Chest X Ray
Chest X-ray (CXR) analysis is a crucial diagnostic tool in healthcare, with research focusing on improving accuracy, efficiency, and accessibility of interpretation. Current efforts center on developing and refining deep learning models, including convolutional neural networks (CNNs) and vision transformers (ViTs), often incorporating techniques like transfer learning, self-supervised learning, and multi-modal approaches that integrate textual reports and other patient data. These advancements aim to automate report generation, improve disease detection (including in under-resourced settings), and enhance the overall quality and speed of radiological diagnosis, ultimately impacting patient care and clinical workflow.
Papers
SLaVA-CXR: Small Language and Vision Assistant for Chest X-ray Report Automation
Jinge Wu, Yunsoo Kim, Daqian Shi, David Cliffton, Fenglin Liu, Honghan Wu
Utility of Multimodal Large Language Models in Analyzing Chest X-ray with Incomplete Contextual Information
Choonghan Kim, Seonhee Cho, Joo Heung Yoon