Medical Imaging
Medical imaging research focuses on developing and improving AI-powered methods for analyzing medical images, primarily aiming to enhance diagnostic accuracy, efficiency, and accessibility. Current research emphasizes robust model architectures (like Vision Transformers and UNets) and algorithms (including federated learning, generative adversarial networks, and diffusion models) to address challenges such as data scarcity, domain shifts (e.g., scanner variations), and privacy concerns. These advancements hold significant potential for improving clinical decision-making, particularly in areas with limited radiologist access, and for facilitating more efficient and reliable medical diagnoses.
Papers
Federated Alternate Training (FAT): Leveraging Unannotated Data Silos in Federated Segmentation for Medical Imaging
Erum Mushtaq, Yavuz Faruk Bakman, Jie Ding, Salman Avestimehr
Generative models improve fairness of medical classifiers under distribution shifts
Ira Ktena, Olivia Wiles, Isabela Albuquerque, Sylvestre-Alvise Rebuffi, Ryutaro Tanno, Abhijit Guha Roy, Shekoofeh Azizi, Danielle Belgrave, Pushmeet Kohli, Alan Karthikesalingam, Taylan Cemgil, Sven Gowal
Towards Evaluating Explanations of Vision Transformers for Medical Imaging
Piotr Komorowski, Hubert Baniecki, Przemysław Biecek
Automated computed tomography and magnetic resonance imaging segmentation using deep learning: a beginner's guide
Diedre Carmo, Gustavo Pinheiro, Lívia Rodrigues, Thays Abreu, Roberto Lotufo, Letícia Rittner