Artificial intelligence for the detection of focal cortical dysplasia: Challenges in translating algorithms into clinical practice

Abstract

Focal cortical dysplasias (FCDs) are malformations of cortical development and one of the most common pathologies causing pharmacoresistant focal epilepsy. Resective neurosurgery yields high success rates, especially if the full extent of the lesion is correctly identified and completely removed. The visual assessment of magnetic resonance imaging does not pinpoint the FCD in 30%–50% of cases, and half of all patients with FCD are not amenable to epilepsy surgery, partly because the FCD could not be sufficiently localized. Computational approaches to FCD detection are an active area of research, benefitting from advancements in computer vision. Automatic FCD detection is a significant challenge and one of the first clinical grounds where the application of artificial intelligence may translate into an advance for patients' health. The emergence of new methods from the combination of health and computer sciences creates novel challenges. Imaging data need to be organized into structured, well‐annotated datasets and combined with other clinical information, such as histopathological subtypes or neuroimaging characteristics. Algorithmic output, that is, model prediction, requires a technically correct evaluation with adequate metrics that are understandable and usable for clinicians. Publication of code and data is necessary to make research accessible and reproducible. This critical review introduces the field of automatic FCD detection, explaining underlying medical and technical concepts, highlighting its challenges and current limitations, and providing a perspective for a novel research environment.

Combining OPM and lesion mapping data for epilepsy surgery planning: a simulation study

“…Here, the source reconstruction priors were selected based on suspected FCDs segmented from structural MRIs by the MELD algorithm. In practice, a similar approach could be taken, with potential sites segmented from MRI by either machine learning methods 59 – 61 or by trained neuroradiologists. Information from other imaging modalities and clinical observation could also be used to decide which priors are chosen and their size, tailoring the OP-MEG source reconstruction to the individual.…”

Combining magnetic resonance fingerprinting with voxel‐based morphometric analysis to reduce false positives for focal cortical dysplasia detection

“…Many prior studies investigated automated FCD prediction using machine/deep learning with voxel‐wise or vertex‐wise MRI‐based features as input 20,46–48 . FP findings were commonly reported 49 . The desired balance between sensitivity and specificity depends on the cohort being evaluated and the user’s experience.…”

“…20,[46][47][48] FP findings were commonly reported. 49 The desired balance between sensitivity and specificity depends on the cohort being evaluated and the user's experience. At multimodal patient management conferences, semiology, video-EEG monitoring, or positron emission tomography (PET) can provide lobar localization or lateralization, and FP findings on MRI can be quickly ruled out based on these other findings.…”

The impact of referring patients with drug-resistant focal epilepsy to an epilepsy center for presurgical diagnosis

“…Therefore, improving diagnostic sensitivity for amygdala dysplasias and FCDs is vital to provide these patients best postoperative outome. Possible options for improving sensitivity for FCD are postprocessing, quantitative MRI, and ultra-high field (7 or 9 T) MRI, techniques that yet have to become accessible for clinical practice [29][30][31][32][33][34][35]. Additionally, it is crucial that epileptologists and radiologists exchange localizing information from EEG and semiology to improve MRI sensitivity to these subtle lesions.…”