Diagnostic MRI evaluation of temporal lobe epilepsy (TLE) depends on the subjective visual interpretation of MRI images. These interpretations could be enhanced by quantitative artificial intelligence (AI) support tools. Humans often make sequential and conditional decisions during their radiological interpretations, such as whether an abnormality is present and, if present, characterizing the abnormality. It is not known whether it is superior to train AI to treat every decision separately in a similar step-wise manner or to train a model holistically on all decisions simultaneously. Here, we analysed three large epilepsy MRI datasets [n = 3676, 2320 people with epilepsy and 1356 healthy controls (HC)] to perform two tasks: (i) establish the presence of a TLE pattern on MRI and (ii) determine TLE pattern lateralization. We compared Step-wise models that independently classify TLE versus HC and lateralize patients as left TLE (L-TLE) or right TLE (R-TLE), against a simultaneous model trained to distinguish all three classes in a single step. To do this, 3D volumetric T1-weighted images were input into an EfficientNetV2 model multiple times to ensure reproducibility of results. Class prediction, model classification confidence and saliency maps were output for interpretability. Step-wise models outperformed the Simultaneous model on both tasks (both Ps < 0.001), with an average ∼2.8% accuracy increase for discriminating HC from TLE and an average 12.7% accuracy increase for distinguishing L-TLE from R-TLE. For both the Step-wise and Simultaneous models, important features discriminating TLE from HC included the known TLE limbic pattern involving the hippocampus, parahippocampal cortical regions, cingulate cortex and lateral temporal regions. However, there was less concordance between the Step-wise and Simultaneous models for the L-TLE versus R-TLE task (all Fisher's Zs > 10.5, Ps < 0.001); the Step-wise model focused less on subcortical regions such as the thalamus and hippocampus and focused more on distributed cortical pathology. Across the two Step-wise models, 95.1% of TLE patients had accurate classifications in either HC versus TLE and/or L-TLE versus R-TLE tasks. These results included 69.6% of patients being both correctly labelled as TLE and lateralized, 13.9% being correctly labelled TLE but lateralized incorrectly and 11.6% being lateralized correctly but not detected as TLE. These findings provide evidence that diagnostic tasks with simpler, Step-wise AI models may enhance diagnostic performance and interpretability in clinical workflows. Future AI clinical support tools can leverage this step-wise approach in the early identification of TLE-related structural patterns, supporting timely diagnosis and treatment decisions.

PURPOSE:Pathogenic variants in AUTS2 are associated with neurodevelopmental disorders, commonly characterized by intellectual disability and autism spectrum disorder. Epilepsy in AUTS2-related syndromes has been reported only in a limited number of patients, usually with scant information on the electroclinical features and longitudinal outcome. METHODS:We report a proband with AUTS2-related syndrome and performed a narrative literature review. RESULTS:The electroclinical features of our case fall within the spectrum of a developmental/epileptic encephalopathy with spike-wave activation in sleep. CONCLUSIONS:This case highlights the importance of a detailed electroclinical characterization of epilepsy in AUTS2-related syndrome and underscores the need for systematic EEG and cognitive monitoring to improve clinical management.

Objective To obtain the standardization and validation of Ped-COMPASS-CQ (Pediatric Composite Autonomic Symptom Score - Caregiver Questionnaire); this new tool was formulated to assess the autonomic symptom profile in the pediatric population. Specifically, we started with the validated COMPASS-31 questionnaire and adapted it for caregiver completion. We added questions to explore additional dysautonomic symptoms not covered in the original questionnaire, including headache, sleep disturbance, neuropathic pain, fatigue, and thermoregulation. Methods We recruited 1888 caregivers of children aged between 5 and 16 years in the period from August 2022 to February 2024. In order to develop a statistically valid instrument, we corroborated the internal structure of the questionnaire through a confirmatory factor analysis; the construct validity of the questionnaire was also confirmed through generalized linear regression models. The internal consistency of the subscales was analyzed by estimating the Cronbach's Alpha as well as by computing Spearman's inter-scale and item-scale correlation coefficients. Results We obtained the standardized reference values of the general population of children, expressed as mean and standard deviation in each autonomic domain and in the total score of the questionnaire. Conclusion Ped-COMPASS-CQ seems to be a sensitive tool for early detection of autonomic dysfunction in children, easy to use and with a low economic impact. The scores obtained represent a starting point to study the function of the autonomic nervous system in pediatric subjects. It could be an ecological tool to be adopted as a first approach to the symptomatic patient with dysautonomia or for monitoring an autonomic dysfunction.

Objective To evaluate the relationship between electroclinical features of epilepsy and cardiac autonomic function, assessed through heart rate variability (HRV), in children and youths with paediatric-onset epilepsies. Materials and Methods We prospectively enrolled patients with epilepsy aged 3–25 years who underwent polygraphic EEG recordings, analysing HRV in a 5-minute resting ECG segment. Nine indices were examined, including time-domain, frequency-domain, and nonlinear measures. Associations between HRV parameters and clinical variables were assessed using Spearman correlations and linear regression models adjusted for age and sex. Principal component analysis (PCA) was used to identify composite autonomic profiles. Results Ninety-eight patients were included (mean age 14.6 ± 5.2 years; 54.1% female). Earlier epilepsy onset was significantly associated with higher resting heart rate and reduced long-range HRV scaling (lower DFA α2), suggesting impaired autonomic maturation. The duration of active epilepsy was significantly associated with a composite HRV profile identified by the PCA analysis (PC1; r = 0.266, p = 0.016), reflecting sympathetic predominance, reduced parasympathetic activity, and altered nonlinear dynamics. Discussion Cardiac autonomic regulation appeared to be influenced by the electro-clinical characteristics of epilepsy, mostly dependent on the age at seizure onset and the duration of active epilepsy. The progressive shift toward sympathetic dominance and reduced autonomic complexity warrants to monitor autonomic function in patients with paediatric-onset epilepsies .

Epilepsy-dyskinesia syndromes (EDS) are a complex group of neurogenetic disorders characterized by the co-occurrence of epilepsy and movement disorders. Despite their increasing clinical recognition, the molecular and clinical spectrum of EDS remains poorly understood. While numerous genetic aetiologies have been implicated, systematic characterization across diverse populations is lacking. This study aimed to delineate the molecular and clinical landscape of EDS in a large, multinational cohort, focusing on movement disorder phenomenologies, genotype-phenotype correlations, and treatment responses. We conducted a multicentre, cross-sectional study involving 609 patients with childhood-onset movement disorders associated with pathogenic variants in 105 predefined genes. Clinical data were collected from over 30 centres across 25 countries using a standardized survey, capturing movement disorder phenomenologies, seizure types, developmental trajectories, motor function and treatment outcomes. We classified EDS-associated genes into biologically meaningful groups by performing unsupervised clustering, which integrated protein-protein interactions and functional data. Genotype-phenotype correlations were assessed using a one-versus-remainder approach to quantify differential enrichment of clinical manifestations and treatment responses. Pathogenic variants were identified in 74 of the 105 predefined genes, with 12 genes accounting for two-thirds of cases. The most frequently reported genes were MECP2, ATP1A3, and GNAO1. Data-driven gene cluster analysis identified 12 functional groups, mapping EDS to relevant biological pathways and informing genotype-phenotype analyses. Dystonia (34.2%), stereotypies (24.6%) and ataxia (16.2%) were the most prevalent movement disorders, with gene- and pathway-specific movement disorder signatures extending beyond previously known associations. Notably, most patients exhibited mixed movement disorders, highlighting the phenotypic complexity of EDS. Epilepsy was diagnosed in only 66.8% of cases, suggesting that some EDS primarily manifest as movement disorders. Developmental trajectories varied by genetic aetiology. Pharmacological responses demonstrated gene- and pathway-specific treatment effects, confirming established therapeutic associations (e.g. PRRT2 variants responding to carbamazepine) and identifying previously unrecognized effects, such as exacerbation of motor symptoms with levodopa/carbidopa in GNAO1 and MECP2 variants. This study provides a detailed characterization of EDS, identifying distinct genetic, phenotypic and therapeutic patterns. The findings underscore the need for early recognition of movement disorders within epilepsy cohorts, offer immediate insights to improve anticipatory guidance and clinical management of EDS, and advocate for personalized treatment strategies. By laying the groundwork for longitudinal studies to refine genotype-phenotype correlations and establish a natural history, this work paves the way for interventional clinical trials and precision medicine approaches.

Epilepsy is a frequent feature of genetic neurodevelopmental disorders and is increasingly recognized as a disorder of disrupted neuronal networks rather than isolated focal pathology. DYNC1H1, encoding the heavy chain of cytoplasmic dynein 1, is implicated in a broad spectrum of neuromuscular and central nervous system disorders, including intellectual disability, malformations of cortical development (MCDs), and epilepsy. We report a female patient with drug-resistant epilepsy beginning at 9 years of age, normal brain MRI and multiple seizure types, including focal motor, tonic–clonic, epileptic spasms, and atypical absence seizures. She also presented with lower limb hypotrophy, pes cavus, and axonal neuropathy. Genetic testing revealed a heterozygous NM_001376.5(DYNC1H1):c.752G > A(p.Arg251His) variant in the N-terminal tail domain, inherited from her father and shared by two siblings with cognitive and gait difficulties. Motor disability progressed over time, and current therapy reduced but did not eliminate seizures. This case expands the phenotypic spectrum of DYNC1H1-related disorders, demonstrating that tail-domain variants can cause late-childhood epilepsy even in the absence of cortical malformations. The coexistence of central and peripheral involvement highlights widespread dynein-mediated network disruption, while intrafamilial variability underscores the heterogeneity of these conditions.

OBJECTIVES:To describe the clinical and epidemiological characteristics of pediatric epilepsy in Sahrawi refugee camps and to explore treatment gaps and perceived environmental influences in a low-resource desert setting. METHODS:A cross-sectional observational study was conducted during a two-week humanitarian mission (April-May 2025) in two hospitals in Sahrawi Refugee Camps in the Tindouf desertic area (Algeria). Consecutive pediatric patients with suspected or confirmed seizures were enrolled (n = 63). Data were collected using a structured clinical record and the Pediatric Epilepsy Classification Questionnaire. Treatment gap was defined according to ILAE criteria. A semi-structured interview assessed caregivers' perceptions of climate-related effects on a subgroup. Descriptive and exploratory analyses were performed. RESULTS:Sixty-three children with epilepsy were included (49 previously diagnosed, 14 newly diagnosed). Seizures were mainly focal. Among participants, 65% had undergone at least one EEG and 48% an MRI. Clinical-estimated epilepsy treatment gap was 38%, with higher prevalence in younger children. Valproic acid was the most used antiseizure medication, while access to alternative therapies depended largely on external supply routes. Medication availability was inconsistent and frequently dependent on humanitarian support. Among a sub-group of interviewed caregivers, most reported perceived seasonal or heat-related influences on seizures, particularly during summer, although responses were heterogeneous and not significantly associated with age or diagnosis. School attendance, used as a proxy for social integration, was not significantly associated with treatment gap. SIGNIFICANCE:According to our exploratory findings, children with epilepsy in Sahrawi refugee camps face substantial diagnostic and therapeutic barriers, compounded by unstable medication supply and environmental stressors. Limited access to investigations, specialist care, and follow-up contributes to persistent treatment gaps. Integrating standardized clinical tools, strengthening supply chains, and addressing climate-related vulnerabilities are essential to improve equity and continuity of care in protracted humanitarian settings.

Introduction Brain structural differences consistent with an older-appearing brain have been reported in people with epilepsy, but the extent to which these differences reflect clinical characteristics vs broader socioeconomic context is unclear. We investigated whether country-level socioeconomic factors are associated with neuroanatomical differences in adults with epilepsy using MRI-based age prediction, along with epilepsy subtype, sex, and clinical factors. Methods Structural MRI and clinical data were collected from 26 epilepsy centres across 12 countries in the Americas, Australia, Europe, Asia and Africa. MRI-based age estimates were estimated using a previously developed prediction model trained on 29,175 healthy subjects. Brain predicted age difference (BrainPAD) was calculated as the difference between MRI-predicted brain age and chronological age. National gross domestic product (GDP) per capita and income inequality (Gini index) were obtained from the World Bank. Associations between BrainPAD and epilepsy subtype (temporal lobe epilepsy, extratemporal epilepsy, and genetic generalised epilepsy), national socioeconomic context (GDP per capita and Gini index), age and sex were assessed using regression models. Results We analyzed 2,109 individuals with epilepsy and 1,041 healthy non-epilepsy controls (57% female; median age = 35; range 17-83). BrainPAD was higher in epilepsy than controls (β 4.2 years, SE 0.4; t=10.6), with increases ranging from 2.5 to 6 years across subtypes. Male sex was associated with 1 year higher BrainPAD relative to females (SE 0.33, t=3.12). There were no main effects of GDP or Gini index; however, significant interactions between were observed. The effect of epilepsy on BrainPAD was greater in countries with lower GDP per capita (t=-2.74) and higher income inequality (t=2.72). Conclusions Clinical factors and socioeconomic context both influence brain structural ageing in epilepsy. These findings highlight the importance of geographic and economic diversity in neuroimaging research and underscore the relevance of global socioeconomic context when interpreting brain health measures.

Although pathogenic variants in MECP2 are classically associated with Rett syndrome (RTT), increasing evidence suggests that they can underlie a broader spectrum of neurological phenotypes. Clinical manifestations may vary according to sex, variant type, residual protein function, and pattern of X-chromosome inactivation. We describe five unrelated individuals carrying pathogenic MECP2 variants identified through multiplex ligation-dependent probe amplification, chromosomal microarray analysis, and next-generation sequencing. Clinical, neuroradiological, neurophysiological, and molecular findings were retrospectively reviewed. Two unrelated girls carrying large de novo Xq28 deletions encompassing the entire MECP2 locus presented with mild neurodevelopmental impairment and epilepsy, but no developmental regression or classic RTT features. Both girls showed borderline cognitive functioning and normal brain MRI. A 9-year-old boy carrying a maternally inherited MECP2 frameshift variant presented with intellectual disability, autism spectrum disorder, and focal epilepsy, whereas carriers in his family exhibited milder neuropsychiatric manifestations. A 44-year-old man carrying a MECP2 missense variant presented with an early-onset spastic-ataxic syndrome, peripheral neuropathy, and cerebellar dysfunction, while a 16-year-old girl patient carrying a distinct de novo MECP2 missense variant displayed isolated mild motor incoordination and subtle cerebellar signs with preserved cognitive functioning. Our findings expand the evidence that pathogenic MECP2 variants can produce neurological phenotypes distinct from classic RTT, including mild neurodevelopmental impairment without regression, and predominantly cerebellar or spastic-ataxic manifestations associated with limited cognitive involvement. Allelic heterogeneity seems to correlate with clinical phenotypes, at least in our small cohort. In conjunction with established diagnostic criteria, these observations support testing MECP2 in a selection of atypical neurodevelopmental and movement disorder presentations.

OBJECTIVE:To assess awareness, attitudes, and preparedness among Italian epilepsy-care professionals regarding the impact of climate change on epilepsy management. METHODS:We conducted a national, anonymous Italian-language online survey distributed through professional networks and scientific societies (LICE, SNO). The questionnaire included Likert-scale items, closed-ended responses were summarized descriptively. RESULTS:We collected 167 responses from a heterogeneous sample by professional role and geographical area. All respondents acknowledged that global warming is occurring; 100% rated its impact on future generations as moderate-to-severe, and 84.3% reported moderate-to-severe concern for their patients. Support was high for continuing professional education on climate and health (99.4%), patient educational materials (88.6%), and workplace sustainability guidelines (97%). Individual mitigation actions were common (e.g., 93.3% reported recycling more frequently), whereas institutional initiatives were less consistently reported (e.g., 46.1% reported telemedicine use and 42.6% reported no transportation-related initiatives). CONCLUSIONS:Italian epilepsy-care professionals demonstrate high awareness and concern regarding climate change and its impact on patients. While support for education and sustainability initiatives is strong, translation into institutional and research practices remains limited, highlighting the need for targeted policies and infrastructure.

Recent studies suggest a possible association between variants in SETD5 and epilepsy, particularly in individuals with intellectual disability and developmental delay. However, the current understanding of SETD5 function in epilepsy is limited. We describe a 6-year-old girl harboring a pathogenic SETD5 gene variant, disclosed in early infancy by whole exome sequencing that was performed for global developmental delay. Her neurologic phenotype evolved during follow-up to include focal and generalized seizures as well as an overt neurodevelopmental disorder, characterized by receptive-expressive language difficulties with speech disorder and mild cognitive impairment. Her clinical picture was also characterized by recurrent urinary tract infections in a duplex collecting system due to a concomitant and unrelated GREB1L gene variant. Our findings confirm that epilepsy may arise after SETD5 variants, with subtle clinical manifestations that may overlap with behavioral phenomena in children who also exhibit cognitive and behavioral comorbidities.

BackgroundCerebral palsy is a group of nonprogressive motor disorders resulting from early brain development impairment. Its prevalence is higher in low- and middle-income countries, where health care resources are limited. Data on cerebral palsy in refugee settings remain scarce, particularly in regions marked by prolonged displacement.MethodsThis cross-sectional study examined 29 children with cerebral palsy in the Sahrawi refugee camps in Tindouf, Algeria. Detailed demographic, medical history, neurological findings, and comorbidity data were collected during outpatient visits conducted as part of a humanitarian mission.ResultsPerinatal distress was reported in 65.5% of cases. Motor impairments were significant, with only 44.8% able to walk and 20.7% lacking head control. Language delays (65.5%), feeding difficulties (65.5%), and epilepsy (52%) were highly prevalent. Diagnostic evaluations, such as magnetic resonance imaging (MRI) and electroencephalography (EEG), were scarce and inconsistent. Access to rehabilitation services was discontinuous, and pharmacologic treatments for spasticity and pain were unavailable. Environmental factors, such as sandy terrain, further complicated mobility.ConclusionCerebral palsy in the Sahrawi refugee camps reflects patterns seen in low- and middle-income countries but is exacerbated by displacement and resource scarcity. Improved access to early diagnosis, structured rehabilitation, and targeted pharmacologic therapies is urgently needed to address these unmet needs and improve outcomes for affected children.

BACKGROUND:Children with epilepsy are at increased risk for reduced health-related quality of life (HRQoL), due to the combined impact of seizures, comorbidities (somatic, psychiatric, neurologic, neurodevelopmental), social limitations. However, validated tools in different languages for HRQoL in pediatric epilepsies remain limited. AIM:To explore HRQoL in children/adolescents with epilepsy, focusing on epilepsy-related factors, social difficulties, and overall well-being, after linguistic validation of the Italian Pediatric Quality of Life Inventory Epilepsy Module (PedsQL-EM). METHODS:The sample included 119 participants (aged 8-18-year-old). Caregivers completed the Italian PedsQL-EM and the Italian version of the Child Behavior Checklist (CBCL) Social Problems subscale. Hierarchical multiple regression was performed to identify predictors of HRQoL, and a mediation model tested the indirect effects on the Social Problems subscale of the CBCL. RESULTS:The Italian PedsQL-EM showed good internal consistency (ω = 0.72-.92). We found an high correlation between each domain of the PedsQL-EM, allowing to perform further analysis using a comprehensive total score. The total score strongly correlated with lower cognitive performances, neurological and psychiatric comorbidities, and was also significantly correlated with the subscale scores of the CBCL. HRQoL significantly mediated the relationship between clinical severity and social problems (indirect effect = 2.83; 95 % CI = 1.374-4.402). CONCLUSION:In children with epilepsy, lower cognitive abilities and neurological/psychiatric comorbidities may affect social functioning through the mediation role of HRQoL. Utilizing PedsQL-EM as a screening tool can help identify these risks early, allowing for targeted interventions. Given the high psychiatric comorbidity in these patients, integrating behavioral health services into epilepsy care could improve comprehensive assessment and treatment, enhancing overall outcomes for affected children.

Outer membrane vesicle (OMV)-based vaccines have been employed worldwide in response to epidemic meningococcal disease outbreaks caused by Neisseria meningitidis. The complex composition of OMVs raises challenges in the identification of antigens which contribute to a protective immune response. Here, we measured total IgG antibody binding profiles to a dedicated antigen microarray using human sera from an open-label Phase II trial (NCT00962624) of 4CMenB (Bexsero), a licensed vaccine containing an OMV component. Significant IgG responses were observed against specific Outer Membrane Proteins (OMPs) from OMV antigens, including FetA, PorB, BamA and PorA. Partial Least Squares Regression was used to correlate IgG antibody reactivity profiles with the human complement-dependent killing of meningococci. We show that this approach is a powerful method to identify the potential contributions of OMV antigens - notably OpcA, FetA, PorA and PorB- towards serum bactericidal activity in human vaccinee serum against indicator strains, a recognised correlate of protection against invasive meningococcal disease.

We present the case of a child who developed focal seizures, emotional and behavioral dysregulation, and sleep abnormalities at age 5. Trio whole genome sequencing identified biallelic mutations in the SDHA gene, which encodes a key component of mitochondrial complex II. Mitochondrial respiratory chain activities and muscle biopsy confirmed impaired oxidative metabolism. Yeast Saccharomyces cerevisiae complementation assays showed that all the mutations were presumably disease related. Mutations in SDHA are associated with developmental delay, hypotonia, ataxia, together with bilateral hyperintensities in the basal ganglia at brain MRI. This case corroborates the phenotypic variability of SDHA variants and highlights the relevance of functional assays in validating genetic findings.

BACKGROUND AND OBJECTIVES:Temporal lobe epilepsy (TLE) is commonly associated with mesiotemporal pathology and widespread alterations of gray and white matter structures. Evidence supports a progressive condition, although the temporal evolution of TLE is poorly defined. In this ENIGMA-Epilepsy study, we aim to investigate structural alterations in gray and white matter across the adult lifespan in patients with TLE by charting both gray and white matter changes and explore the covariance of age-related alterations in both compartments. METHODS:Mega-analysis of parcellated T1-weighted and diffusion MRI data across 18 international sites for patients with TLE was compared against healthy controls. We combined median-age split groupwise comparisons with cross-sectional sliding age-window analyses to explore gray (cortical thickness, subcortical volume) and white matter microstructure (fractional anisotropy, mean diffusivity) age-related changes. Five-year range age windows were constructed from mean z scores of all patients. Covariance analyses examined the coupled correlations of gray and white matter lifespan curves for each region. RESULTS:We studied 769 patients with TLE and 885 healthy controls across an age range of 17-73 years. Robust (pFDR < 0.05) gray matter thickness/volume decline (d < -0.20) was seen across a broad cortico-subcortical territory, extending beyond the mesiotemporal lobe throughout the adult lifespan in patients with TLE. White matter changes were also widespread across multiple fiber tracts with peak effects in temporolimbic fibers in fractional anisotropy (d < -0.3, pFDR < 0.05) and mean diffusivity measures (d > 0.3, pFDR < 0.05). Changes spanned the adult time window and effects exceeded typical aging-related processes in patients at the level of cortical thickness, subcortical volume, and diffusion measures, particularly in patients older than 55 years. Covariance analyses revealed strong associations across multiple white matter tracts, subcortical structures, and cortical regions within and beyond the temporolimbic system. DISCUSSION:This study highlights that patients with TLE exhibit more pronounced and widespread gray and white matter atrophy across the lifespan. The cross-sectional nature of our study limits definitive conclusions on whether the atrophy shown is progressive but emphasizes the importance of prompt diagnosis and intervention in patients. Collectively, our results motivate future longitudinal studies to clarify consequences of drug-resistant epilepsy.

Background Persistent cortical deafness in the pediatric population is rarely reported, and there is limited information on its implications for early intervention. Objectives This study aims to (1) conduct a scoping review on pediatric cortical deafness and (2) present a case report of a 7-year-old girl with left unilateral spastic cerebral palsy and cortical deafness resulting from presumed perinatal bilateral stroke. Methods A search of PubMed, Scopus, and Web of Science identified 407 manuscripts. After the screening, 5 studies met the inclusion criteria for analysis. The case report details clinical characteristics, diagnostic challenges, and intervention strategies for pediatric cortical deafness. Results The scoping review highlighted the limited literature on pediatric cortical deafness, emphasizing its association with extensive bilateral lesions and heterogeneous etiology. The case report underscored the need for comprehensive auditory function measurements, early diagnosis, and tailored interventions. Conclusions Early and tailored interventions are crucial for improving prognosis in pediatric cortical deafness, particularly in cases associated with bilateral perinatal stroke.

N-methyl-D-aspartate receptors (NMDARs) are ionotropic glutamate channels that play a pivotal role in brain development and the regulation of learning and memory processes. De novo pathogenic variants in four genes encoding NMDA receptor subunits (GRIN1, GRIN2A, GRIN2B, and GRIN2D) have been implicated in a broad spectrum of neurodevelopmental disorders, including developmental delay, intellectual disability, autism spectrum disorders, epilepsy, and movement disorders. Mutations in the GRIN1 and GRIN2B genes, which encode the GluN1 and GluN2B subunits, respectively, are strongly associated with malformations of cortical development, including diffuse dysgyria, bilateral polymicrogyria, hippocampal dysplasia, corpus callosum hypoplasia, and other findings such as ventricular enlargement and basal ganglia abnormalities. Conversely, GRIN2A mutations are associated with heterogeneous and less specific neuroimaging patterns. We reviewed the existing literature on the neuroradiological features associated with GRIN gene mutations, also providing pictorial representations from our patient cohort. The analysis revealed a more consistent association of malformations of cortical development with GRIN1 and GRIN2B variants, likely reflecting the critical role of these genes in neuronal migration and proper development of cortical structures. In comparison, GRIN2A mutations are associated with milder brain abnormalities. An integrated assessment of neuroimaging patterns and GRIN gene variants provides valuable insights for differential diagnosis and supports targeted genetic screening in patients presenting with epileptic encephalopathy, global developmental delay, and autism spectrum disorders.