Latest AI and machine learning research in strokes for healthcare professionals.
Non-valvular atrial fibrillation (AF) is associated with a five-fold increased risk of stroke, mainly due to impaired contractility of the left atrium (LA) leading to blood stasis and subsequent thrombus formation within the left atrial appendage (LAA). Current AF stroke risk stratification schemes, such as the CHA2DS2-VASc/ CHA2DS2-VA score, use comorbidities and do not capture mechanistic factor...
Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Although deep learning methods have improved binarization performance, most existing approaches rely on convolutional, transformer-based, or generative architectures, while Mamba-based state space models remain largely unexplored for this task. In this wor...
Poly(ethylene terephthalate) (PET), a ubiquitous polyester used in packaging and textiles, persists in the environment due to its high crystallinity a...
Recent generative models have largely closed the gap on low-level artifacts - pixel fingerprints, frequency anomalies, upsampling traces - particularl...
Background: Stroke is a time-sensitive neurological emergency in which early EMS activation and presentation to definitive care are cornerstones of ef...
Approximately 30-40% of stroke patients retain aphasia at 12 months. Early forecasting may guide rehabilitation and prognostic enrichment of clinical ...
Deep learning and multi-modal fusion have demonstrated transformative potential in medical diagnosis by integrating diverse data sources. However, acc...
Carotid atherosclerosis is a major contributor to ischemic stroke and transient ischemic attack. Conventional ultrasound assessment is commonly based ...
Computational models are a linchpin in our understanding of the neurocognitive basis of reading. These models can simulate idealized profiles of alexi...
Stroke starts as a focal vascular lesion, but its structural consequences often extend beyond the lesion site, resulting in distributed brain atrophy ...
Motor imagery electroencephalography (MI-EEG) decoding offers a non-invasive route for post-stroke rehabilitation, but cross-patient use remains diffi...
Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among ...
Single-cell foundation models (scFMs) have shown promise as transferable representations of cellular state, but recent zero-shot evaluations suggest t...
Antiphospholipid syndrome (APS) lacks targeted therapies beyond anticoagulation, and its molecular heterogeneity remains poorly characterized. We empl...
Background Polycyclic aromatic hydrocarbons (PAHs) and volatile organic compounds (VOCs) are combustion-derived pollutants linked to cardiovascular di...
Introduction Despite the proven benefits of reperfusion therapies in acute ischemic stroke, treatment decisions in the hyperacute phase remain complex...
Background Outcome after stroke varies according to stroke subtype by location, but healthcare systems data studies do not include subtyping informati...
Background: Chronic conditions such as hypertension can significantly disrupt daily life and emotional wellbeing. The interaction between patients' pe...
Background: Current medical large language model (LLM) evaluations largely rely on small collections of cases, whereas rigorous safety testing require...
Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retrainin...