Abstract
Epileptic seizure classification based on seizure semiology requires automated, quantitative approaches to support the diagnosis of epilepsy, which affects 1 % of the world's population. Current approaches address the problem on a seizure level, neglecting the detailed evaluation of the classification of the underlying action features, also known as Movements of Interest (MOIs), which are critical for epileptologists in determining their classifications. Moreover, it hinders objective comparison of these approaches and attribution of performance differences due to datasets, intra-dataset MOI distribution, or architecture variations. Objective evaluation of action recognition techniques is crucial, with MOIs serving as foundational elements of semiology for clinical in-bed applications to facilitate epileptic seizure classification. However, until now, there were no MOI datasets available nor benchmarks comparing different action recognition approaches for this clinical problem. Therefore, as a pilot, we introduced a novel, simulated seizure semiology dataset carried out by 8 experienced epileptologists in an EMU bed, consisting of 7 MOI classes. We compare several computer vision methods for MOI classification, two image-based (I3D and Uniformerv2), and two skeleton-based (ST-GCN++ and PoseC3D) action recognition approaches. This study emphasizes the advantages of a 2-stage skeleton-based action recognition approach in a transfer learning setting (4 classes) and the multi-scale challenge of MOI classification (7 classes), advocating for the integration of skeleton-based methods with hand gesture recognition technologies in the future. The study's controlled MOI simulation dataset provides us with the opportunity to advance the development of automated epileptic seizure classification systems, paving the way for enhancing their performance and having the potential to contribute to improved patient care.

Abstract
Hypertension is the primary risk factor for cerebral small vessel disease (CSVD). However, its mechanistic links are yet to be completely understood. Advancements in diffusion-weighted magnetic resonance imaging (dMRI) increased sensitivity in detecting subtle white matter (WM) structural integrity changes. 44 hypertension patients without symptomatic CSVD underwent multi-modal evaluation of cerebral structure and function, including dMRI, neuropsychological tests and transcranial Doppler monitoring of the right middle cerebral artery (MCA) and left posterior cerebral artery (PCA) to assess neurovascular coupling (NVC). In the PCA, the modeled NVC curve was studied. We examined the cross-sectional relationship of WM integrity with NVC and cognitive performance, using correlational tractography. Diffusion measures from two dMRI models were used: fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity from diffusion tensor imaging, and quantitative anisotropy (QA) and isotropy from q-space diffeomorphic reconstruction. Regarding the NVC in the PCA, vascular elastic properties and initial response speed markers indicated better functional hyperemia with better WM integrity. However, the amplitude suggested increased NVC with worse WM integrity. In the MCA, increased NVC was associated with lower WM integrity. Better cognitive performance associated with preserved WM integrity. Increased functional hyperemia despite worse WM integrity may reflect less efficient NVC in hypertensive patients, potentially arising from (mal)adaptive mechanisms and brain network reorganization in response to CSVD. This observational study highlights the potential of transcranial Doppler and QA as susceptibility markers of pre-symptomatic CSVD.

Abstract

Abstract