Mammogram classification using dynamic time warping

This paper presents a new approach for breast cancer classification using time series analysis. In particular, the region of interest (ROI) in mammogram images is classified as normal or abnormal using dynamic time warping (DTW) as a similarity measure. According to the analogous case in time series...

Full description

Main Authors: Gardezi, S.J.S., Faye, I., Sanchez Bornot, J.M., Kamel, N., Hussain, M.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.21817 /
Published: Springer New York LLC 2018
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009197914&doi=10.1007%2fs11042-016-4328-8&partnerID=40&md5=387f82d6fa0da944864f0b4216603182
http://eprints.utp.edu.my/21817/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.21817
recordtype eprints
spelling utp-eprints.218172018-10-23T01:35:43Z Mammogram classification using dynamic time warping Gardezi, S.J.S. Faye, I. Sanchez Bornot, J.M. Kamel, N. Hussain, M. This paper presents a new approach for breast cancer classification using time series analysis. In particular, the region of interest (ROI) in mammogram images is classified as normal or abnormal using dynamic time warping (DTW) as a similarity measure. According to the analogous case in time series analysis, the DTW subsumes Euclidean distance (ED) as a specific case with increased robustness due to DTW flexibility to address local horizontal/vertical deformations. This method is especially attractive for biomedical image analysis and is applied to mammogram classification for the first time in this paper. The current study concludes that varying the size of the ROI images and the restriction on the search criteria for the warping path do not affect the performance because the method produces good classification results with reduced computational complexity. The method is tested on the IRMA and MIAS dataset using the k-nearest neighbour classifier for different k values, which produces an area under curve (AUC) value of 0.9713 for one of the best scenarios. © 2017, Springer Science+Business Media New York. Springer New York LLC 2018 Article PeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009197914&doi=10.1007%2fs11042-016-4328-8&partnerID=40&md5=387f82d6fa0da944864f0b4216603182 Gardezi, S.J.S. and Faye, I. and Sanchez Bornot, J.M. and Kamel, N. and Hussain, M. (2018) Mammogram classification using dynamic time warping. Multimedia Tools and Applications, 77 (3). pp. 3941-3962. http://eprints.utp.edu.my/21817/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description This paper presents a new approach for breast cancer classification using time series analysis. In particular, the region of interest (ROI) in mammogram images is classified as normal or abnormal using dynamic time warping (DTW) as a similarity measure. According to the analogous case in time series analysis, the DTW subsumes Euclidean distance (ED) as a specific case with increased robustness due to DTW flexibility to address local horizontal/vertical deformations. This method is especially attractive for biomedical image analysis and is applied to mammogram classification for the first time in this paper. The current study concludes that varying the size of the ROI images and the restriction on the search criteria for the warping path do not affect the performance because the method produces good classification results with reduced computational complexity. The method is tested on the IRMA and MIAS dataset using the k-nearest neighbour classifier for different k values, which produces an area under curve (AUC) value of 0.9713 for one of the best scenarios. © 2017, Springer Science+Business Media New York.
format Article
author Gardezi, S.J.S.
Faye, I.
Sanchez Bornot, J.M.
Kamel, N.
Hussain, M.
spellingShingle Gardezi, S.J.S.
Faye, I.
Sanchez Bornot, J.M.
Kamel, N.
Hussain, M.
Mammogram classification using dynamic time warping
author_sort Gardezi, S.J.S.
title Mammogram classification using dynamic time warping
title_short Mammogram classification using dynamic time warping
title_full Mammogram classification using dynamic time warping
title_fullStr Mammogram classification using dynamic time warping
title_full_unstemmed Mammogram classification using dynamic time warping
title_sort mammogram classification using dynamic time warping
publisher Springer New York LLC
publishDate 2018
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009197914&doi=10.1007%2fs11042-016-4328-8&partnerID=40&md5=387f82d6fa0da944864f0b4216603182
http://eprints.utp.edu.my/21817/
_version_ 1741196525621477376
score 11.62408

Similar Items