Latest AI and machine learning research in neurosurgery for healthcare professionals.
Endovascular aneurysm repair has been associated with changes in arterial stiffness, as estimated by pulse wave velocity (PWV). This marker is influenced by the medical status of the patient, the elastic characteristics of the aneurysm wall, and the presence of intraluminal thrombus. Therefore, in order to delineate the influence of the endograft implantation in the early post-operative period, we...
OBJECTIVE Providing a reliable assessment of language lateralization is an important task to be performed prior to neurosurgery in patients with epilepsy. Over the last decade, functional MRI (fMRI) has emerged as a useful noninvasive tool for language lateralization, supplementing or replacing traditional invasive methods. In standard practice, fMRI-based language lateralization is assessed quali...
Shape memory polymer (SMP) foams were synthesized with three different nanoparticles (tungsten, silicon dioxide, and aluminum oxide) for embolization ...
We report an autopsy case of hemopericardium caused by rupture of a ventricular aneurysm associated with acute myocarditis in an infant boy aged 2 yea...
BACKGROUND: Lifelong surveillance after endovascular repair (EVAR) of abdominal aortic aneurysms (AAA) is considered mandatory to detect potentially l...
OBJECTIVE: Ruptured abdominal aortic aneurysm (rAAA) carries a high mortality rate, even with prompt transfer to a medical center. An artificial neura...
Study Design Case report. Objective To report the first case of ligamentum flavum hematoma after cervical spine instrumentation 11 years after the ind...
The goal of this cadaver study was to evaluate the feasibility and safety of da Vinci robot-assisted keyhole neurosurgery. Several keyhole craniotomie...
OBJECTIVE: This study reviewed the current developments in manual tracking and robotic navigation technologies for application in endovascular aortic ...
We present a novel design of an intelligent robotic hospital bed, named Flexbed, with autonomous navigation ability. The robotic bed is developed for ...
Artificial neural networks (ANNs) effectively analyze non-linear data sets. The aimed was A review of the relevant published articles that focused on ...
Objectives: To develop and externally validate a wall-focused deep learning framework for identifying composite unstable intracranial aneurysm phenoty...
Clinically actionable, patient-specific hemodynamic assessment, specifically wall shear stress, vortex structure and pressure distributions, is critic...
I present a training-free low-light enhancement method that combines local bright-channel illumination estimation, Retinex division, and edge-preservi...
Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods res...
Federated learning enables multiple institutions to train shared models without exchanging raw clinical EEG data, but it does not fully prevent privac...
Hyperspectral intrinsic decomposition (HID) aims to disentangle material-related spectral properties and photometric effects in hyperspectral images (...
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward eff...
Minimally invasive endovascular procedures offer reduced surgical trauma, shorter recovery times, and improved outcomes, but rely on 2D fluoroscopic X...
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systemat...