The classification of endoscopy images with persistent homology

Dunaeva, Olga; Edelsbrunner, Herbert; Lukyanov, Anton; Machin, Michael; Malkova, Daria; Kuvaev, Roman; Kashin, Sergey

The classification of endoscopy images with persistent homology

O. Dunaeva, H. Edelsbrunner, A. Lukyanov, M. Machin, D. Malkova, R. Kuvaev, S. Kashin, Pattern Recognition Letters 83 (2016) 13–22.

Download

2016-Edelsbrunner_The_classification.pdf 1.92 MB

DOI

10.1016/j.patrec.2015.12.012

Journal Article | Published | English

Author

Dunaeva, Olga ; Edelsbrunner, Herbert^{IST Austria} ; Lukyanov, Anton ; Machin, Michael ; Malkova, Daria ; Kuvaev, Roman ; Kashin, Sergey

Department

Edelsbrunner Group

Abstract

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.

Publishing Year

2016

Date Published

2016-11-01

Journal Title

Pattern Recognition Letters

Acknowledgement

This research is partially supported by the Russian Government under the Mega Project 11.G34.31.0053. This research is partially supported by the project no. 477 of P.G. Demidov Yaroslavl State University within State Assignment for Research.

Volume

Issue

Page

13 - 22

IST-REx-ID

1289

Cite this

Dunaeva O, Edelsbrunner H, Lukyanov A, et al. The classification of endoscopy images with persistent homology. Pattern Recognition Letters. 2016;83(1):13-22. doi:10.1016/j.patrec.2015.12.012

Dunaeva, O., Edelsbrunner, H., Lukyanov, A., Machin, M., Malkova, D., Kuvaev, R., & Kashin, S. (2016). The classification of endoscopy images with persistent homology. Pattern Recognition Letters, 83(1), 13–22. https://doi.org/10.1016/j.patrec.2015.12.012

Dunaeva, Olga, Herbert Edelsbrunner, Anton Lukyanov, Michael Machin, Daria Malkova, Roman Kuvaev, and Sergey Kashin. “The Classification of Endoscopy Images with Persistent Homology.” Pattern Recognition Letters 83, no. 1 (2016): 13–22. https://doi.org/10.1016/j.patrec.2015.12.012.

O. Dunaeva et al., “The classification of endoscopy images with persistent homology,” Pattern Recognition Letters, vol. 83, no. 1, pp. 13–22, 2016.

Dunaeva O, Edelsbrunner H, Lukyanov A, Machin M, Malkova D, Kuvaev R, Kashin S. 2016. The classification of endoscopy images with persistent homology. Pattern Recognition Letters. 83(1), 13–22.

Dunaeva, Olga, et al. “The Classification of Endoscopy Images with Persistent Homology.” Pattern Recognition Letters, vol. 83, no. 1, Elsevier, 2016, pp. 13–22, doi:10.1016/j.patrec.2015.12.012.

All files available under the following license(s):

Creative Commons License:

Creative Commons Attribution-NonCommercial-NoDerivs (CC BY-NC-ND 4.0)