The classification of endoscopy images with persistent homology

Dunaeva, Olga A and Edelsbrunner, Herbert and Lukyanov, Anton D and Machin, Michael and Malkova, Daria B and Kuvaev, Roman and Kashin, Sergey (2016) The classification of endoscopy images with persistent homology. Pattern Recognition Letters, 83. pp. 13-22. ISSN 0167-8655

[img] Text
2016-Edelsbrunner_The_classification.pdf - Accepted Version
Restricted to Registered users only until 1 November 2018.
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (1876Kb)
Official URL:


Aiming at the automatic diagnosis of tumors using narrow band imaging (NBI) magnifying endoscopic (ME) images of the stomach, we combine methods from image processing, topology, geometry, and machine learning to classify patterns into three classes: oval, tubular and irregular. Training the algorithm on a small number of images of each type, we achieve a high rate of correct classifications. The analysis of the learning algorithm reveals that a handful of geometric and topological features are responsible for the overwhelming majority of decisions.

Item Type: Article
DOI: 10.1016/j.patrec.2015.12.012
Uncontrolled Keywords: Persistent homology, image processing, computational topology, machine learning, endoscopy, automated diagnostics
Subjects: 000 Computer science, knowledge & general works > 000 Computer science, knowledge & systems > 004 Data processing & computer science
500 Science > 510 Mathematics > 514 Topology
Research Group: Edelsbrunner Group
SWORD Depositor: Sword Import User
Depositing User: Sword Import User
Date Deposited: 27 Feb 2018 10:23
Last Modified: 27 Feb 2018 10:23

Actions (login required)

View Item View Item