A5083903227- Acute Ischemic Stroke Management
- Cerebrovascular and Carotid Artery Diseases
- Stroke Rehabilitation and Recovery
- Artificial Intelligence in Healthcare and Education
- Machine Learning in Healthcare
- Intracranial Aneurysms: Treatment and Complications
- Medical Image Segmentation Techniques
- Transcranial Magnetic Stimulation Studies
- Explainable Artificial Intelligence (XAI)
- Retinal Imaging and Analysis
- Traumatic Brain Injury and Neurovascular Disturbances
- Sepsis Diagnosis and Treatment
- Generative Adversarial Networks and Image Synthesis
- Moyamoya disease diagnosis and treatment
- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- Meningioma and schwannoma management
- Monoclonal and Polyclonal Antibodies Research
- Intracerebral and Subarachnoid Hemorrhage Research
- Traumatic Brain Injury Research
- Venous Thromboembolism Diagnosis and Management
- Medical Imaging and Analysis
- Advanced Neuroimaging Techniques and Applications
- Cardiac, Anesthesia and Surgical Outcomes
- MRI in cancer diagnosis
Charité - Universitätsmedizin Berlin
2015-2025
Humboldt-Universität zu Berlin
2023-2024
Freie Universität Berlin
2023-2024
Artificial Intelligence in Medicine (Canada)
2022
Weatherford College
2022
Berlin Institute of Health at Charité - Universitätsmedizin Berlin
2019
Institute for Transfusion Medicine
2007
Abstract Background Explainability is one of the most heavily debated topics when it comes to application artificial intelligence (AI) in healthcare. Even though AI-driven systems have been shown outperform humans certain analytical tasks, lack explainability continues spark criticism. Yet, not a purely technological issue, instead invokes host medical, legal, ethical, and societal questions that require thorough exploration. This paper provides comprehensive assessment role medical AI makes...
BACKGROUND: Transcranial magnetic stimulation (TMS) is the only noninvasive method for presurgical mapping of cortical function. Recent technical advancements have significantly increased focality and usability method. OBJECTIVE: To compare accuracy a 3-dimensional resonance imaging-navigated TMS system (nTMS) with gold standard direct (DCS). METHODS: The primary motor areas 20 patients rolandic tumors were mapped preoperatively nTMS at 110% individual resting threshold. Intraoperative DCS...
Brain vessel status is a promising biomarker for better prevention and treatment in cerebrovascular disease. However, classic rule-based segmentation algorithms need to be hand-crafted are insufficiently validated. A specialized deep learning method-the U-net-is alternative. Using labeled data from 66 patients with disease, the U-net framework was optimized evaluated three metrics: Dice coefficient, 95% Hausdorff distance (95HD) average (AVD). The model performance compared traditional...
State-of-the-art machine learning (ML) artificial intelligence methods are increasingly leveraged in clinical predictive modeling to provide decision support systems physicians. Modern ML approaches such as neural networks (ANNs) and tree boosting often perform better than more traditional like logistic regression. On the other hand, these modern yield a limited understanding of resulting predictions. However, medical domain, applied models is essential, particular, when informing support....
Abstract Average Hausdorff distance is a widely used performance measure to calculate the between two point sets. In medical image segmentation, it compare ground truth images with segmentations allowing their ranking. We identified, however, ranking errors of average making less suitable for applications in segmentation assessment. To mitigate this error, we present modified calculation that have coined “balanced distance”. simulate ranking, manually created non-overlapping common magnetic...
Artificial intelligence (AI) has the potential to transform clinical decision-making as we know it. Powered by sophisticated machine learning algorithms, decision support systems (CDSS) can generate unprecedented amounts of predictive information about individuals' health. Yet, despite these promote proactive and improve health outcomes, their utility impact remain poorly understood due still rare application in practice. Taking example AI-powered CDSS stroke medicine a case point, this...
Neurological and oncological outcomes of motor eloquent brain-tumor patients depend upon the ability to localize functional areas respective proposed therapy. We set out determine whether use navigated transcranial magnetic stimulation (nTMS) had an impact on treatment outcome in with brain tumors locations.We enrolled 250 consecutive compared their a matched pre-nTMS control group (n = 115).nTMS mapping results disproved suspected involvement primary cortex 25.1% cases, expanded surgical...
Neuroimaging and neuropsychological experiments suggest that modality-preferential cortices, including motor- somatosensory areas contribute to the semantic processing of action related concrete words. In contrast, a possible role – sensorimotor in abstract meaning remains under debate. However, recent fMRI studies indicate an involvement left cortex abstract-emotional words (e.g. "love"). But are these indeed necessary for action-related words? The current study now investigates word two...
Introduction: Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Non-invasive neuroimaging techniques, such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied clinical routine to depict arteries. They are, however, only visually assessed. Fully automated segmentation integrated into could facilitate time-critical diagnosis of abnormalities and might identification valuable biomarkers events. In...
To evaluate the transferability of deep learning (DL) models for early detection adverse events to previously unseen hospitals.
Deep learning requires large labeled datasets that are difficult to gather in medical imaging due data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used generate images with their corresponding labels, they cannot capture the volumetric information 3D imaging. more suitable for this volumes but not labels. One reason might be synthesizing is challenging...
Reliable prediction of outcomes aneurysmal subarachnoid hemorrhage (aSAH) based on factors available at patient admission may support responsible allocation resources as well treatment decisions. Radiographic and clinical scoring systems help clinicians estimate disease severity, but their predictive value is limited, especially in devising strategies. In this study, we aimed to examine whether a machine learning (ML) approach using variables improve outcome aSAH compared established...
Moyamoya disease is a rare steno-occlusive cerebrovascular disorder often resulting in hemorrhagic and ischemic strokes. Although sharing the same stimulus with atherosclerotic disease, characterized by highly instable system which prone to rupture due pathological neovascularization. To understand molecular mechanisms underlying this instability, angiopoietin-2 gene expression was analyzed middle cerebral artery lesions obtained from patients. Angiopoietin-2 significantly up-regulated...
Outcome prediction after mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) and large vessel occlusion (LVO) is commonly performed by focusing on favorable outcome (modified Rankin Scale, mRS 0-2) 3 months but poor representing severe disability mortality (mRS 5 6) might be of equal importance for clinical decision-making.We retrospectively analyzed AIS LVO undergoing MT from 2009 to 2018. Prognostic variables were grouped baseline (A), MRI-derived including mismatch...
Hematoma expansion occasionally occurs in patients with intracerebral hemorrhage (ICH), associating poor outcome. Multimodal neural networks incorporating convolutional network (CNN) analysis of images and tabular data are known to show promising results prediction classification tasks. We aimed develop a reliable multimodal model that comprehensively analyzes CT clinical variables predict hematoma expansion. retrospectively enrolled ICH at four hospitals between 2017 2021, assigning from...
Moyamoya disease (MMD) is a rare steno-occlusive cerebrovascular disorder. Mechanisms driving the formation of aberrant MMD vessels remain elusive. We collected serum and vessel specimens from atherosclerotic (ACVD) patients serving as controls due to same hypoxic stimulus but substantial differences in terms vascular features. Based on patient material an vitro model mimicking ACVD conditions, matrix metalloproteinase-9 (MMP-9) vascular-endothelial growth factor (VEGF) were tested for their...
This study asks whether lesions in different parts of the brain have effects on processing words typically used to refer objects with and without action affordances, for example tools animal-related nouns. A cohort neurological patients focal participated a lexical decision paradigm where nouns semantically related tools, foods animals were presented along matched pseudo-words. Differences semantic features between categories confirmed using extensive ratings whereas all word relevant...