Tags

Type your tag names separated by a space and hit enter

Low-dose CT via convolutional neural network.
Biomed Opt Express 2017; 8(2):679-694BO

Abstract

In order to reduce the potential radiation risk, low-dose CT has attracted an increasing attention. However, simply lowering the radiation dose will significantly degrade the image quality. In this paper, we propose a new noise reduction method for low-dose CT via deep learning without accessing original projection data. A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion. Qualitative results demonstrate a great potential of the proposed method on artifact reduction and structure preservation. In terms of the quantitative metrics, the proposed method has showed a substantial improvement on PSNR, RMSE and SSIM than the competing state-of-art methods. Furthermore, the speed of our method is one order of magnitude faster than the iterative reconstruction and patch-based image denoising methods.

Authors+Show Affiliations

College of Computer Science, Sichuan University, Chengdu 610065, China; National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China.College of Computer Science, Sichuan University, Chengdu 610065, China.College of Computer Science, Sichuan University, Chengdu 610065, China.Department of Scientific Research and Education, The Sixth People's Hospital of Chengdu, Chengdu 610065, China.College of Computer Science, Sichuan University, Chengdu 610065, China; National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China.College of Computer Science, Sichuan University, Chengdu 610065, China.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USA.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

28270976

Citation

Chen, Hu, et al. "Low-dose CT Via Convolutional Neural Network." Biomedical Optics Express, vol. 8, no. 2, 2017, pp. 679-694.
Chen H, Zhang Y, Zhang W, et al. Low-dose CT via convolutional neural network. Biomed Opt Express. 2017;8(2):679-694.
Chen, H., Zhang, Y., Zhang, W., Liao, P., Li, K., Zhou, J., & Wang, G. (2017). Low-dose CT via convolutional neural network. Biomedical Optics Express, 8(2), pp. 679-694. doi:10.1364/BOE.8.000679.
Chen H, et al. Low-dose CT Via Convolutional Neural Network. Biomed Opt Express. 2017 Feb 1;8(2):679-694. PubMed PMID: 28270976.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Low-dose CT via convolutional neural network. AU - Chen,Hu, AU - Zhang,Yi, AU - Zhang,Weihua, AU - Liao,Peixi, AU - Li,Ke, AU - Zhou,Jiliu, AU - Wang,Ge, Y1 - 2017/01/09/ PY - 2016/10/11/received PY - 2016/12/26/revised PY - 2016/12/27/accepted PY - 2017/3/9/entrez PY - 2017/3/9/pubmed PY - 2017/3/9/medline KW - (100.3190) Inverse problems KW - (100.6950) Tomographic image processing KW - (340.7440) X-ray imaging SP - 679 EP - 694 JF - Biomedical optics express JO - Biomed Opt Express VL - 8 IS - 2 N2 - In order to reduce the potential radiation risk, low-dose CT has attracted an increasing attention. However, simply lowering the radiation dose will significantly degrade the image quality. In this paper, we propose a new noise reduction method for low-dose CT via deep learning without accessing original projection data. A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion. Qualitative results demonstrate a great potential of the proposed method on artifact reduction and structure preservation. In terms of the quantitative metrics, the proposed method has showed a substantial improvement on PSNR, RMSE and SSIM than the competing state-of-art methods. Furthermore, the speed of our method is one order of magnitude faster than the iterative reconstruction and patch-based image denoising methods. SN - 2156-7085 UR - https://www.unboundmedicine.com/medline/citation/28270976/Low_dose_CT_via_convolutional_neural_network_ L2 - https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/28270976/ DB - PRIME DP - Unbound Medicine ER -