Medical Image Analysis
Medical image analysis uses computational methods to extract meaningful information from medical images, primarily aiming to improve diagnosis, treatment planning, and disease understanding. Current research heavily emphasizes the development and application of deep learning models, including transformers, U-Nets, and novel architectures like Mamba, alongside techniques like self-explainable AI and efficient fine-tuning for improved accuracy, robustness, and explainability. This field is crucial for advancing healthcare, enabling faster and more accurate diagnoses, personalized treatment strategies, and ultimately improving patient outcomes.
Papers
EAFP-Med: An Efficient Adaptive Feature Processing Module Based on Prompts for Medical Image Detection
Xiang Li, Long Lan, Husam Lahza, Shaowu Yang, Shuihua Wang, Wenjing Yang, Hengzhu Liu, Yudong Zhang
Where to Begin? From Random to Foundation Model Instructed Initialization in Federated Learning for Medical Image Segmentation
Ming Li, Guang Yang