Share Email Print
cover

Proceedings Paper • new

Quadratic neural networks for CT metal artifact reduction
Author(s): Fenglei Fan; Hongming Shan; Lars Gjesteby; Ge Wang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Recently, deep learning has become the mainstream method in multiple fields of artificial intelligence / machine learning (AI/ML) applications, including medical imaging. Encouraged by the neural diversity in the human body, our group proposed to replace the inner product in the current artificial neuron with a quadratic operation on inputs (called quadratic neuron) for deep learning. Since the representation capability at the cellular level is enhanced by the quadratic neuron, we are motivated to build network architectures and evaluate the potential of quadratic neurons towards “quadratic deep learning”. Along this direction, our previous theoretical studies have shown advantages of quadratic neurons and quadratic networks in terms of efficiency and representation. In this paper, we prototype a quadratic residual neural network (Q-ResNet) by incorporating quadratic neurons into a convolutional residual structure, and then deploy it for CT metal artifact reduction. Also, we report our experiments on a simulated dataset to show that Q-ResNet performs better than the classic NMAR algorithm.

Paper Details

Date Published: 11 September 2019
PDF: 7 pages
Proc. SPIE 11113, Developments in X-Ray Tomography XII, 111130W (11 September 2019); doi: 10.1117/12.2530363
Show Author Affiliations
Fenglei Fan, Rensselaer Polytechnic Institute (United States)
Hongming Shan, Rensselaer Polytechnic Institute (United States)
Lars Gjesteby, Rensselaer Polytechnic Institute (United States)
Ge Wang, Rensselaer Polytechnic Institute (United States)


Published in SPIE Proceedings Vol. 11113:
Developments in X-Ray Tomography XII
Bert Müller; Ge Wang, Editor(s)

© SPIE. Terms of Use
Back to Top