Diffusion magnetic resonance imaging connectome features are predictive of functional lateralization of semantic processing in the anterior temporal lobes.

Assessment of regional language lateralization is crucial in many scenarios, but not all populations are suited for its evaluation via task-functional magnetic resonance imaging (fMRI). In this study, the utility of structural connectome features for the classification of language lateralization in the anterior temporal lobes (ATLs) was investigated. Laterality indices for semantic processing in the ATL were computed from task-fMRI in 1038 subjects from the Human Connectome Project who were labeled as stronger rightward lateralized (RL) or stronger leftward to bilaterally lateralized (LL) in a data-driven approach. Data of unrelated subjects (n = 432) were used for further analyses. Structural connectomes were generated from diffusion-MRI tractography, and graph theoretical metrics (node degree, betweenness centrality) were computed. A neural network (NN) and a random forest (RF) classifier were trained on these metrics to classify subjects as RL or LL. After classification, comparisons of network measures were conducted via permutation testing. Degree-based classifiers produced significant above-chance predictions both during cross-validation (NN: AUC-ROC[CI] = 0.68[0.64-0.73], accuracy[CI] = 68.34%[63-73.2%]; RF: AUC-ROC[CI] = 0.7[0.66-0.73], accuracy[CI] = 64.81%[60.9-68.5]) and testing (NN: AUC-ROC[CI] = 0.69[0.53-0.84], accuracy[CI] = 68.09[53.2-80.9]; RF: AUC-ROC[CI] = 0.68[0.53-0.84], accuracy[CI] = 68.09[55.3-80.9]). Comparison of network metrics revealed small effects of increased node degree within the right posterior middle temporal gyrus (pMTG) in subjects with RL, while degree was decreased in the right posterior cingulate cortex (PCC). Above-chance predictions of functional language lateralization in the ATL are possible based on diffusion-MRI connectomes alone. Increased degree within the right pMTG as a right-sided homologue of a known semantic hub, and decreased hubness of the right PCC may form a structural basis for rightward-lateralized semantic processing.

Increased body mass index (BMI) associated with late epilepsy onset in patients with temporal encephaloceles: a systematic review and analysis of individual patient data.

OBJECTIVE: This study investigates the association of Body Mass Index (BMI) and age of epilepsy onset, in patients with epilepsy associated with temporal encephaloceles (TEs). METHODS: A comprehensive PubMed literature review was conducted using the keywords "temporal encephaloceles" and "epilepsy" for identifying articles for the analysis. Inclusion criteria encompassed all evidence levels reporting patients with TE-related epilepsy and documented BMI. Logistic regression analyses were performed to examine the effect of BMI on predicting epilepsy onset after the 25th year of age. Spearman's correlation assessed the relationship between BMI with epilepsy onset. Finally, the association between BMI and postsurgical outcomes, distinguishing between more favourable outcomes (Engel Class I and II) and less favourable outcomes (Engell Class III and IV) was explored. RESULTS: Of the initially identified 88 articles, nine were included in the analysis, involving 127 patients with TE-related epilepsy and reported BMI. The mean age of epilepsy onset was 24.9 years (SD = 14.8 years), with a mean BMI of 28.0 kg/m2 (SD = 7.4 kg/m2). A significant positive correlation was observed between BMI and age of epilepsy onset (rho = 0.448, p < 0.001). Female patients had higher BMI compared to male patients (30.1 kg/m2, SD = 8.7 kg/m2 and 26.5 kg/m2, SD = 5.3 kg/m2 respectively, p = 0.008). However, the epilepsy onset did not differ significantly between male and female patients (p = 0.26). The bivariate logistic regression showed that patients with increased BMI were more likely to have an epilepsy onset after the 25th year of age, adjusted for the confounder sex (OR = 1.133, 95%-CI [1.060, 1.211], p < 0.001). Finally, a potential trend indicated a higher average BMI among patients with more favourable postsurgical outcomes than less favourable postsurgical outcomes (27.3 kg/m2, SD = 7.7 kg/m2 and 24.8 kg/m2, SD = 2.2 kg/m2 respectively, p = 0.076).

Random forest analysis of midbrain hypometabolism using [18F]-FDG PET identifies Parkinson's disease at the subject-level.

Parkinson's disease (PD) is currently diagnosed largely on the basis of expert judgement with neuroimaging serving only as a supportive tool. In a recent study, we identified a hypometabolic midbrain cluster, which includes parts of the substantia nigra, as the best differentiating metabolic feature for PD-patients based on group comparison of [18F]-fluorodeoxyglucose ([18F]-FDG) PET scans. Longitudinal analyses confirmed progressive metabolic changes in this region and, an independent study showed great potential of nigral metabolism for diagnostic workup of parkinsonian syndromes. In this study, we applied a machine learning approach to evaluate midbrain metabolism measured by [18F]-FDG PET as a diagnostic marker for PD. In total, 51 mid-stage PD-patients and 16 healthy control subjects underwent high-resolution [18F]-FDG PET. Normalized tracer update values of the midbrain cluster identified by between-group comparison were extracted voxel-wise from individuals' scans. Extracted uptake values were subjected to a random forest feature classification algorithm. An adapted leave-one-out cross validation approach was applied for testing robustness of the model for differentiating between patients and controls. Performance of the model across all runs was evaluated by calculating sensitivity, specificity and model accuracy for the validation data set and the percentage of correctly categorized subjects for test data sets. The random forest feature classification of voxel-based uptake values from the midbrain cluster identified patients in the validation data set with an average sensitivity of 0.91 (Min: 0.82, Max: 0.94). For all 67 runs, in which each of the individuals was treated once as test data set, the test data set was correctly categorized by our model. The applied feature importance extraction consistently identified a subset of voxels within the midbrain cluster with highest importance across all runs which spatially converged with the left substantia nigra. Our data suggest midbrain metabolism measured by [18F]-FDG PET as a promising diagnostic imaging tool for PD. Given its close relationship to PD pathophysiology and very high discriminatory accuracy, this approach could help to objectify PD diagnosis and enable more accurate classification in relation to clinical trials, which could also be applicable to patients with prodromal disease.