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

Dual-energy computed tomography (DECT) utilizes separate X-ray energy spectrato improve multi-material decomposition (MMD) for various diagnosticapplications. However accurate decomposing more than two types of materialremains challenging using conventional methods. Deep learning (DL) methods haveshown promise to improve the MMD performance, but typical approaches ofconducing DL-MMD in the image domain fail to fully utilize projectioninformation or under iterative setup are computationally inefficient in bothtraining and prediction. In this work, we present a clinical-applicable MMD(>2) framework rFast-MMDNet, operating with raw projection data innon-recursive setup, for breast tissue differentiation. rFast-MMDNet is atwo-stage algorithm, including stage-one SinoNet to perform dual energyprojection decomposition on tissue sinograms and stage-two FBP-DenoiseNet toperform domain adaptation and image post-processing. rFast-MMDNet was tested ona 2022 DL-Spectral-Challenge breast phantom dataset. The two stages ofrFast-MMDNet were evaluated separately and then compared with four noniterativereference methods including a direct inversion method (AA-MMD), an image domainDL method (ID-UNet), AA-MMD/ID-UNet + DenoiseNet and a sinogram domain DLmethod (Triple-CBCT). Our results show that models trained from informationstored in DE transmission domain can yield high-fidelity decomposition of theadipose, calcification, and fibroglandular materials with averaged RMSE, MAE,negative PSNR, and SSIM of 0.004+/-~0, 0.001+/-~0, -45.027+/-~0.542, and0.002+/-~0 benchmarking to the ground truth, respectively. Training of entirerFast-MMDNet on a 4xRTX A6000 GPU cluster took a day with inference time <1s.All DL methods generally led to more accurate MMD than AA-MMD. rFast-MMDNetoutperformed Triple-CBCT, but both are superior to the image-domain basedmethods.

A Two-Step Framework for Multi-Material Decomposition of Dual Energy Computed Tomography from Projection Domain