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

Ulcerative colitis (UC) is a chronic inflammatory bowel disease characterizedby relapsing inflammation of the large intestine. The severity of UC is oftenrepresented by the Mayo Endoscopic Subscore (MES) which quantifies mucosaldisease activity from endoscopy videos. In clinical trials, an endoscopy videois assigned an MES based upon the most severe disease activity observed in thevideo. For this reason, severe inflammation spread throughout the colon willreceive the same MES as an otherwise healthy colon with severe inflammationrestricted to a small, localized segment. Therefore, the extent of diseaseactivity throughout the large intestine, and overall response to treatment, maynot be completely captured by the MES. In this work, we aim to automaticallyestimate UC severity for each frame in an endoscopy video to provide a higherresolution assessment of disease activity throughout the colon. Becauseannotating severity at the frame-level is expensive, labor-intensive, andhighly subjective, we propose a novel weakly supervised, ordinal classificationmethod to estimate frame severity from video MES labels alone. Using clinicaltrial data, we first achieved 0.92 and 0.90 AUC for predicting mucosal healingand remission of UC, respectively. Then, for severity estimation, wedemonstrate that our models achieve substantial Cohen's Kappa agreement withground truth MES labels, comparable to the inter-rater agreement of expertclinicians. These findings indicate that our framework could serve as afoundation for novel clinical endpoints, based on a more localized scoringsystem, to better evaluate UC drug efficacy in clinical trials.

Automatic Estimation of Ulcerative Colitis Severity from Endoscopy Videos using Ordinal Multi-Instance Learning