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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Purpose. Early squamous cell neoplasia (ESCN) in the oesophagus is a highlytreatable condition. Lesions confined to the mucosal layer can be curativelytreated endoscopically. We build a computer-assisted detection (CADe) systemthat can classify still images or video frames as normal or abnormal with highdiagnostic accuracy. Methods. We present a new benchmark dataset containing 68Kbinary labeled frames extracted from 114 patient videos whose imaged areas havebeen resected and correlated to histopathology. Our novel convolutional network(CNN) architecture solves the binary classification task and explains whatfeatures of the input domain drive the decision-making process of the network.Results. The proposed method achieved an average accuracy of 91.7 % compared tothe 94.7 % achieved by a group of 12 senior clinicians. Our novel networkarchitecture produces deeply supervised activation heatmaps that suggest thenetwork is looking at intrapapillary capillary loop (IPCL) patterns whenpredicting abnormality. Conclusion. We believe that this dataset and baselinemethod may serve as a reference for future benchmarks on both video frameclassification and explainability in the context of ESCN detection. A futurework path of high clinical relevance is the extension of the classification toESCN types.

Intrapapillary Capillary Loop Classification in Magnification Endoscopy: Open Dataset and Baseline Methodology