Format

Send to

Choose Destination
PLoS One. 2017 Dec 21;12(12):e0190069. doi: 10.1371/journal.pone.0190069. eCollection 2017.

Stacked competitive networks for noise reduction in low-dose CT.

Du W1,2, Chen H1,2, Wu Z1,2, Sun H3, Liao P4, Zhang Y1.

Author information

1
School of Computer Science, Sichuan University, Chengdu, China.
2
National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu, China.
3
Department of Radiology, West China Hospital of Sichuan University, Chengdu, China.
4
Department of Scientific Research and Education, The Sixth People's Hospital of Chengdu, Chengdu, China.

Abstract

Since absorption of X-ray radiation has the possibility of inducing cancerous, genetic and other diseases to patients, researches usually attempt to reduce the radiation dose. However, reduction of the radiation dose associated with CT scans will unavoidably increase the severity of noise and artifacts, which can seriously affect diagnostic confidence. Due to the outstanding performance of deep neural networks in image processing, in this paper, we proposed a Stacked Competitive Network (SCN) approach to noise reduction, which stacks several successive Competitive Blocks (CB). The carefully handcrafted design of the competitive blocks was inspired by the idea of multi-scale processing and improvement the network's capacity. Qualitative and quantitative evaluations demonstrate the competitive performance of the proposed method in noise suppression, structural preservation, and lesion detection.

PMID:
29267360
PMCID:
PMC5739486
DOI:
10.1371/journal.pone.0190069
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center