Chest Radiograph
Chest radiographs (CXRs) are fundamental in diagnosing thoracic diseases, and research focuses on improving their analysis through artificial intelligence. Current efforts utilize large language models (LLMs) and vision transformers (ViTs), often incorporating multimodal learning to integrate image data with clinical reports and patient history, aiming for improved diagnostic accuracy and explainability. These advancements, including the development of novel architectures and training strategies like instruction tuning and contrastive learning, hold significant promise for assisting radiologists, enhancing diagnostic consistency, and potentially improving patient outcomes.
Papers
Fast-staged CNN Model for Accurate pulmonary diseases and Lung cancer detection
Abdelbaki Souid, Mohamed Hamroun, Soufiene Ben Othman, Hedi Sakli, Naceur Abdelkarim
Multilabel Classification for Lung Disease Detection: Integrating Deep Learning and Natural Language Processing
Maria Efimovich, Jayden Lim, Vedant Mehta, Ethan Poon
MedPromptX: Grounded Multimodal Prompting for Chest X-ray Diagnosis
Mai A. Shaaban, Adnan Khan, Mohammad Yaqub
Evaluating GPT-4 with Vision on Detection of Radiological Findings on Chest Radiographs
Yiliang Zhou, Hanley Ong, Patrick Kennedy, Carol Wu, Jacob Kazam, Keith Hentel, Adam Flanders, George Shih, Yifan Peng