AirNet-SNL: End-to-End Training of Iterative Reconstruction and Deep Neural Network Regularization for Sparse-Data XPCI CT

Autor: Edward S. Jimenez, Collin J. C. Epstein, Dennis J. Lee, Derek West, Ryan N. Goodner, John Mulcahy-Stanislawczyk
Rok vydání: 2021
Předmět:
Zdroj: OSA Imaging and Applied Optics Congress 2021 (3D, COSI, DH, ISA, pcAOP).
DOI: 10.1364/dh.2021.df4f.2
Popis: We present a deep learning image reconstruction method called AirNet-SNL for sparse view computed tomography. It combines iterative reconstruction and convolutional neural networks with end-to-end training. Our model reduces streak artifacts from filtered back-projection with limited data, and it trains on randomly generated shapes. This work shows promise to generalize learning image reconstruction.
Databáze: OpenAIRE