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

Nonuniform rotational distortion (NURD) correction is vital for endoscopicoptical coherence tomography (OCT) imaging and its functional extensions, suchas angiography and elastography. Current NURD correction methods requiretime-consuming feature tracking or cross-correlation calculations and thussacrifice temporal resolution. Here we propose a cross-attention learningmethod for the NURD correction in OCT. Our method is inspired by the recentsuccess of the self-attention mechanism in natural language processing andcomputer vision. By leveraging its ability to model long-range dependencies, wecan directly obtain the correlation between OCT A-lines at any distance, thusaccelerating the NURD correction. We develop an end-to-end stackedcross-attention network and design three types of optimization constraints. Wecompare our method with two traditional feature-based methods and a CNN-basedmethod, on two publicly-available endoscopic OCT datasets and a private datasetcollected on our home-built endoscopic OCT system. Our method achieved a$\sim3\times$ speedup to real time ($26\pm 3$ fps), and superior correctionperformance.

Cross-attention learning enables real-time nonuniform rotational distortion correction in OCT