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: Automated Surgical Phase Recognition (SPR) uses ArtificialIntelligence (AI) to segment the surgical workflow into its key events,functioning as a building block for efficient video review, surgical educationas well as skill assessment. Previous research has focused on short and linearsurgical procedures and has not explored if temporal context influencesexperts' ability to better classify surgical phases. This research addressesthese gaps, focusing on Robot-Assisted Partial Nephrectomy (RAPN) as a highlynon-linear procedure. Methods: Urologists of varying expertise were grouped andtasked to indicate the surgical phase for RAPN on both single frames and videosnippets using a custom-made web platform. Participants reported theirconfidence levels and the visual landmarks used in their decision-making. AIarchitectures without and with temporal context as trained and benchmarked onthe Cholec80 dataset were subsequently trained on this RAPN dataset. Results:Video snippets and presence of specific visual landmarks improved phaseclassification accuracy across all groups. Surgeons displayed high confidencein their classifications and outperformed novices, who struggled discriminatingphases. The performance of the AI models is comparable to the surgeons in thesurvey, with improvements when temporal context was incorporated in both cases.Conclusion: SPR is an inherently complex task for expert surgeons and computervision, where both perform equally well when given the same context.Performance increases when temporal information is provided. Surgical tools andorgans form the key landmarks for human interpretation and are expected toshape the future of automated SPR.

Surgeons vs. Computer Vision: A comparative analysis on surgical phase recognition capabilities