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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Most of the Deep Neural Networks (DNNs) based CT image denoising literatureshows that DNNs outperform traditional iterative methods in terms of metricssuch as the RMSE, the PSNR and the SSIM. In many instances, using the samemetrics, the DNN results from low-dose inputs are also shown to be comparableto their high-dose counterparts. However, these metrics do not reveal if theDNN results preserve the visibility of subtle lesions or if they alter the CTimage properties such as the noise texture. Accordingly, in this work, we seekto examine the image quality of the DNN results from a holistic viewpoint forlow-dose CT image denoising. First, we build a library of advanced DNNdenoising architectures. This library is comprised of denoising architecturessuch as the DnCNN, U-Net, Red-Net, GAN, etc. Next, each network is modeled, aswell as trained, such that it yields its best performance in terms of the PSNRand SSIM. As such, data inputs (e.g. training patch-size, reconstructionkernel) and numeric-optimizer inputs (e.g. minibatch size, learning rate, lossfunction) are accordingly tuned. Finally, outputs from thus trained networksare further subjected to a series of CT bench testing metrics such as thecontrast-dependent MTF, the NPS and the HU accuracy. These metrics are employedto perform a more nuanced study of the resolution of the DNN outputs'low-contrast features, their noise textures, and their CT number accuracy tobetter understand the impact each DNN algorithm has on these underlyingattributes of image quality.

Deep neural networks-based denoising models for CT imaging and their efficacy