PC-UNet: An Enforcing Poisson Statistics U-Net for Positron Emission Tomography Denoising
This work addresses noise reduction in medical imaging for PET scans, potentially enabling lower radiation doses, but it appears incremental as it builds on U-Net with a specialized loss function.
The paper tackled the problem of Poisson noise in low-dose Positron Emission Tomography (PET) denoising, which current methods fail to handle, and proposed a Poisson Consistent U-Net (PC-UNet) with a new loss function, resulting in improved physical consistency and image fidelity in tests on PET datasets.
Positron Emission Tomography (PET) is crucial in medicine, but its clinical use is limited due to high signal-to-noise ratio doses increasing radiation exposure. Lowering doses increases Poisson noise, which current denoising methods fail to handle, causing distortions and artifacts. We propose a Poisson Consistent U-Net (PC-UNet) model with a new Poisson Variance and Mean Consistency Loss (PVMC-Loss) that incorporates physical data to improve image fidelity. PVMC-Loss is statistically unbiased in variance and gradient adaptation, acting as a Generalized Method of Moments implementation, offering robustness to minor data mismatches. Tests on PET datasets show PC-UNet improves physical consistency and image fidelity, proving its ability to integrate physical information effectively.