We improve image reconstruction from sparse data in photoacoustic tomography using a deep convolutional network. The weights of the convolutional network are adjusted prior to the actual image reconstruction through training with pairs of reconstructions including artifacts and the corresponding artifact-free images. We demonstrate with simulated and experimental data that the proposed approach provides reconstructed images with a quality comparable to state of the art approaches and reduced numerical costs.
This presentation is part of Minisymposium “MS65 - Machine learning techniques for image reconstruction (2 parts)”
organized by: Markus Haltmeier (University Innsbruck) , Linh Nguyen (University of Idaho) .