Latest AI and machine learning research in strokes for healthcare professionals.
Vision-language models (VLMs) are increasingly used in settings where sensitivity to low-level image degradations matters, including content moderation, image restoration, and quality monitoring. Yet their ability to recognize distortion type and severity remains poorly understood. We present DistortBench, a diagnostic benchmark for no-reference distortion perception in VLMs. DistortBench contains...
Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objectives such as model stealing or adversarial fine-tuning, while transferable attacks from natural images introduce visible distortions that clinicians can easily detect. To address ...
Stroke-associated pneumonia (SAP) is a common, severe complication in acute ischemic stroke (AIS) patients receiving bridging therapy (intravenous thr...
The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning...
In stroke-based rendering, search methods often get trapped in local minima due to discrete stroke placement, while differentiable optimizers lack str...
This work introduces a new approach to automatic oil painting that emphasizes the creation of dynamic and expressive brushstrokes. A pivotal challenge...
Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia worldwide and is strongly associated with increased risks of stroke, heart failure, ...
Background: The 2017 American College of Cardiology/American Heart Association (ACC/AHA) guideline lowered diagnostic threshold for hypertension, enco...
Cells that appear transcriptionally identical can maintain vastly different functions or fate, an enduring blind spot in single-cell transcriptomics. ...
Background: Current risk assessment tools for guiding direct oral anticoagulant (DOAC) therapy for patients with atrial fibrillation (AF) based on cli...
Accurate sleep staging is essential for diagnosing OSA and hypopnea in stroke patients. Although PSG is reliable, it is costly, labor-intensive, and m...
Sleep disturbances lead to risk for cardiovascular (CV), metabolic, and neurological diseases. While in-lab polysomnography (PSG) is the gold standard...
Retinal fundus imaging enables low-cost and scalable hypertension (HTN) screening, but HTN-related retinal cues are subtle, yielding high-variance pre...
Background: Prospective stroke registries have advanced our understanding of cerebrovascular disease, yet most reduce neuroimaging to categorical vari...
Stroke is a leading cause of mortality and morbidity worldwide. MRI-visible perivascular spaces (PVS) are an emerging marker of cerebral small vessel ...
Background Hemorrhagic transformation (HT) after endovascular thrombectomy (EVT) is a principal determinant of clinical outcome. Artificial intelligen...
Early identification of individuals at risk of stroke remains a major clinical challenge, as prodromal motor im- pairments are often subtle and transi...
Purpose: To develop a data-efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables fa...
Chronic diseases are long-lasting conditions that require lifelong medical attention. Using big EMR data, we have developed early disease risk predict...
Introduction Postoperative complications after major surgery have substantial impacts on morbidity and resource utilisation. We investigated whether a...