Tags

Type your tag names separated by a space and hit enter

Two stage residual CNN for texture denoising and structure enhancement on low dose CT image.

Abstract

BACKGROUND AND OBJECTIVE

X-ray computed tomography (CT) plays an important role in modern medical science. Human health problems caused by CT radiation have attracted the attention of the academic community widely. Reducing radiation dose results in a deterioration in image quality and further affects doctor's diagnosis. Therefore, this paper introduces a new denoise method for low dose CT (LDCT) images, called two stage residual convolutional neural network (TS-RCNN).

METHODS

There are two important parts with respect to our network. 1) The first stage RCNN is proposed for texture denoising via the stationary wavelet transform (SWT) and the perceptual loss. Specifically, SWT is performed on each normal dose CT (NDCT) image and generated four wavelet images are considered as the labels. 2) The second stage RCNN is established for structure enhancement via the average NDCT model on the basis of the first network's result. Finally, the denoised CT image is obtained via inverse SWT.

RESULTS

Our proposed TS-RCNN is trained on three groups of simulated LDCT images in 1123 images per group and evaluated on 129 simulated LDCT images for each group. Besides, to demonstrate the clinical application of TS-RCNN, we also test our method on the 2016 Low Dose CT Grand Challenge dataset. Quantitative results show that TS-RCNN almost achieves the best results in terms of MSE, SSIM and PSNR compared to other methods.

CONCLUSIONS

The experimental results and comparisons demonstrate that TS-RCNN not only preserves more texture information, but also enhances structural information on LDCT images.

Authors+Show Affiliations

Software College, Northeastern University, Shenyang 110819, China.Software College, Northeastern University, Shenyang 110819, China. Electronic address: hyjiang@mail.neu.edu.cn.Sino-Dutch Biomedical and Information Engineering College, Northeastern University, Shenyang 110819, China.Software College, Northeastern University, Shenyang 110819, China.Sino-Dutch Biomedical and Information Engineering College, Northeastern University, Shenyang 110819, China.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31627148

Citation

Huang, Liangliang, et al. "Two Stage Residual CNN for Texture Denoising and Structure Enhancement On Low Dose CT Image." Computer Methods and Programs in Biomedicine, vol. 184, 2019, p. 105115.
Huang L, Jiang H, Li S, et al. Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. Comput Methods Programs Biomed. 2019;184:105115.
Huang, L., Jiang, H., Li, S., Bai, Z., & Zhang, J. (2019). Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. Computer Methods and Programs in Biomedicine, 184, p. 105115. doi:10.1016/j.cmpb.2019.105115.
Huang L, et al. Two Stage Residual CNN for Texture Denoising and Structure Enhancement On Low Dose CT Image. Comput Methods Programs Biomed. 2019 Oct 8;184:105115. PubMed PMID: 31627148.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. AU - Huang,Liangliang, AU - Jiang,Huiyan, AU - Li,Shaojie, AU - Bai,Zhiqi, AU - Zhang,Jitong, Y1 - 2019/10/08/ PY - 2019/01/23/received PY - 2019/09/27/revised PY - 2019/10/02/accepted PY - 2019/10/19/pubmed PY - 2019/10/19/medline PY - 2019/10/19/entrez KW - Image denoising KW - Low dose CT KW - Normal dose CT model KW - Two stage residual CNN SP - 105115 EP - 105115 JF - Computer methods and programs in biomedicine JO - Comput Methods Programs Biomed VL - 184 N2 - BACKGROUND AND OBJECTIVE: X-ray computed tomography (CT) plays an important role in modern medical science. Human health problems caused by CT radiation have attracted the attention of the academic community widely. Reducing radiation dose results in a deterioration in image quality and further affects doctor's diagnosis. Therefore, this paper introduces a new denoise method for low dose CT (LDCT) images, called two stage residual convolutional neural network (TS-RCNN). METHODS: There are two important parts with respect to our network. 1) The first stage RCNN is proposed for texture denoising via the stationary wavelet transform (SWT) and the perceptual loss. Specifically, SWT is performed on each normal dose CT (NDCT) image and generated four wavelet images are considered as the labels. 2) The second stage RCNN is established for structure enhancement via the average NDCT model on the basis of the first network's result. Finally, the denoised CT image is obtained via inverse SWT. RESULTS: Our proposed TS-RCNN is trained on three groups of simulated LDCT images in 1123 images per group and evaluated on 129 simulated LDCT images for each group. Besides, to demonstrate the clinical application of TS-RCNN, we also test our method on the 2016 Low Dose CT Grand Challenge dataset. Quantitative results show that TS-RCNN almost achieves the best results in terms of MSE, SSIM and PSNR compared to other methods. CONCLUSIONS: The experimental results and comparisons demonstrate that TS-RCNN not only preserves more texture information, but also enhances structural information on LDCT images. SN - 1872-7565 UR - https://www.unboundmedicine.com/medline/citation/31627148/Two_stage_residual_CNN_for_texture_denoising_and_structure_enhancement_on_low_dose_CT_image L2 - https://linkinghub.elsevier.com/retrieve/pii/S0169-2607(19)30103-8 DB - PRIME DP - Unbound Medicine ER -