
Proceedings Paper
Hierarchical convolutional network for sparse-view X-ray CT reconstructionFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
We present a hierarchical imaging reconstruction algorithm for a 3D phase tomography based on the densely extracted features on a multi-band pyramid of convolutional network. By implementing a layer-wise hierarchical machine learning network and combine different bands of information for the imaging retrieval, a more efficient and adaptive learning strategy is established to enable an accurate reconstruction with fewer training data and improved accuracy. In addition, the distinction of intensity and spectral bands in the feature training process enables bias correction for reconstruction under varied conditions. In particular, we demonstrate a robust imaging reconstruction for a sparse-view phase tomography application, where spectrally biased phase diffraction and intensity-biased photon noise are both successfully corrected for.
Paper Details
Date Published: 13 May 2019
PDF: 6 pages
Proc. SPIE 10990, Computational Imaging IV, 109900V (13 May 2019); doi: 10.1117/12.2521239
Published in SPIE Proceedings Vol. 10990:
Computational Imaging IV
Abhijit Mahalanobis; Lei Tian; Jonathan C. Petruccelli, Editor(s)
PDF: 6 pages
Proc. SPIE 10990, Computational Imaging IV, 109900V (13 May 2019); doi: 10.1117/12.2521239
Show Author Affiliations
Ziling Wu, Virginia Polytechnic Institute and State Univ. (United States)
Ting Yang, Virginia Polytechnic Institute and State Univ. (United States)
Ting Yang, Virginia Polytechnic Institute and State Univ. (United States)
Ling Li, Virginia Polytechnic Institute and State Univ. (United States)
Yunhui Zhu, Virginia Polytechnic Institute and State Univ. (United States)
Yunhui Zhu, Virginia Polytechnic Institute and State Univ. (United States)
Published in SPIE Proceedings Vol. 10990:
Computational Imaging IV
Abhijit Mahalanobis; Lei Tian; Jonathan C. Petruccelli, Editor(s)
© SPIE. Terms of Use
