Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization

• Published in: IEEE Nuclear Science Symposium conference record (1997) Vol. 2024; p. 1
• Main Authors: Liu, X., Marin, T., Eslahi, S. Vafay, Tiss, A., Chemli, Y., Johson, K. A., Fakhri, G. El, Ouyang, J.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.10.2024
• Subjects: Feature extraction; Microwave integrated circuits; Noise; Noise reduction; Semiconductor detectors; Three-dimensional displays; Training

Recent advances in deep learning (DL) have greatly improved the performance of positron emission tomography (PET) denoising performance. However, DL model performance can vary a lot across subjects, due to the large variability of the count levels and spatial distributions. A generalizable DL model...