Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classification

RB Lanfredi, P Mukherjee, R Summers - arXiv preprint arXiv:2403.04024, 2024 - arxiv.org
In chest X-ray (CXR) image analysis, rule-based systems are usually employed to extract
labels from reports, but concerns exist about label quality. These datasets typically offer only …

More Than Positive and Negative: Communicating Fine Granularity in Medical Diagnosis

X Peng, K Wang, J Yang, Y Zhu, Y You - arXiv preprint arXiv:2408.02214, 2024 - arxiv.org
With the advance of deep learning, much progress has been made in building powerful
artificial intelligence (AI) systems for automatic Chest X-ray (CXR) analysis. Most existing AI …