X Ray Image
X-ray image analysis is a rapidly evolving field focused on improving the accuracy, efficiency, and accessibility of medical diagnoses and other applications using AI. Current research emphasizes developing robust deep learning models, including Vision Transformers and various convolutional neural networks (like YOLO and ResNet variants), often pre-trained on large datasets and fine-tuned for specific tasks such as disease detection, bone structure reconstruction, and report generation. These advancements aim to reduce diagnostic burdens, improve treatment planning, and enhance overall healthcare efficiency, particularly in resource-constrained settings. The use of synthetic data and techniques like domain adaptation are also actively explored to address data scarcity and variability across different imaging systems.
Papers
StyleX: A Trainable Metric for X-ray Style Distances
Dominik Eckert, Christopher Syben, Christian Hümmer, Ludwig Ritschl, Steffen Kappler, Sebastian Stober
Structural Entities Extraction and Patient Indications Incorporation for Chest X-ray Report Generation
Kang Liu, Zhuoqi Ma, Xiaolu Kang, Zhusi Zhong, Zhicheng Jiao, Grayson Baird, Harrison Bai, Qiguang Miao