Emulating Low-Dose PCCT Image Pairs With Independent Noise for Self-Supervised Spectral Image Denoising
- 28 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (1) , 530-542
Abstract
Photon counting CT (PCCT) acquires spectral measurements and enables generation of material decomposition (MD) images that provide distinct advantages in various clinical situations. However, noise amplification is observed in MD images, and denoising is typically applied. Clean or high-quality references are rare in clinical scans, often making supervised learning (Noise2Clean) impractical. Noise2Noise is a self-supervised counterpart, using noisy images and corresponding noisy references with zero-mean, independent noise. PCCT counts transmitted photons separately, and raw measurements are assumed to follow a Poisson distribution in each energy bin, providing the possibility to create noise-independent pairs. The approach is to use binomial selection to split the counts into two low-dose scans with independent noise. We prove that the reconstructed spectral images inherit the noise independence from counts domain through noise propagation analysis and also validated it in numerical simulation and experimental phantom scans. The method offers the flexibility to split measurements into desired dose levels while ensuring the reconstructed images share identical underlying features, thereby strengthening the model’s robustness for input dose levels and capability of preserving fine details. In both numerical simulation and experimental phantom scans, we demonstrated that Noise2Noise with binomial selection outperforms other common self-supervised learning methods based on different presumptive conditions.Keywords
Funding Information
- GE Healthcare
This publication has 52 references indexed in Scilit:
- Initial Clinical Images From a Second-Generation Prototype Silicon-Based Photon-Counting Computed Tomography SystemAcademic Radiology, 2023
- Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation2023
- Estimating the accuracy of dual energy chest radiography for coronary calcium detection with lateral or anteroposterior orientationsMedical Physics, 2022
- Modified nnU-Net for the MICCAI KiTS21 Challenge2022
- Low‐dose CT reconstruction with Noise2Noise network and testing‐time fine‐tuningMedical Physics, 2021
- Self-supervised PET DenoisingNuclear Medicine and Molecular Imaging, 2020
- Comparison of Low Dose Performance of Photon-Counting and Energy Integrating CTAcademic Radiology, 2020
- Consensus Neural Network for Medical Imaging Denoising with Only Noisy Training Samples2019
- Liver virtual non-enhanced CT with dual-source, dual-energy CT: a preliminary studyEuropean Radiology, 2010
- Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal priorComputerized Medical Imaging and Graphics, 2009