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

Retinal Optical Coherence Tomography (OCT), a noninvasive cross-sectionalscan of the eye with qualitative 3D visualization of the retinal anatomy is useto study the retinal structure and the presence of pathogens. The advent of theretinal OCT has transformed ophthalmology and it is currently paramount for thediagnosis, monitoring and treatment of many eye pathogens including MacularEdema which impairs vision severely or Glaucoma that can cause irreversibleblindness. However the quality of retinal OCT images varies among devicemanufacturers. Deep Learning methods have had their success in the medicalimage segmentation community but it is still not clear if the level of successcan be generalised across OCT images collected from different device vendors.In this work we propose two variants of the nnUNet [8]. The standard nnUNet andan enhanced vision call nnUnet_RASPP (nnU-Net with residual and Atrous SpatialPyramid Pooling) both of which are robust and generalise with consistent highperformance across images from multiple device vendors. The algorithm wasvalidated on the MICCAI 2017 RETOUCH challenge dataset [1] acquired from 3device vendors across 3 medical centers from patients suffering from 2 retinaldisease types. Experimental results show that our algorithms outperform thecurrent state-of-the-arts algorithms by a clear margin for segmentationobtaining a mean Dice Score (DS) of 82.3% for the 3 retinal fluids scoring84.0%, 80.0%, 83.0% for Intraretinal Fluid (IRF), Subretinal Fluid (SRF), andPigment Epithelium Detachments (PED) respectively on the testing dataset. Alsowe obtained a perfect Area Under the Curve (AUC) score of 100% for thedetection of the presence of fluid for all 3 fluid classes on the testingdataset.

nnUNet RASPP for Retinal OCT Fluid Detection, Segmentation and Generalisation over Variations of Data Sources