Translator Disclaimer
Paper
30 August 2019 Fractal analysis for classification of breast lesions
Author Affiliations +
Abstract
Nowadays, breast lesions are a common health problem among women. Breast thermograms are images recorded by digital-optical systems with high resolution that use infrared technology in order to show vascular and temperature changes. In the present work, we study benign and malignant breast lesions shape by means of fractal analysis. The Fractal Dimension (FD) is calculated with the Box Counting method and the Hurst exponent is obtained using the Wavelet coefficients and the Detrending Moving Average algorithm. These algorithms was applied to synthetic images and breast thermograms. The Fractal Dimension value is used for patient classification with or without breast injury. The proposed methodology was applied to the Database For Mastology Research (DMR) in order to classify thermographic images. The FD of ROIs for breast thermograms was calculated. Results shows that the FD BCM values ranges from [0.45,0.81] in 4 healthy cases and from [0.92,1.33] in 4 unhealthy cases.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
L. B. Alvarado-Cruz, M. Delgadillo-Herrera, C. Toxqui-Quitl, A. Padilla-Vivanco, R. Castro-Ortega, and M. Arreola-Esquivel "Fractal analysis for classification of breast lesions", Proc. SPIE 11104, Current Developments in Lens Design and Optical Engineering XX, 111040U (30 August 2019); https://doi.org/10.1117/12.2531201
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
Back to Top