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/

Zendy Plus

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

Zendy Tools

Zendy Open

Diabetic retinopathy is one of the leading causes of preventable blindness inthe world. Its earliest sign are red lesions, a general term that groups bothmicroaneurysms and hemorrhages. In daily clinical practice, these lesions aremanually detected by physicians using fundus photographs. However, this task istedious and time consuming, and requires an intensive effort due to the smallsize of the lesions and their lack of contrast. Computer-assisted diagnosis ofDR based on red lesion detection is being actively explored due to itsimprovement effects both in clinicians consistency and accuracy. Severalmethods for detecting red lesions have been proposed in the literature, most ofthem based on characterizing lesion candidates using hand crafted features, andclassifying them into true or false positive detections. Deep learning basedapproaches, by contrast, are scarce in this domain due to the high expense ofannotating the lesions manually. In this paper we propose a novel method forred lesion detection based on combining both deep learned and domain knowledge.Features learned by a CNN are augmented by incorporating hand crafted features.Such ensemble vector of descriptors is used afterwards to identify true lesioncandidates using a Random Forest classifier. We empirically observed thatcombining both sources of information significantly improve results withrespect to using each approach separately. Furthermore, our method reported thehighest performance on a per-lesion basis on DIARETDB1 and e-ophtha, and forscreening and need for referral on MESSIDOR compared to a second human expert.Results highlight the fact that integrating manually engineered approaches withdeep learned features is relevant to improve results when the networks aretrained from lesion-level annotated data. An open source implementation of oursystem is publicly available online.

An Ensemble Deep Learning Based Approach for Red Lesion Detection in Fundus Images