Improving temporal stability and accuracy for endoscopic video tissue classification using recurrent neural networks

Tim Boers (Corresponding author), Joost van der Putten, Maarten Struyvenberg, Kiki Fockens, Jelmer Jukema, Erik Schoon, Fons van der Sommen, Jacques Bergman, Peter de With

Research output: Contribution to journalLetterAcademicpeer-review

1 Citation (Scopus)

Abstract

Early Barrett’s neoplasia are often missed due to subtle visual features and inexperience of the non-expert endoscopist with such lesions. While promising results have been reported on the automated detection of this type of early cancer in still endoscopic images, video-based detection using the temporal domain is still open. The temporally stable nature of video data in endoscopic examinations enables to develop a framework that can diagnose the imaged tissue class over time, thereby yielding a more robust and improved model for spatial predictions. We show that the introduction of Recurrent Neural Network nodes offers a more stable and accurate model for tissue classification, compared to classification on individual images. We have developed a customized Resnet18 feature extractor with four types of classifiers: Fully Connected (FC), Fully Connected with an averaging filter (FC Avg(n = 5)), Long Short Term Memory (LSTM) and a Gated Recurrent Unit (GRU). Experimental results are based on 82 pullback videos of the esophagus with 46 high-grade dysplasia patients. Our results demonstrate that the LSTM classifier outperforms the FC, FC Avg(n = 5) and GRU classifier with an average accuracy of 85.9% compared to 82.2%, 83.0% and 85.6%, respectively. The benefit of our novel implementation for endoscopic tissue classification is the inclusion of spatio-temporal information for improved and robust decision making, and it is the first step towards full temporal learning of esophageal cancer detection in endoscopic video.

Original languageEnglish
Article number4133
Number of pages11
JournalSensors
Volume20
Issue number15
DOIs
Publication statusPublished - Aug 2020

Keywords

  • Barrett neoplasia
  • Recurrent neural networks
  • Tissue detection
  • Upper GI tract

Fingerprint Dive into the research topics of 'Improving temporal stability and accuracy for endoscopic video tissue classification using recurrent neural networks'. Together they form a unique fingerprint.

  • Cite this