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 diagnosis process of colorectal cancer mainly focuses on the localizationand characterization of abnormal growths in the colon tissue known as polyps.Despite recent advances in deep object localization, the localization of polypsremains challenging due to the similarities between tissues, and the high levelof artifacts. Recent studies have shown the negative impact of the presence ofartifacts in the polyp detection task, and have started to take them intoaccount within the training process. However, the use of prior knowledgerelated to the spatial interaction of polyps and artifacts has not yet beenconsidered. In this work, we incorporate artifact knowledge in apost-processing step. Our method models this task as an inductive graphrepresentation learning problem, and is composed of training and inferencesteps. Detected bounding boxes around polyps and artifacts are considered asnodes connected by a defined criterion. The training step generates a nodeclassifier with ground truth bounding boxes. In inference, we use thisclassifier to analyze a second graph, generated from artifact and polyppredictions given by region proposal networks. We evaluate how the choices inthe connectivity and artifacts affect the performance of our method and showthat it has the potential to reduce the false positives in the results of aregion proposal network.

Polyp-artifact relationship analysis using graph inductive learned representations