Deep Learning for PET Imaging: from Denoising to Learned Primal-Dual Reconstruction

One of the main issues of PET imaging is the high level of noise that characterizes the reconstructed image. During this project we implemented several algorithms with the aim of improving the reconstruction of PET images exploiting the power of Neural Networks. We developed a simple Denoiser, then two Neural Network based iterative reconstruction algorithms and finally, we used the most promising approach to reconstruct images from data acquired with the KTH MTH microCT - miniPET.