Fast Voxel-Wise Kinetic Modeling in Dynamic PET using a Physics-Informed CycleGAN

arXiv — cs.CVTuesday, October 28, 2025 at 4:00:00 AM
A recent study introduces a physics-informed CycleGAN that enhances dynamic PET imaging by improving tracer kinetic modeling. This advancement simplifies the complex process of estimating arterial input functions, which is crucial for accurate diagnosis and treatment planning in oncology. The promising results show that the model can predict arterial input functions and generate parameter maps that closely match established references, potentially transforming how practitioners approach imaging and treatment.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting
PositiveArtificial Intelligence
The introduction of PETARSeg-11K, a large-scale dataset, and PETAR-4B, a 3D vision-language model, marks a significant advancement in automating report generation for 3D positron emission tomography (PET) and CT imaging. This initiative addresses the complexities of whole-body imaging and the scarcity of annotated datasets, aiming to enhance the accuracy and efficiency of radiological reporting.