Title
Applying a modified version of Lyapunov exponent for cancer diagnosis in biomedical images: the case of breast mammograms
Abstract
Recently, there has been a great interest in the application of Lyapunov exponents for calculation of chaos levels in dynamical systems. Accordingly, this study aims at presenting two new methods for utilizing Lyapunov exponents to evaluate the spatiotemporal chaos in various images. Further, early detection of cancerous tumors could be obtained by measuring the chaotic indices in biomedical images. Unlike the available systems described by partial differential equations, the proposed method employs a number of interactive dynamic variables for image modeling. Since the Lyapunov exponents cannot be applied to such systems, the image model should be modified. The mean Lyapunov exponent is defined as a chaotic index for measuring the contour borders irregularities in images to detect benign or malignant tumors. Moreover, a two-dimensional mean Lyapunov exponent is incorporated to identify irregularities existing in each axis of the targeted images. Experiments on a set of region of interest in breast mammogram images yielded a sensitivity of 95 % and a specificity of 97.3 % and verified the remarkable precision of the proposed methods in classifying of breast lesions obtained from breast mammogram images.
Year
DOI
Venue
2018
https://doi.org/10.1007/s11045-016-0446-8
Multidim. Syst. Sign. Process.
Keywords
Field
DocType
Mean Lyapunov exponent,Two-dimensional mean Lyapunov exponent,Partial differential equations,Breast mammograms,Cancer diagnosis,Computer aided diagnosis
Early detection,Discrete mathematics,Mathematical optimization,Computer-aided diagnosis,Dynamical systems theory,Region of interest,Chaotic,Partial differential equation,Mathematics,Lyapunov exponent
Journal
Volume
Issue
ISSN
29
1
0923-6082
Citations 
PageRank 
References 
0
0.34
19
Authors
4
Name
Order
Citations
PageRank
Hamed Khodadadi131.42
Ali Khaki-Sedigh294.83
Mohammad Ataei300.68
Mohammad Reza Jahed-Motlagh4247.35