Two stage residual CNN for texture denoising and structure enhancement on low dose CT image. (February 2020)

• Record Type: Journal Article
• Authors: Huang, Liangliang; Jiang, Huiyan; Li, Shaojie; Bai, Zhiqi; Zhang, Jitong
• Is Part Of: Computer methods and programs in biomedicine. Volume 184(2020)
• Publication Date: 2020-02
• Subjects: Image denoising -- Low dose CT -- Two stage residual CNN -- Normal dose CT model; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.105115
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: This paper proposes a two stage residual convolutional neural network (TS-RCNN) method for low dose CT images denoising. This paper uses an extra CNN for image structural enhancement, which improves image quality visually and numerically. An average normal dose CT model is built to solve the problem that the second stage CNN lack of ideal training label. Perceptual loss acts as part of loss function. Different from original work, it is applied in high frequency wavelet image. The experimentations and comparisons demonstrate the merit of TS-RCNN compared with related low dose CT denoising methods. 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.