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

Automated segmentation of hard exudates in colour fundus images is achallenge task due to issues of extreme class imbalance and enormous sizevariation. This paper aims to tackle these issues and proposes a dual-branchnetwork with dual-sampling modulated Dice loss. It consists of two branches:large hard exudate biased learning branch and small hard exudate biasedlearning branch. Both of them are responsible for their own duty separately.Furthermore, we propose a dual-sampling modulated Dice loss for the trainingsuch that our proposed dual-branch network is able to segment hard exudates indifferent sizes. In detail, for the first branch, we use a uniform sampler tosample pixels from predicted segmentation mask for Dice loss calculation, whichleads to this branch naturally be biased in favour of large hard exudates asDice loss generates larger cost on misidentification of large hard exudatesthan small hard exudates. For the second branch, we use a re-balanced samplerto oversample hard exudate pixels and undersample background pixels for losscalculation. In this way, cost on misidentification of small hard exudates isenlarged, which enforces the parameters in the second branch fit small hardexudates well. Considering that large hard exudates are much easier to becorrectly identified than small hard exudates, we propose an easy-to-difficultlearning strategy by adaptively modulating the losses of two branches. Weevaluate our proposed method on two public datasets and results demonstratethat ours achieves state-of-the-art performances.

Dual-Branch Network with Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation from Colour Fundus Images