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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning techniques are widely used in the medical imaging field; forexample, low-dose CT denoising. However, all these methods usually require alarge number of data samples, which are at risk of privacy leaking, expensive,and time-consuming. Because privacy and other concerns create challenges todata sharing, publicly available CT datasets are up to only a few thousandcases. Generating synthetic data provides a promising alternative to complementor replace training datasets without patient-specific information. Recently,diffusion models have gained popularity in the computer vision community with asolid theoretical foundation. In this paper, we employ latent diffusion modelsto generate synthetic images from a publicly available CT dataset-the MayoLow-dose CT Challenge dataset. Then, an equivalent synthetic dataset wascreated. Furthermore, we use both the original Mayo CT dataset and thesynthetic dataset to train the RED-CNN model respectively. The results showthat the RED-CNN model achieved similar performance in the two cases, whichsuggests the feasibility of using synthetic data to conduct the low-dose CTresearch. Additionally, we use the latent diffusion model to augment the Mayodataset. The results on the augmented dataset demonstrate an improved denoisingperformance.

Conversion of the Mayo LDCT Data to Synthetic Equivalent through the  Diffusion Model for Training Denoising Networks with a Theoretically Perfect  Privacy