Dose Map

Dose map prediction in radiotherapy aims to automate the creation of accurate 3D dose distributions, streamlining treatment planning and potentially improving treatment outcomes. Current research heavily utilizes deep learning, employing various architectures such as convolutional neural networks (CNNs), transformers, diffusion models, and graph neural networks, often incorporating attention mechanisms and multi-scale feature extraction to improve prediction accuracy and address issues like over-smoothing. These advancements leverage anatomical information and incorporate constraints to better predict dose in target volumes and organs at risk, ultimately aiming to reduce the time and expertise required for radiotherapy planning. The resulting improvements in efficiency and accuracy have significant implications for cancer treatment delivery.