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

Cholecystectomy (gallbladder removal) is one of the most common procedures inthe US, with more than 1.2M procedures annually. Compared with classical opencholecystectomy, laparoscopic cholecystectomy (LC) is associated withsignificantly shorter recovery period, and hence is the preferred method.However, LC is also associated with an increase in bile duct injuries (BDIs),resulting in significant morbidity and mortality. The primary cause of BDIsfrom LCs is misidentification of the cystic duct with the bile duct. Criticalview of safety (CVS) is the most effective of safety protocols, which is saidto be achieved during the surgery if certain criteria are met. However, due tosuboptimal understanding and implementation of CVS, the BDI rates have remainedstable over the last three decades. In this paper, we develop deep-learningtechniques to automate the assessment of CVS in LCs. An innovative aspect ofour research is on developing specialized learning techniques by incorporatingdomain knowledge to compensate for the limited training data available inpractice. In particular, our CVS assessment process involves a fusion of twosegmentation maps followed by an estimation of a certain region of interestbased on anatomical structures close to the gallbladder, and then finallydetermination of each of the three CVS criteria via rule-based assessment ofstructural information. We achieved a gain of over 11.8% in mIoU on relevantclasses with our two-stream semantic segmentation approach when compared to asingle-model baseline, and 1.84% in mIoU with our proposed Sobel loss functionwhen compared to a Transformer-based baseline model. For CVS criteria, weachieved up to 16% improvement and, for the overall CVS assessment, we achieved5% improvement in balanced accuracy compared to DeepCVS under the sameexperiment settings.

Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy