In Medical physics ; h5-index 59.0
BACKGROUND : Since the potential health risks of the radiation generated by computer tomography (CT), concerns have been expressed on reducing the radiation dose. However, low-dose CT (LDCT) images contain complex noise and artifacts, bringing uncertainty to medical diagnosis.
PURPOSE : Existing deep learning (DL)-based denoising methods are difficult to fully exploit hierarchical features of different levels, limiting the effect of denoising. Moreover, the standard convolution kernel is parameter sharing and cannot be adjusted dynamically with input change. This paper proposes an LDCT denoising network using high-level feature refinement and multi-scale dynamic convolution to mitigate these problems.
METHODS : The dual network structure proposed in this paper consists of the feature refinement network (FRN) and the dynamic perception network (DPN). The FDN extracts features of different levels through residual dense connections. The high-level hierarchical information is transmitted to DPN to improve the low-level representations. In DPN, the two networks' features are fused by local channel attention to assign weights in different regions and handle CT images' delicate tissues better. Then, the dynamic dilated convolution with multi-branch and multi-scale receptive fields is proposed to enhance the expression and processing ability of the denoising network. The experiments were trained and tested on the dataset "NIH-AAPM-Mayo Clinic Low-Dose CT Grand Challenge, " consisting of ten anonymous patients with normal-dose abdominal CT and LDCT at 25% dose. In addition, external validation was performed on the dataset "Low Dose CT Image and Projection Data," which included 300 chest CT images at 10% dose and 300 head CT images at 25% dose.
RESULTS : Proposed method compared with seven mainstream LDCT denoising algorithms. On the Mayo dataset, achieved peak signal to noise ratio (PSNR): 46.3526dB (95%CI: 46.0121dB - 46.6931dB) and structural similarity (SSIM): 0.9844 (95%CI: 0.9834 - 0.9854). Compared with LDCT, the average increase was 3.4159 dB and 0.0239, respectively. The results are relatively optimal and statistically significant compared with other methods. In external verification, our algorithm can cope well with ultra-low-dose chest CT images at 10% dose and obtain PSNR: 28.6130 (95%CI: 28.1680dB - 29.0580dB) and SSIM: 0.7201 (95%CI: 0.7101 - 0.7301). Compared with LDCT, PSNR/SSIM increased by 3.6536dB and 0.2132, respectively. In addition, the quality of LDCT can also be improved in head CT denoising.
CONCLUSIONS : This paper proposes a DL-based LDCT denoising algorithm, which utilizes high-level features and multi-scale dynamic convolution to optimize the network's denoising effect. This method can realize speedy denoising and performs well in noise suppression and detail preservation, which can be helpful for the diagnosis of LDCT. This article is protected by copyright. All rights reserved.
Yang Sihan, Pu Qiang, Lei Chunting, Zhang Qiao, Jeon Seunggil, Yang Xiaomin
2022-Dec-21
deep learning (DL), dynamic convolution, image denoising, low-dose CT (LDCT)
