Neural KEM: A Kernel Method with Deep Coefficient Prior for PET Image Reconstruction.
Siqi LiKuang GongRamsey D. BadawiEdward J. KimJinyi QiGuobao WangPublished in: CoRR (2022)
Keyphrases
- image reconstruction
- kernel methods
- maximum a posteriori
- image reconstruction algorithms
- kernel function
- emission computed tomography
- super resolution
- support vector
- positron emission tomography
- support vector machine
- machine learning
- compressed sensing
- feature space
- kernel matrix
- reconstruction method
- reproducing kernel hilbert space
- poisson noise
- emission tomography
- random projections
- sparsely sampled
- limited angle
- prior information
- high quality