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

Optical coherence tomography angiography (OCTA) is a novel non-invasiveimaging modality for the visualisation of microvasculature in vivo that hasencountered broad adoption in retinal research. OCTA potential in theassessment of pathological conditions and the reproducibility of studies relieson the quality of the image analysis. However, automated segmentation ofparafoveal OCTA images is still an open problem. In this study, we generate thefirst open dataset of retinal parafoveal OCTA images with associated groundtruth manual segmentations. Furthermore, we establish a standard for OCTA imagesegmentation by surveying a broad range of state-of-the-art vessel enhancementand binarisation procedures. We provide the most comprehensive comparison ofthese methods under a unified framework to date. Our results show that, for theset of images considered, deep learning architectures (U-Net and CS-Net)achieve the best performance. For applications where manually segmented data isnot available to retrain these approaches, our findings suggest that optimaloriented flux is the best handcrafted filter from those considered.Furthermore, we report on the importance of preserving network structure in thesegmentation to enable deep vascular phenotyping. We introduce new metrics fornetwork structure evaluation in segmented angiograms. Our results demonstratethat segmentation methods with equal Dice score perform very differently interms of network structure preservation. Moreover, we compare the error in thecomputation of clinically relevant vascular network metrics (e.g. fovealavascular zone area and vessel density) across segmentation methods. Ourresults show up to 25% differences in vessel density accuracy depending on thesegmentation method employed. These findings should be taken into account whencomparing the results of clinical studies and performing meta-analyses.

Automated Segmentation of Optical Coherence Tomography Angiography Images: Benchmark Data and Clinically Relevant Metrics