Researchers have developed a novel feed-forward neural network designed to improve inter-crystal scatter (ICS) event recovery in ultra-high resolution positron emission tomography (UHR-PET) imaging. This method aims to address the challenge of ICS events, which typically lead to reduced sensitivity or degraded image resolution in UHR-PET systems. The new approach was validated using both simulations and experimental data from the LabPET-II system, demonstrating a significant increase in sensitivity while maintaining sub-millimeter spatial resolution. AI
IMPACT This AI-driven approach could lead to more sensitive PET scans with lower radiation doses and reduced scan times.
RANK_REASON The cluster contains a research paper detailing a new machine learning method for improving PET imaging. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
