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/

Zendy Plus

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

Zendy Tools

Zendy Open

Purpose The course of surgical procedures is often unpredictable, making itdifficult to estimate the duration of procedures beforehand. A context-awaremethod that analyses the workflow of an intervention online and automaticallypredicts the remaining duration would alleviate these problems. As basis forsuch an estimate, information regarding the current state of the interventionis required. Methods Today, the operating room contains a diverse range ofsensors. During laparoscopic interventions, the endoscopic video stream is anideal source of such information. Extracting quantitative information from thevideo is challenging though, due to its high dimensionality. Other surgicaldevices (e.g. insufflator, lights, etc.) provide data streams which are, incontrast to the video stream, more compact and easier to quantify. Thoughwhether such streams offer sufficient information for estimating the durationof surgery is uncertain. Here, we propose and compare methods, based onconvolutional neural networks, for continuously predicting the duration oflaparoscopic interventions based on unlabeled data, such as from endoscopicimages and surgical device streams. Results The methods are evaluated on 80laparoscopic interventions of various types, for which surgical device data andthe endoscopic video are available. Here the combined method performs best withan overall average error of 37% and an average halftime error of 28%.Conclusion In this paper, we present, to our knowledge, the first approach foronline procedure duration prediction using unlabeled endoscopic video data andsurgical device data in a laparoscopic setting. We also show that a methodincorporating both vision and device data performs better than methods basedonly on vision, while methods only based on tool usage and surgical device dataperform poorly, showing the importance of the visual channel.

Prediction of laparoscopic procedure duration using unlabeled, multimodal sensor data