English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Being low-level radiation exposure and less harmful to health, low-dosecomputed tomography (LDCT) has been widely adopted in the early screening oflung cancer and COVID-19. LDCT images inevitably suffer from the degradationproblem caused by complex noises. It was reported that deep learning (DL)-basedLDCT denoising methods using convolutional neural network (CNN) achievedimpressive denoising performance. Although most existing DL-based methods(e.g., encoder-decoder framework) can implicitly utilize non-local andcontextual information via downsampling operator and 3D CNN, the explicitmulti-information (i.e., local, non-local, and contextual) integration may notbe explored enough. To address this issue, we propose a novel graphconvolutional network-based LDCT denoising model, namely GCN-MIF, to explicitlyperform multi-information fusion for denoising purpose. Concretely, byconstructing intra- and inter-slice graph, the graph convolutional network isintroduced to leverage the non-local and contextual relationships among pixels.The traditional CNN is adopted for the extraction of local information.Finally, the proposed GCN-MIF model fuses all the extracted local, non-local,and contextual information. Extensive experiments show the effectiveness of ourproposed GCN-MIF model by quantitative and visualized results. Furthermore, adouble-blind reader study on a public clinical dataset is also performed tovalidate the usability of denoising results in terms of the structuralfidelity, the noise suppression, and the overall score. Models and code areavailable at https://github.com/tonyckc/GCN-MIF_demo.

GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising