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

Our work proposes neural network design choices that set the state-of-the-arton a challenging public benchmark on cataract surgery, CaDIS. Our methodologyachieves strong performance across three semantic segmentation tasks withincreasingly granular surgical tool class sets by effectively handling classimbalance, an inherent challenge in any surgical video. We consider andevaluate two conceptually simple data oversampling methods as well as differentloss functions. We show significant performance gains across networkarchitectures and tasks especially on the rarest tool classes, therebypresenting an approach for achieving high performance when imbalanced granulardatasets are considered. Our code and trained models are available athttps://github.com/RViMLab/MICCAI2021_Cataract_semantic_segmentation andqualitative results on unseen surgical video can be found athttps://youtu.be/twVIPUj1WZM.

Effective semantic segmentation in Cataract Surgery: What matters most?