We propose a Learned Primal-Dual algorithm for tomographic reconstruction. The algorithm includes the (possibly non-linear) forward operator in a deep neural network inspired by unrolled proximal primal-dual optimization methods, but where the proximal operators have been replaced with convolutional neural networks. The algorithm is trained end-to-end, working directly from raw measured data and does not depend on any initial reconstruction such as FBP. We present results in CT reconstruction, demonstrating >10dB improvements.
This is poster number 56 in Poster Session