Attention-based surgical phase boundaries detection in laparoscopic videos

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

Abstract

A new deep learning-based method is proposed for identifying the boundaries of all surgical phases in a laparoscopic video. The model is designed based on the sequence-to-sequence architecture with an attention mechanism, to map the extracted visual features to the frame numbers of the beginning and the ending of each phase. The main novelty is that the alignment vectors for each phase are taken as the outputs, and are trained directly to select the indices. We evaluated our model using a large publicly available dataset of laparoscopic cholecystectomy procedure and obtained the Mean Absolute Error (MAE) of 48 seconds.

Original languageEnglish (US)
Title of host publicationProceedings - 6th Annual Conference on Computational Science and Computational Intelligence, CSCI 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages577-583
Number of pages7
ISBN (Electronic)9781728155845
DOIs
StatePublished - Dec 2019
Externally publishedYes
Event6th Annual International Conference on Computational Science and Computational Intelligence, CSCI 2019 - Las Vegas, United States
Duration: Dec 5 2019Dec 7 2019

Publication series

NameProceedings - 6th Annual Conference on Computational Science and Computational Intelligence, CSCI 2019

Conference

Conference6th Annual International Conference on Computational Science and Computational Intelligence, CSCI 2019
Country/TerritoryUnited States
CityLas Vegas
Period12/5/1912/7/19

Keywords

  • Attention mechanis
  • CNN
  • RNN
  • Sequence-to-sequence
  • Surgical phase detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Signal Processing
  • Hardware and Architecture
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Attention-based surgical phase boundaries detection in laparoscopic videos'. Together they form a unique fingerprint.

Cite this