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

Accurate polyp detection is critical for early colorectal cancer diagnosis.Although remarkable progress has been achieved in recent years, the complexcolon environment and concealed polyps with unclear boundaries still posesevere challenges in this area. Existing methods either involve computationallyexpensive context aggregation or lack prior modeling of polyps, resulting inpoor performance in challenging cases. In this paper, we propose the EnhancedCenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training \&end-to-end inference framework that leverages images and bounding boxannotations to train a general model and fine-tune it based on the inferencescore to obtain a final robust model. Specifically, we conduct Box-assistedContrastive Learning (BCL) during training to minimize the intra-classdifference and maximize the inter-class difference between foreground polypsand backgrounds, enabling our model to capture concealed polyps. Moreover, toenhance the recognition of small polyps, we design the Semantic Flow-guidedFeature Pyramid Network (SFFPN) to aggregate multi-scale features and theHeatmap Propagation (HP) module to boost the model's attention on polyptargets. In the fine-tuning stage, we introduce the IoU-guided SampleRe-weighting (ISR) mechanism to prioritize hard samples by adaptively adjustingthe loss weight for each sample during fine-tuning. Extensive experiments onsix large-scale colonoscopy datasets demonstrate the superiority of our modelcompared with previous state-of-the-art detectors.

ECC-PolypDet: Enhanced CenterNet with Contrastive Learning for Automatic Polyp Detection