Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS

Abstract: 

The goal of endoscopic analysis is to find abnormal lesions and determine further therapy from the obtained information. However, the procedure produces a variety of non-informative frames and lesions can be missed due to poor video quality. Especially when analyzing entire endoscopic videos made by non-expert endoscopists, informative frame classification is crucial to e.g. video quality grading. This work concentrates on the design of an automated indication of informativeness of video frames. We propose an algorithm consisting of state-of-the-art deep learning techniques, to initialize frame-based classification, followed by a hidden Markov model to incorporate temporal information and control consistent decision making. Results from the performed experiments show that the proposed model improves on the state-of-the-art with an F1-score of 91%, and a substantial increase in sensitivity of 10%. Additionally, the algorithm is capable of processing 261 frames per second.

up
0 users have voted:

Paper Details

Authors:
Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with
Submitted On:
12 September 2019 - 2:18am
Short Link:
Type:
Poster
Event:
Document Year:
2019
Cite

Document Files

poster_JvdP_ARGOS_informative_frame.pdf

(4)

Subscribe

[1] Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with, "INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4601. Accessed: Sep. 15, 2019.
@article{4601-19,
url = {http://sigport.org/4601},
author = {Jeroen de groof; Fons van der Sommen; Maarten Struyvenberg; Svitlana Zinger; Wouter Curvers; Erik Schoon; Jacques Bergman; Peter de with },
publisher = {IEEE SigPort},
title = {INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS},
year = {2019} }
TY - EJOUR
T1 - INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS
AU - Jeroen de groof; Fons van der Sommen; Maarten Struyvenberg; Svitlana Zinger; Wouter Curvers; Erik Schoon; Jacques Bergman; Peter de with
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4601
ER -
Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with. (2019). INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS. IEEE SigPort. http://sigport.org/4601
Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with, 2019. INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS. Available at: http://sigport.org/4601.
Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with. (2019). "INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS." Web.
1. Jeroen de groof, Fons van der Sommen, Maarten Struyvenberg, Svitlana Zinger, Wouter Curvers, Erik Schoon, Jacques Bergman, Peter de with. INFORMATIVE FRAME CLASSIFICATION OF ENDOSCOPIC VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS AND HIDDEN MARKOV MODELS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4601