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

Intravascular ultrasound (IVUS) imaging allows direct visualization of thecoronary vessel wall and is suitable for the assessment of atherosclerosis andthe degree of stenosis. Accurate segmentation and measurements of lumen andmedian-adventitia (MA) from IVUS are essential for such a successful clinicalevaluation. However, current segmentation relies on manual operations, which istime-consuming and user-dependent. In this paper, we aim to develop a deeplearning-based method using an encoder-decoder deep architecture toautomatically extract both lumen and MA border. Our method named IVUS-U-Net++is an extension of the well-known U-Net++ model. More specifically, a featurepyramid network was added to the U-Net++ model, enabling the utilization offeature maps at different scales. As a result, the accuracy of the probabilitymap and subsequent segmentation have been improved We collected 1746 IVUSimages from 18 patients in this study. The whole dataset was split into atraining dataset (1572 images) for the 10-fold cross-validation and a testdataset (174 images) for evaluating the performance of models. Our IVUS-U-Net++segmentation model achieved a Jaccard measure (JM) of 0.9412, a Hausdorffdistance (HD) of 0.0639 mm for the lumen border, and a JM of 0.9509, an HD of0.0867 mm for the MA border, respectively. Moreover, the Pearson correlationand Bland-Altman analyses were performed to evaluate the correlations of 12clinical parameters measured from our segmentation results and the groundtruth, and automatic measurements agreed well with those from the ground truth(all Ps<0.01). In conclusion, our preliminary results demonstrate that theproposed IVUS-U-Net++ model has great promise for clinical use.

A Deep Learning-based Method to Extract Lumen and Media-Adventitia in Intravascular Ultrasound Images