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

X-ray Computed Tomography (CT) is an important tool in medical imaging toobtain a direct visualization of patient anatomy. However, the x-ray radiationexposure leads to the concern of lifetime cancer risk. Low-dose CT scan canreduce the radiation exposure to patient while the image quality is usuallydegraded due to the appearance of noise and artifacts. Numerous studies havebeen conducted to regularize CT image for better image quality. Yet, exploringthe underlying manifold where real CT images residing on is still an openproblem. In this paper, we propose a fully data-driven manifold learningapproach by incorporating the emerging deep-learning technology. Anencoder-decoder convolutional neural network has been established to map a CTimage to the inherent low-dimensional manifold, as well as to restore the CTimage from its corresponding manifold representation. A novel reconstructionalgorithm assisted by the leant manifold prior has been developed to achievehigh quality low-dose CT reconstruction. In order to demonstrate theeffectiveness of the proposed framework, network training, testing, andcomprehensive simulation study have been performed using patient abdomen CTimages. The trained encoder-decoder CNN is capable of restoring high-quality CTimages with average error of ~20 HU. Furthermore, the proposed manifold priorassisted reconstruction scheme achieves high-quality low-dose CTreconstruction, with average reconstruction error of < 30 HU, more than fivetimes and two times lower than that of filtered back projection method andtotal-variation based iterative reconstruction method, respectively.

Low dose CT reconstruction assisted by an image manifold prior