Loading [a11y]/accessibility-menu.js
Convolutional analysis operator learning: Application to sparse-view CT : (Invited Paper) | IEEE Conference Publication | IEEE Xplore

Convolutional analysis operator learning: Application to sparse-view CT : (Invited Paper)


Abstract:

Convolutional analysis operator learning (CAOL) methods train an autoencoding convolutional neural network (CNN) in an unsupervised learning manner, to more accurately so...Show More

Abstract:

Convolutional analysis operator learning (CAOL) methods train an autoencoding convolutional neural network (CNN) in an unsupervised learning manner, to more accurately solve inverse problems. Block Proximal Gradient method using a Majorizer (BPG-M) achieved fast and convergent CAOL, by using sharp majorizers and the momentum terms. This paper proposes a model-based image reconstruction (MBIR) method using autoencoding CNNs trained via CAOL, for sparse-view computational tomography (CT). We apply BPG-M to rapidly and stably solve the corresponding block multi-nonconvex optimization problem. Numerical experiments show that, for sparse-view CT, 1) the proposed MBIR method outperforms the standard MBIR method using edge-preserving regularization; 2) larger parameter dimensions of autoencoding CNNs improve reconstruction accuracy of the proposed MBIR method; and 3) when using BPG-M, sharper majorization is more critical for accelerating its convergence than giving more weights on extrapolation.
Date of Conference: 28-31 October 2018
Date Added to IEEE Xplore: 21 February 2019
ISBN Information:

ISSN Information:

Conference Location: Pacific Grove, CA, USA

References

References is not available for this document.