Macq, BenoîtCerra, MicheleMicheleCerra2025-02-042025-02-042023https://dial-mem.test.bib.ucl.ac.be/handle/123456789/35955Objective: Vagus Nerve Stimulation (VNS) offers treatment for drug-resistant epilepsy, but the mechanism underlying its efficacy remains unclear. This study aimed to uncover microstructural features in VNS responders and non-responders using diffusion magnetic resonance imaging (dMRI), diffusion models and machine learning techniques. Methods: Data were collected from 19 patients with drug-resistant epilepsy. Diffusion tensor imaging and other multi-compartment models (NODDI, DIAMOND and Microstructure Fingerprinting) were used to compute microstructural metrics within distinct regions of interest (ROIs) outlined on tractography pathways estimated using FreeSurfer and MRtrix3. We calculated the weighted mean, standard deviation, skewness, and kurtosis of the metrics along the tracts for summarising their distribution. Univariate analysis has been performed through non-parametric statistical tests: Mann-Whitney U rank, Kruskal-Wallis and Barnard exact tests. Multivariate analysis has been performed by a sequential feature selector on a trained logistic regression to select the best classifying set of microstructural metrics. Results: Treatment non-responders demonstrated a greater mean diffusivity (MD) in the thalamocortical connections, the fornix, and the anterior commissure (p < 0.01), as well as the feature selector, selected the fornix, anterior commissure and the middle cerebellar peduncle as best classifying features. The classifier trained with these results demonstrated 83.5% accuracy (AUX=1, F1-score=0.857), estimated through a cross-validation stratified shuffle split. Interpretation: Further studies are needed to fully understand the roles of the corpus callosum, anterior commissure and longitudinal fasciculus in mediating the effect of VNS. Our results emphasize the potential of microstructural connections and machine learning to guide personalized VNS treatment adjustments, improving patient outcomes.VNSEpilepsyDTINODDIDIAMONDMicrostructure fingerprintingTractographyMachine learningMRIDiffusiontext::thesis::master thesisthesis:42160