Elaine Kuan

Naturalistic fMRI offers a patient‐friendly alternative to task‐based language mapping but presents analytical challenges due to complex brain responses. This study presents an automated framework for language mapping using naturalistic fMRI analysed with a Rotation Forest (RotF) classifier. Participants were presented a televised quiz show during fMRI acquisition and completed seven task‐based language paradigms, which were used as reference maps. RotF models were trained on voxel‐wise time series labelled using task‐based activation maps and evaluated on independent participants. Performance was assessed using the structural similarity index measure (SSIM) and the language lateralisation indices (LI). RotF generated activation maps demonstrated strong spatial and lateralisation agreement with task‐based activation, capturing both receptive and expressive language regions. Data quality, which was assessed through head motion and post‐scan questionnaire score, influenced model performance and provided a practical quality control measure. Feature selection identified a short, informative stimulus segment, enabling reliable language mapping with a scan duration of approximately 5 min. These findings demonstrate the feasibility of accurate, efficient and patient‐friendly language mapping using naturalistic fMRI combined with machine learning.

Objective: Focal to bilateral tonic–clonic seizures (FBTC) are associated with significant morbidity and an elevated risk of sudden unexpected death in epilepsy (SUDEP). The cerebellum has been implicated in modulating the frequency and severity of tonic–clonic seizures. The present study aimed to identify alterations in cerebellar functional connectivity (FC) associated with susceptibility to FBTC in individuals diagnosed with temporal lobe epilepsy (TLE). Methods: This prospective study involved the recruitment of 30 patients with unilateral TLE, who were classified into two groups: active FBTC (≥1 FBTC in the past year) and inactive FBTC (ongoing focal seizures but no FBTC within the past year, and in some cases no lifetime history), each consisting of 15 patients. Additionally, 20 demographically matched control subjects were included. Resting‐state functional MRI (rs‐fMRI) and high‐resolution T1‐weighted imaging were utilised. FC analysis was performed using the CONN toolbox, with a focus on cerebellar and subcortical regions. Group comparisons were executed using Kruskal–Wallis tests, followed by post hoc pairwise analyses. Results: The findings indicated that FC between the posterior vermis and lateral cerebellar lobules (Crus I/II) bilaterally were significantly lower in the active FBTC group compared to healthy controls. In comparison to the inactive group, the active FBTC group exhibited significantly lower FC with the contralateral Crus I and Crus II. In comparison to controls, the TLE groups exhibited lower FC between the posterior vermis and the mediodorsal and pulvinar thalamic nuclei as well as between the flocculonodular lobe and mesial temporal structures (hippocampus, parahippocampus, and amygdala). Significance: The results demonstrate impaired intracerebellar FC, particularly between the posterior vermis and lateral cerebellar lobules, in individuals with active FBTC, thereby supporting the hypothesis that the cerebellum has a regulatory role in modulating susceptibility to tonic–clonic seizures. Plain Language Summary: Focal to bilateral tonic–clonic seizures are severe seizures that start in one brain region and spread to both sides of the brain. In this study, people with temporal lobe epilepsy who had recent tonic–clonic seizures showed reduced communication between the posterior vermis and lateral cerebellar regions. Alterations in other cerebellar connections with the thalamus and temporal lobe were related to temporal lobe epilepsy itself. These findings suggest that cerebellar networks may influence vulnerability to tonic–clonic seizure spread and may be relevant to future sudden unexpected death in epilepsy risk research.