Multi Organ
Multi-organ research focuses on developing methods for simultaneously analyzing and treating multiple interconnected organ systems, addressing the limitations of single-organ approaches. Current research heavily utilizes deep learning, particularly transformer and U-Net architectures, with advancements in self-supervised and semi-supervised learning to overcome data scarcity challenges in medical image segmentation and analysis. These efforts aim to improve diagnostic accuracy, treatment planning, and ultimately patient outcomes across various medical applications, including radiotherapy and surgical planning. The development of large, multi-organ datasets and novel evaluation metrics are also key areas of focus.
Papers
Organ localisation using supervised and semi supervised approaches combining reinforcement learning with imitation learning
Sankaran Iyer, Alan Blair, Laughlin Dawes, Daniel Moses, Christopher White, Arcot Sowmya
Separated Contrastive Learning for Organ-at-Risk and Gross-Tumor-Volume Segmentation with Limited Annotation
Jiacheng Wang, Xiaomeng Li, Yiming Han, Jing Qin, Liansheng Wang, Zhou Qichao