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.
Breast thermography uses ultrasensitive infrared cameras to produce high resolution images of temperatures and vascular changes. In the present work we propose the development of computational methods that allow the analysis and digital processing of breast thermographic images for the detection of regions related to a probable lesion. A semi-automated segmentation algorithm is presented by means of polynomial curve Ötting for the detection a region of breast (ROI). A public database which contains information on volunteers with diagnose made by mammography and biopsy is used.