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

Pulmonary embolism (PE) is a prevalent lung disease that can lead to rightventricular hypertrophy and failure in severe cases, ranking second in severityonly to myocardial infarction and sudden death. Pulmonary artery CT angiography(CTPA) is a widely used diagnostic method for PE. However, PE detectionpresents challenges in clinical practice due to limitations in imagingtechnology. CTPA can produce noises similar to PE, making confirmation of itspresence time-consuming and prone to overdiagnosis. Nevertheless, thetraditional segmentation method of PE can not fully consider the hierarchicalstructure of features, local and global spatial features of PE CT images. Inthis paper, we propose an automatic PE segmentation method called SCUNet++(Swin Conv UNet++). This method incorporates multiple fusion dense skipconnections between the encoder and decoder, utilizing the Swin Transformer asthe encoder. And fuses features of different scales in the decoder subnetworkto compensate for spatial information loss caused by the inevitabledownsampling in Swin-UNet or other state-of-the-art methods, effectivelysolving the above problem. We provide a theoretical analysis of this method indetail and validate it on publicly available PE CT image datasets FUMPE andCAD-PE. The experimental results indicate that our proposed method achieved aDice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95thpercentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% andan HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that ourmethod exhibits strong performance in PE segmentation tasks, potentiallyenhancing the accuracy of automatic segmentation of PE and providing a powerfuldiagnostic tool for clinical physicians. Our source code and new FUMPE datasetare available at https://github.com/JustlfC03/SCUNet-plusplus.

SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation