Next Article in Journal
Deep Vibro-Tactile Perception for Simultaneous Texture Identification, Slip Detection, and Speed Estimation
Next Article in Special Issue
Sensors, Signal and Image Processing in Biomedicine and Assisted Living
Previous Article in Journal
Base Station Selection for Hybrid TDOA/RTT/DOA Positioning in Mixed LOS/NLOS Environment
Previous Article in Special Issue
Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach
Open AccessLetter

Improving Temporal Stability and Accuracy for Endoscopic Video Tissue Classification Using Recurrent Neural Networks

1
Department of Electrical Engineering, Eindhoven University of Technology, Groene Loper 3, 5612 AE Eindhoven, The Netherlands
2
Amsterdam University Medical Center, Meibergdreef 9, 1105 AZ Amsterdam, The Netherlands
3
Catharina Hospital, Michelangelolaan 2, 5623 EJ Eindhoven, The Netherlands
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(15), 4133; https://doi.org/10.3390/s20154133
Received: 31 May 2020 / Revised: 9 July 2020 / Accepted: 20 July 2020 / Published: 24 July 2020
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. View Full-Text
Keywords: Barrett neoplasia; tissue detection; recurrent neural networks; upper GI tract Barrett neoplasia; tissue detection; recurrent neural networks; upper GI tract
Show Figures

Figure 1

MDPI and ACS Style

Boers, T.; van der Putten, J.; Struyvenberg, M.; Fockens, K.; Jukema, J.; Schoon, E.; van der Sommen, F.; Bergman, J.; de With, P. Improving Temporal Stability and Accuracy for Endoscopic Video Tissue Classification Using Recurrent Neural Networks. Sensors 2020, 20, 4133. https://doi.org/10.3390/s20154133

AMA Style

Boers T, van der Putten J, Struyvenberg M, Fockens K, Jukema J, Schoon E, van der Sommen F, Bergman J, de With P. Improving Temporal Stability and Accuracy for Endoscopic Video Tissue Classification Using Recurrent Neural Networks. Sensors. 2020; 20(15):4133. https://doi.org/10.3390/s20154133

Chicago/Turabian Style

Boers, Tim; van der Putten, Joost; Struyvenberg, Maarten; Fockens, Kiki; Jukema, Jelmer; Schoon, Erik; van der Sommen, Fons; Bergman, Jacques; de With, Peter. 2020. "Improving Temporal Stability and Accuracy for Endoscopic Video Tissue Classification Using Recurrent Neural Networks" Sensors 20, no. 15: 4133. https://doi.org/10.3390/s20154133

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop