使

Patrick Wienholt1,2, Sophie Caselitz3,4, Robert Siepmann3,4

  • 1Lab for Artificial Intelligence in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. pwienholt@ukaachen.de.

European radiology
|February 20, 2026
PubMed
概括

离散语义 (DSE) 能够有效地检测视觉语言模型 (VLMs) 容易产生幻觉的问题. 这种方法显著提高了放射图像分析的准确性,提高了临床应用的VLM可靠性.