FDG Pet

FDG PET, a medical imaging technique using a radioactive glucose analog to detect metabolically active tissues, is crucial for cancer diagnosis and monitoring. Current research focuses on improving automated lesion segmentation and quantification using deep learning models, particularly 3D convolutional neural networks (like UNet and its variants) and diffusion models, often incorporating both PET and CT data for enhanced accuracy. These advancements aim to reduce the need for time-consuming manual analysis, improve diagnostic precision, and ultimately facilitate more effective cancer treatment planning and response assessment.