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

Purpose: Sparse-view computed tomography (CT) is an effective way to reducedose by lowering the total number of views acquired, albeit at the expense ofimage quality, which, in turn, can impact the ability to detect diseases. Weexplore deep learning-based artifact reduction in sparse-view cranial CT scansand its impact on automated hemorrhage detection. Methods: We trained a U-Netfor artefact reduction on simulated sparse-view cranial CT scans from 3000patients obtained from a public dataset and reconstructed with varying levelsof sub-sampling. Additionally, we trained a convolutional neural network onfully sampled CT data from 17,545 patients for automated hemorrhage detection.We evaluated the classification performance using the area under the receiveroperator characteristic curves (AUC-ROCs) with corresponding 95% confidenceintervals (CIs) and the DeLong test, along with confusion matrices. Theperformance of the U-Net was compared to an analytical approach based on totalvariation (TV). Results: The U-Net performed superior compared to unprocessedand TV-processed images with respect to image quality and automated hemorrhagediagnosis. With U-Net post-processing, the number of views can be reduced from4096 (AUC-ROC: 0.974; 95% CI: 0.972-0.976) views to 512 views (0.973;0.971-0.975) with minimal decrease in hemorrhage detection (P<.001) and to 256views (0.967; 0.964-0.969) with a slight performance decrease (P<.001).Conclusion: The results suggest that U-Net based artifact reductionsubstantially enhances automated hemorrhage detection in sparse-view cranialCTs. Our findings highlight that appropriate post-processing is crucial foroptimal image quality and diagnostic accuracy while minimizing radiation dose.

Improving Automated Hemorrhage Detection in Sparse-view Computed Tomography via Deep Convolutional Neural Network based Artifact Reduction