Abstract
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.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Kang Shen and Chao Tian
M4G.3 Asia Communications and Photonics Conference (ACP) 2021
Yair Rivenson, Yibo Zhang, Harun Günaydın, Da Teng, and Aydogan Ozcan
STh1J.3 CLEO: Science and Innovations (CLEO:S&I) 2018
Baurzhan Muminov, Altai Perry, Rakib Hyder, M. Salman Asif, and Luat T. Vuong
ITh5D.5 Imaging Systems and Applications (IS) 2021