A computationally efficient reconstruction algorithm for circular cone-beam computed tomography using shallow neural networks

no code implementations • 1 Oct 2020 • Marinus J. Lagerwerf, Daniel M. Pelt, Willem Jan Palenstijn, K. Joost Batenburg

Moreover, we show that the training time of an NN-FDK network is orders of magnitude lower than the considered deep neural networks, with only a slight reduction in reconstruction accuracy.

Computational Efficiency Computed Tomography (CT)

Noise2Filter: fast, self-supervised learning and real-time reconstruction for 3D Computed Tomography

no code implementations • 3 Jul 2020 • Marinus J. Lagerwerf, Allard A. Hendriksen, Jan-Willem Buurlage, K. Joost Batenburg

To overcome this issue, we propose Noise2Filter, a learned filter method that can be trained using only the measured data, and does not require any additional training data.

3D Reconstruction Self-Supervised Learning