Background and ObjectivesFocal cortical dysplasia (FCD) is a type of malformations of cortical development and one of the leading causes of drug-resistant epilepsy. Postoperative results improve the diagnosis of lesions on structural MRIs. Advances in quantitative algorithms have increased the identification of FCD lesions. However, due to significant differences in size, shape, and location of the lesion in different patients and a big deal of time for the objective diagnosis of lesion as well as the dependence of individual interpretation, sensitive approaches are required to address the challenge of lesion diagnosis. In this research, a FCD computer-aided diagnostic system to improve existing methods is presented.MethodsMagnetic resonance imaging (MRI) data were collected from 58 participants (30 with histologically confirmed FCD type II and 28 without a record of any neurological prognosis). Morphological and intensity-based features were calculated for each cortical surface and inserted into an artificial neural network. Statistical examinations evaluated classifier efficiency.ResultsNeural network evaluation metrics—sensitivity, specificity, and accuracy—were 96.7, 100, and 98.6%, respectively. Furthermore, the accuracy of the classifier for the detection of the lobe and hemisphere of the brain, where the FCD lesion is located, was 84.2 and 77.3%, respectively.ConclusionAnalyzing surface-based features by automated machine learning can give a quantitative and objective diagnosis of FCD lesions in presurgical assessment and improve postsurgical outcomes.

Background: Selective amygdalohippocampectomy (SA) is an effective treatment for drug-resistant cases of epilepsy due to hippocampal sclerosis (HS). However, its neurocognitive outcomes are inconsistent across the previous studies, pointing to potential location-specific confounders. Here, we investigated the neurocognitive outcomes of SA in an Iranian center recently adopting this approach. Methods: Thirty adults (53.3% of females, age 31.4 ± 6.2 years) with drug-resistant epilepsy due to HS were included in the study. Patients were stratified into surgical (n = 15) and medical (n = 15) treatment groups based on their preferences. Neurocognitive function was assessed before and 6 months after intervention using Wisconsin Card Sorting Test (WCST), Wechsler Adult Intelligence Scale-Revised, and Wechsler Memory Scale- Third Edition (WMS-III). Postintervention performance changes were compared between the two groups, and predictors of worse postoperative outcomes were investigated. Results: Longitudinal changes of performance in WMS-III and WCST were significantly different between the surgically and medically treated patients. Postoperative WMS-III performance showed an average 25% decline (mean ∆T2-T1 = –25.1%, T = –6.6, P < 0.001), and WCST performance improved by an average of 49% (mean ∆T2-T1 = +49.1%, T = 4.6, P < 0.001). The decline in memory performance was more severe in the left-sided surgery and in patients with higher baseline education (mean ∆T2-T1 = –31.1%, T = –8.9, P < 0.001). Conclusion: In our center, executive functioning improved or remained stable after SA, but memory functions declined moderately. The left-sided SA and higher education were associated with more severe decline in memory functions, highlighting the need for special considerations for these groups.

Background: Accurate classi cation of focal cortical dysplasia (FCD) has been challenging due to the problematic visual detection in magnetic resonance imaging (MRI). Hence, recently, there has been a necessity for employing new techniques to solve the problem.Methods: MRI data were collected from 58 participants (30 subjects with FCD type II and 28 normal subjects). Morphological and intensity-based characteristics were calculated for each cortical level and then the performance of the three classi ers: decision tree (DT), support vector machine (SVM) and arti cial neural network (ANN) was evaluated.Results: Metrics for evaluating classi cation methods, sensitivity, speci city and accuracy for the DT were 96.7%, 100% and 98.6%, respectively; It was 95%, 100% and 97.9% for the SVM and 96.7%, 100% and 98.6% for the ANN.Conclusion: Comparison of the performance of the three classi cations used in this study showed that all three have excellent performance in speci city, but in terms of classi cation sensitivity and accuracy, the arti cial neural network method has worked better. HighlightsAn ANN based model for detecting focal cortical dysplasia (FCD) from MRI images is proposed.FCD detection accuracy of the proposed model is 98.6%.The proposed method can be a valuable tool to improve the preoperative evaluation of patients with drug-resistant epilepsy.

No abstract