A5057120068- Epilepsy research and treatment
- Artificial Intelligence in Healthcare and Education
- Radiomics and Machine Learning in Medical Imaging
- Brain Tumor Detection and Classification
- Action Observation and Synchronization
- Functional Brain Connectivity Studies
- Endoplasmic Reticulum Stress and Disease
- Neural and Behavioral Psychology Studies
- Fetal and Pediatric Neurological Disorders
- Mitochondrial Function and Pathology
- EEG and Brain-Computer Interfaces
- Neonatal and fetal brain pathology
- Medical Imaging and Analysis
- AI in cancer detection
- Lipid metabolism and biosynthesis
- Neural dynamics and brain function
University Hospital Bonn
2024-2025
University of Bonn
2020
Center for Research in Molecular Medicine and Chronic Diseases
2016
Universidade de Santiago de Compostela
2016
This study aims to report human performance in the detection of Focal Cortical Dysplasias (FCDs) using an openly available dataset. Additionally, it defines a subset this data as "difficult" test set establish public baseline benchmark against which new methods for automated FCD can be evaluated. The 28 readers with varying levels expertise detecting FCDs was originally analyzed 146 subjects (not all are available), we 85 cases. Performance measured based on overlap between predicted regions...
Objectives Artificial intelligence (AI) is thought to improve lesion detection. However, a lack of knowledge about human performance prevents comparative evaluation AI and an accurate assessment its impact on clinical decision-making. The objective this work quantitatively evaluate the ability humans detect focal cortical dysplasia (FCD), compare it state-of-the-art AI, determine how may aid diagnostics. Materials Methods We prospectively recorded readers in detecting FCDs using single...
Background: Artificial Intelligence (AI) has significantly improved diagnostic accuracy in many disorders. Advances have been most evident the classification of medical images. A correct diagnosis, however, often involves localising pathological tissue, which may be crucial for a targeted treatment. The output AI such tasks differs from human diagnosis clinical setting, and both are not natively comparable. Here, we aimed to create common ground between technical domains lay foundation AI's...
<title>Abstract</title> This study aims to report human performance in the detection of Focal Cortical Dysplasias (FCDs), localized regions malformed cerebral cortex, using a public dataset. Additionally, it defines subset this data as representative testset establish baseline benchmark for evaluation automatic FCD approaches. The 28 readers was analyzed 85 publicly available cases. Performance measured based on overlap between predicted interest (ROIs) and ground truth lesion masks. chosen...
PELD (Progressive Encephalopathy with or without Lipodystrophy Celia's Encephalopathy) is a fatal and rare neurodegenerative syndrome associated the BSCL2 mutation c.985C>T, that results in an aberrant transcript exon 7 (Celia seipin). The aim of this study was to evaluate both process cellular senescence effect unsaturated fatty acids on preadipocytes from homozygous c.985C>T patient. Also, role seipin isoform adipogenesis studied adipose-derived human mesenchymal stem cells.Cellular...
Confidence and uncertainty in our thoughts are extremely important when making decisions, but how does the brain compute confidence? We found a region closely associated with confidence. This sheds light on evaluates own actions.