Logo image
Back
Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising
Journal article   Open access   Peer reviewed

Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising

Fenglei Fan, Hongming Shan, Mannudeep K. Kalra, Ramandeep Singh, Guhan Qian, Matthew Getzin, Yueyang Teng, Juergen Hahn and Ge Wang
IEEE transactions on medical imaging, Vol.39(6), pp.2035-2050
06/01/2020
DOI: 10.1109/TMI.2019.2963248
PMCID: PMC7376975
PMID: 31902758
url
https://www.ncbi.nlm.nih.gov/pmc/articles/7376975View
Open Access

Abstract

Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of "quadratic-neuron-based deep learning". Our prior theoretical studies have shown important merits of quadratic neurons and networks in representation, efficiency, and interpretability. In this paper, we use quadratic neurons to construct an encoder-decoder structure, referred as the quadratic autoencoder, and apply it to low-dose CT denoising. The experimental results on the Mayo low-dose CT dataset demonstrate the utility and robustness of quadratic autoencoder in terms of image denoising and model efficiency. To our best knowledge, this is the first time that the deep learning approach is implemented with a new type of neurons and demonstrates a significant potential in the medical imaging field.
 autoencoder Complexity theory Computed tomography Deep learning Feature extraction Image reconstruction low-dose CT Neurons Noise reduction quadratic neurons

Details

Metrics

10 Record Views
112 Times Cited - Web of Science
Logo image