Mammogram classification using dynamic time warping
- 195 Downloads
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.
KeywordsDynamic time warping Mammogram classification Orientation False alarms Type II error Sensitivity
This research was supported by the URIF grant 0153AA-B52.
SJS, IF and JMSB proposed the idea; participated in implementation and coordinated in optimization of study parameters using matlab. SJSG and JMSB also performed the literature survey and worked on database construction. NK and MH provided valuable suggestions in design and implementation of study and assisted in drafting of the manuscript. All authors have read and approved the final manuscript.
Compliance with ethical standards
The authors declare that they have no competing interests.
- 3.Berndt DJ, Clifford J (1994) Using dynamic time warping to find patterns in time series, vol 16. KDD workshop, Seattle, pp 359–370Google Scholar
- 4.Bhanu B, Zhou X (2004) Face recognition from face profile using dynamic time warping. In: Pattern recognition. ICPR 2004. Proceedings of the 17th International Conference on. IEEE, pp 499–502Google Scholar
- 5.Bodiroza S, Doisy G, Hafner V (2013) Position-invariant, real-time gesture recognition based on dynamic time warping. In: Human–Robot Interaction (HRI), 2013 8th ACM/IEEE International Conference on. IEEE, pp 87–88Google Scholar
- 7.Celebi S, Aydin AS, Temiz TT, Arici T (2013) Gesture recognition using skeleton data with weighted dynamic time warping. In: Computer vision theory and applications, VisappGoogle Scholar
- 11.Duarte Y, Nascimento M, Oliveira D. (2014) Classification of mammographic lesion based in Completed Local Binary Pattern and using multiresolution representation. In: Journal of Physics: Conference Series. vol 1. IOP Publishing, p 012127Google Scholar
- 16.Gardezi SJS, Faye I, Eltoukhy MM (2014) Analysis of mammogram images based on texture features of curvelet sub-bands. In: Fifth International Conference on Graphic and Image Processing. Int Soc Optics Photonics, pp 906924-906924-906926Google Scholar
- 17.Hajian-Tilaki K (2013) Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation. Caspian J Intern Med 4(2):627Google Scholar
- 19.International Agency for Cancer Research (IARC) (2013) Latest world cancer statistics: global cancer burden rises to 14.1 million new cases in 2012: marked increase in breast cancers must be addressed. World Health Organisation (WHO), LyonGoogle Scholar
- 27.Martens R, Claesen L (1996) On-line signature verification by dynamic time-warping. In: Pattern recognition, Proceedings of the 13th International Conference on. IEEE, pp 38–42Google Scholar
- 29.Mugavin ME (2008) Multidimensional scaling: a brief overview. Nurs Res 57(1):64–68. doi: 10.1097/1001.NNR.0000280659.0000288760.0000280657c CrossRefGoogle Scholar
- 30.Niennattrakul V, Ratanamahatana CA (2009) Learning DTW global constraint for time series classification. arXiv preprint arXiv:09030041Google Scholar
- 31.Oliveira JE, Gueld MO, Araújo AdA, Ott B, Deserno TM (2008) Toward a standard reference database for computer-aided mammography. In: Medical imaging. International Society for Optics and Photonics, pp 69151Y-69151Y-69159Google Scholar
- 32.Oliveira JEE, Gueld MO, de A. Araújo A, Ott B, Deserno TM (2008) Toward a standard reference database for computer-aided mammography. pp 69151Y-69151Y-69159Google Scholar
- 33.Oliver A, Lladó X, Freixenet J, Martí J (2007) False positive reduction in mammographic mass detection using local binary patterns. In: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2007. Springer, pp 286–293Google Scholar
- 36.Ratanamahatana CA, Keogh E (2005) Three myths about dynamic time warping data mining. In. Proc of the 5th SIAM Int. Conf. on Data Mining, SDMGoogle Scholar
- 38.Salvador S, Chan P (2004) FastDTW: Toward accurate dynamic time warping in linear time and space. In: KDD workshop on mining temporal and sequential data. CiteseerGoogle Scholar
- 41.Suckling JSA, Betal D, Cerneaz N, Dance DR, Kok S-L, Parker J, Ricketts I, Savage J, Stamatakis E, Taylor P (1994) The mammographic image analysis society digital mammogram database exerpta medica. Int Congr Ser 1069:375–378Google Scholar
- 47.Wickelmaier F (2003) An introduction to MDS: sound quality research unit. Aalborg University, AalborgGoogle Scholar
- 48.Xi X, Keogh E, Shelton C, Wei L, Ratanamahatana CA (2006) Fast time series classification using numerosity reduction. In: Proceedings of the 23rd international conference on Machine learning. ACM, pp 1033–1040Google Scholar
- 49.Zhang Y-D, Wang S-H, Liu G, Yang J (2016) Computer-aided diagnosis of abnormal breasts in mammogram images by weighted-type fractional Fourier transform. Adv Mech Eng 8(2). doi: 10.1177/1687814016634243