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

Modern surgeries are performed in complex and dynamic settings, includingever-changing interactions between medical staff, patients, and equipment. Theholistic modeling of the operating room (OR) is, therefore, a challenging butessential task, with the potential to optimize the performance of surgicalteams and aid in developing new surgical technologies to improve patientoutcomes. The holistic representation of surgical scenes as semantic scenegraphs (SGG), where entities are represented as nodes and relations betweenthem as edges, is a promising direction for fine-grained semantic ORunderstanding. We propose, for the first time, the use of temporal informationfor more accurate and consistent holistic OR modeling. Specifically, weintroduce memory scene graphs, where the scene graphs of previous time stepsact as the temporal representation guiding the current prediction. We design anend-to-end architecture that intelligently fuses the temporal information ofour lightweight memory scene graphs with the visual information from pointclouds and images. We evaluate our method on the 4D-OR dataset and demonstratethat integrating temporality leads to more accurate and consistent resultsachieving an +5% increase and a new SOTA of 0.88 in macro F1. This work opensthe path for representing the entire surgery history with memory scene graphsand improves the holistic understanding in the OR. Introducing scene graphs asmemory representations can offer a valuable tool for many temporalunderstanding tasks.

LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms