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

The advance of computer-aided detection systems using deep learning opened anew scope in endoscopic image analysis. However, the learning-based modelsdeveloped on closed datasets are susceptible to unknown anomalies in complexclinical environments. In particular, the high false positive rate of polypdetection remains a major challenge in clinical practice. In this work, werelease the FPPD-13 dataset, which provides a taxonomy and real-world cases oftypical false positives during computer-aided polyp detection in real-worldcolonoscopy. We further propose a post-hoc module EndoBoost, which can beplugged into generic polyp detection models to filter out false positivepredictions. This is realized by generative learning of the polyp manifold withnormalizing flows and rejecting false positives through density estimation.Compared to supervised classification, this anomaly detection paradigm achievesbetter data efficiency and robustness in open-world settings. Extensiveexperiments demonstrate a promising false positive suppression in bothretrospective and prospective validation. In addition, the released dataset canbe used to perform 'stress' tests on established detection systems andencourages further research toward robust and reliable computer-aidedendoscopic image analysis. The dataset and code will be publicly available athttp://endoboost.miccai.cloud.

EndoBoost: a plug-and-play module for false positive suppression during computer-aided polyp detection in real-world colonoscopy (with dataset)