Dose Prediction

Dose prediction, the automated estimation of radiation or therapeutic agent distribution, aims to optimize treatment efficacy and minimize adverse effects in various medical applications, primarily radiotherapy. Current research heavily utilizes deep learning, employing architectures like transformers, convolutional neural networks (CNNs), and diffusion models, often incorporating anatomical information and incorporating uncertainty quantification techniques like risk-controlling prediction sets. These advancements offer the potential to accelerate treatment planning, improve treatment precision, and enhance patient safety by providing more accurate and reliable dose estimations.