Tags

Type your tag names separated by a space and hit enter

Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising.
IEEE Access 2018; 6:41839-41855IA

Abstract

Computed tomography (CT) is a popular medical imaging modality and enjoys wide clinical applications. At the same time, the x-ray radiation dose associated with CT scannings raises a public concern due to its potential risks to the patients. Over the past years, major efforts have been dedicated to the development of Low-Dose CT (LDCT) methods. However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that downgrade CT image quality. In this paper, we propose a novel 3D noise reduction method, called Structurally-sensitive Multi-scale Generative Adversarial Net (SMGAN), to improve the LDCT image quality. Specifically, we incorporate three-dimensional (3D) volumetric information to improve the image quality. Also, different loss functions for training denoising models are investigated. Experiments show that the proposed method can effectively preserve structural and textural information in reference to normal-dose CT (NDCT) images, and significantly suppress noise and artifacts. Qualitative visual assessments by three experienced radiologists demonstrate that the proposed method retrieves more information, and outperforms competing methods.

Authors+Show Affiliations

Departments of Bioengineering and Electrical Engineering, Stanford University, Stanford, CA, 94305.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.Jiangsu Key Laboratory of Molecular and Functional Imaging, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nanjing 210009, China.Department of Radiology, Wuxi No.2 People's Hospital,Wuxi, 214000, China.Jiangsu Key Laboratory of Molecular and Functional Imaging, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nanjing 210009, China.College of Computer Science, Sichuan University, Chengdu 610065, China.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

30906683

Citation

You, Chenyu, et al. "Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising." IEEE Access : Practical Innovations, Open Solutions, vol. 6, 2018, pp. 41839-41855.
You C, Yang Q, Shan H, et al. Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising. IEEE Access. 2018;6:41839-41855.
You, C., Yang, Q., Shan, H., Gjesteby, L., Li, G., Ju, S., ... Wang, G. (2018). Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising. IEEE Access : Practical Innovations, Open Solutions, 6, pp. 41839-41855. doi:10.1109/ACCESS.2018.2858196.
You C, et al. Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising. IEEE Access. 2018;6:41839-41855. PubMed PMID: 30906683.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Structurally-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising. AU - You,Chenyu, AU - Yang,Qingsong, AU - Shan,Hongming, AU - Gjesteby,Lars, AU - Li,Guang, AU - Ju,Shenghong, AU - Zhang,Zhuiyang, AU - Zhao,Zhen, AU - Zhang,Yi, AU - Wenxiang,Cong, AU - Wang,Ge, Y1 - 2018/07/20/ PY - 2019/3/26/entrez PY - 2018/1/1/pubmed PY - 2018/1/1/medline KW - Deep learning KW - Image denoising KW - Loss Function KW - Low dose CT KW - Machine Leaning SP - 41839 EP - 41855 JF - IEEE access : practical innovations, open solutions JO - IEEE Access VL - 6 N2 - Computed tomography (CT) is a popular medical imaging modality and enjoys wide clinical applications. At the same time, the x-ray radiation dose associated with CT scannings raises a public concern due to its potential risks to the patients. Over the past years, major efforts have been dedicated to the development of Low-Dose CT (LDCT) methods. However, the radiation dose reduction compromises the signal-to-noise ratio (SNR), leading to strong noise and artifacts that downgrade CT image quality. In this paper, we propose a novel 3D noise reduction method, called Structurally-sensitive Multi-scale Generative Adversarial Net (SMGAN), to improve the LDCT image quality. Specifically, we incorporate three-dimensional (3D) volumetric information to improve the image quality. Also, different loss functions for training denoising models are investigated. Experiments show that the proposed method can effectively preserve structural and textural information in reference to normal-dose CT (NDCT) images, and significantly suppress noise and artifacts. Qualitative visual assessments by three experienced radiologists demonstrate that the proposed method retrieves more information, and outperforms competing methods. SN - 2169-3536 UR - https://www.unboundmedicine.com/medline/citation/30906683/Structurally_sensitive_Multi_scale_Deep_Neural_Network_for_Low_Dose_CT_Denoising_ L2 - https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/30906683/ DB - PRIME DP - Unbound Medicine ER -