Automatic detection of surgical phases in laparoscopic videos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The assement and evaluation of surgical skills require a considerable amount of time and effort. Currently, the assessment is accomplished by either observing a recorded video from the surgery in the case of laparoscopic procedures, or watching it in real-time in an operating room in the case of open surgical procedures. Given the limited time available to experts, knowing the surgical workflow can expedite the process of assessment by helping the surgeons to focus on the most important parts of each surgical phase. In this paper, we developed a method called Surgical Phase Detection using a Deep Learning System (SPD-DLS) to identify the surgical phases from recorded videos of a laparoscopic procedure. We used a deep Convolutional Neural Network (CNN) followed by a Long Short-Term Memory (LSTM) model to consider both spatial and temporal information to identify the surgical phases in the video frames. In order to evaluate the resulting model, we used the publicly available cholec80 dataset, which contains 80 videos of laparoscopic cholecystectomy procedure. Our experimental results show significant improvement in both real-time and off-line modes in the automatic identification of surgical phases over existing methods that use the same dataset.

Original languageEnglish (US)
Title of host publication2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018 - Proceedings of the 2018 International Conference on Artificial Intelligence, ICAI 2018
EditorsHamid R. Arabnia, David de la Fuente, Elena B. Kozerenko, Jose A. Olivas, Fernando G. Tinetti
PublisherCSREA Press
Pages124-130
Number of pages7
ISBN (Electronic)1601324804, 9781601324801
StatePublished - 2018
Externally publishedYes
Event2018 International Conference on Artificial Intelligence, ICAI 2018 at 2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018 - Las Vegas, United States
Duration: Jul 30 2018Aug 2 2018

Publication series

Name2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018 - Proceedings of the 2018 International Conference on Artificial Intelligence, ICAI 2018

Conference

Conference2018 International Conference on Artificial Intelligence, ICAI 2018 at 2018 World Congress in Computer Science, Computer Engineering and Applied Computing, CSCE 2018
Country/TerritoryUnited States
CityLas Vegas
Period7/30/188/2/18

Keywords

  • Convolutional neural networks
  • Deep Learning
  • LSTM
  • Surgical workflow

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Automatic detection of surgical phases in laparoscopic videos'. Together they form a unique fingerprint.

Cite this