Smoke detection in endoscopic surgery videos: a first step towards retrieval of semantic events. Issue 1 (10th March 2014)

• Record Type: Journal Article
• Authors: Loukas, Constantinos; Georgiou, Evangelos
• Is Part Of: International journal of medical robotics and computer assisted surgery. Volume 11:Issue 1(2015)
• Page Start: 80
• Page End: 94
• Publication Date: 2014-03-10
• Subjects: Robotics in medicine -- Periodicals; Surgery -- Technological innovations -- Periodicals; Imaging systems in medicine -- Periodicals; 617.90285
• DOI: 10.1002/rcs.1578
• Languages: English
• ISSNs: 1478-5951

Abstract

<abstract abstract-type="main"> <title>Abstract</title> <sec id="rcs1578-sec-0001" sec-type="section"> <title>Background</title> <p>Event‐based annotation of surgical operations has not received much attention, mainly due to diversity of the visual content. As a first attempt at retrieval of surgical events, we address the problem of detecting the smoke produced by electrosurgery tasks.</p> </sec> <sec id="rcs1578-sec-0002" sec-type="section"> <title>Methods</title> <p>After video decomposition into shots, a grid of particles is placed over the initial frame. The grid is advected with the space–time optical flow and a number of <italic>ad hoc</italic> kinematic features are extracted. After feature selection, a one‐class support vector machine is employed for classification. A vision‐based fire surveillance method is used for comparison.</p> </sec> <sec id="rcs1578-sec-0003" sec-type="section"> <title>Results</title> <p>Experimental evaluation is performed on individual shots and laparoscopic cholecystectomy videos. In the first set‐up, average specificity and sensitivity were 86% and 83%, respectively. In video‐based assessment the recognition accuracy was ≥ 80% for two of the three videos tested. The fire surveillance method had a maximum accuracy of 63%.</p> </sec> <sec id="rcs1578-sec-0004" sec-type="section"> <title>Conclusions</title> <p>The irregular movement of smoke was captured robustly by the proposed features, which could also be employed for interpretation of other semantic occurrences in surgical videos. Copyright © 2014 John Wiley & Sons, Ltd.</p> </sec> </abstract>