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

Photon-counting spectral computed tomography is now clinically available.These new detectors come with the promise of higher contrast-to-noise ratio andspatial resolution and improved low-dose imaging. However, one important designconsideration is to build detector elements that are sufficiently homogeneous.In practice, there will always be a degree of inhomogeneity in the detectorelements, which will materialize as variations in the energy bin thresholds.Without proper detector calibration, this will lead to streak artifacts in thesinograms and corresponding ring artifacts in the reconstructed images, whichlimit their clinical usefulness. Since detector calibration is a time-consumingprocess, having access to a fast ring correction technique may greatly improveworkflow. In this paper, we propose a deep learning-based post-processingtechnique for ring artifact correction in photon-counting spectral CT. We traina UNet with a custom loss to correct for ring artifacts in the material basisimages. Our proposed loss is made ``task-aware'' by explicitly incorporatingthe fact that we are working with spectral CT by combining a L1-loss operatingon the material basis images with a perceptual loss, using VGG16 as featureextractor, operating on 70 keV virtual monoenergetic images. Our resultsindicate that using this novel loss greatly improves performance. Wedemonstrate that our proposed method can successfully produce ring corrected40, 70, and 100 keV virtual monoenergetic images.

Ring Artifact Correction in Photon-Counting Spectral CT Using a Convolutional Neural Network With Spectral Loss