Low‐dose CT denoising with a high‐level feature refinement and dynamic convolution network

Abstract

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 multiscale 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 (LCA) to assign weights in different regions and handle CT images' delicate tissues better. Then, the dynamic dilated convolution (DDC) with multibranch and multiscale 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 10 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): 46.3526 dB (95% CI: 46.0121–46.6931 dB) 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: 28.1680–29.0580 dB) and SSIM: 0.7201 (95% CI: 0.7101–0.7301). Compared with LDCT, PSNR/SSIM is 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 multiscale 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.

Opportunities for artificial intelligence in radiation protection

“…In einer Studie wurde ein neuartiges Modell zum Entrauschen von Niedrigdosis-CT-Bildern vorgeschlagen, das eine Verfeinerung von Strukturen und eine dynamische Faltung auf mehreren Skalen nutzt, um die Einschränkungen früherer DL-basierter Entrauschungsmethoden zu umgehen [ 4 ]. Zu diesen Einschränkungen gehören die unvollständige Nutzung hierarchischer Merkmale und die Tatsache, dass sich Standard-Faltungskerne nicht dynamisch an Änderungen der Eingaben anpassen.…”