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

This study investigated the potential of end-to-end deep learning tools as amore effective substitute for FEM in predicting stress-strain fields within 2Dcross sections of arterial wall. We first proposed a U-Net based fullyconvolutional neural network (CNN) to predict the von Mises stress and straindistribution based on the spatial arrangement of calcification within arterialwall cross-sections. Further, we developed a conditional generative adversarialnetwork (cGAN) to enhance, particularly from the perceptual perspective, theprediction accuracy of stress and strain field maps for arterial walls withvarious calcification quantities and spatial configurations. On top of U-Netand cGAN, we also proposed their ensemble approaches, respectively, to furtherimprove the prediction accuracy of field maps. Our dataset, consisting of inputand output images, was generated by implementing boundary conditions andextracting stress-strain field maps. The trained U-Net models can accuratelypredict von Mises stress and strain fields, with structural similarity indexscores (SSIM) of 0.854 and 0.830 and mean squared errors of 0.017 and 0.018 forstress and strain, respectively, on a reserved test set. Meanwhile, the cGANmodels in a combination of ensemble and transfer learning techniquesdemonstrate high accuracy in predicting von Mises stress and strain fields, asevidenced by SSIM scores of 0.890 for stress and 0.803 for strain.Additionally, mean squared errors of 0.008 for stress and 0.017 for strainfurther support the model's performance on a designated test set. Overall, thisstudy developed a surrogate model for finite element analysis, which canaccurately and efficiently predict stress-strain fields of arterial wallsregardless of complex geometries and boundary conditions.

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment