation strategies.