Add to BibSonomyAbstract
We present a novel multi-stage algorithm for CBCT reconstruction from very limited projections. Our proposed method uses 3D patch-based supervised and adversarial learning from scarce training data, combined with physics (forward) models and statistical priors.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
AirNet-SNL: End-to-End Training of Iterative Reconstruction and Deep Neural Network Regularization for Sparse-Data XPCI CT
Dennis J. Lee, John Mulcahy-Stanislawczyk, Edward Jimenez, Derek West, Ryan Goodner, and Collin Epstein
DF4F.2 Digital Holography and Three-Dimensional Imaging (DH) 2021
Patient-specific 3D CT Images Reconstruction from 2D KV images via Vision Transformer-based Deep-Learning
Yuzhen Ding, Jason Holmes, Baoxin Li, Carlos E. Vargas, Sujay A. Vora, William W. Wong, Mirek Fatyga, Robert L. Foote, Samir H. Patel, and Wei Liu
HTu2D.2 Digital Holography and Three-Dimensional Imaging (DH) 2023
Optics-Free Imaging Using A Self-Consistent Supervised Deep Neural Network
Soren Nelson and Rajesh Menon
JTu5A.3 Applied Industrial Spectroscopy (AIS) 2021