Skip to main content
EJNMMI Physics
Fig. 4 | EJNMMI Physics

Fig. 4

From: Combining deep learning with a kinetic model to predict dynamic PET images and generate parametric images

Fig. 4

Examples of generated dynamic PET images obtained from different planes (the transverse plane, coronal plane and sagittal plane). The ground truths are the last frames of the dynamic PET images, which were obtained 1 h after injection with a 5-min scanning time. The images in the upper-right corner were obtained by our proposed network with the kinetic model, and the images on the bottom were generated by the same network without the kinetic model

Back to article page