Direct PET Image Reconstruction Incorporating Deep Image Prior and a Forward Projection Model
This work addresses a bottleneck in PET imaging for medical diagnostics by enabling unsupervised reconstruction, though it is incremental as it builds on existing deep learning frameworks.
The authors tackled the problem of requiring large training datasets for direct PET image reconstruction by proposing an unsupervised method that incorporates a deep image prior and a forward projection model, achieving superior quantitative and qualitative performance over FBP and ML-EM algorithms in brain PET simulations.
Convolutional neural networks (CNNs) have recently achieved remarkable performance in positron emission tomography (PET) image reconstruction. In particular, CNN-based direct PET image reconstruction, which directly generates the reconstructed image from the sinogram, has potential applicability to PET image enhancements because it does not require image reconstruction algorithms, which often produce some artifacts. However, these deep learning-based, direct PET image reconstruction algorithms have the disadvantage that they require a large number of high-quality training datasets. In this study, we propose an unsupervised direct PET image reconstruction method that incorporates a deep image prior framework. Our proposed method incorporates a forward projection model with a loss function to achieve unsupervised direct PET image reconstruction from sinograms. To compare our proposed direct reconstruction method with the filtered back projection (FBP) and maximum likelihood expectation maximization (ML-EM) algorithms, we evaluated using Monte Carlo simulation data of brain [$^{18}$F]FDG PET scans. The results demonstrate that our proposed direct reconstruction quantitatively and qualitatively outperforms the FBP and ML-EM algorithms with respect to peak signal-to-noise ratio and structural similarity index.