Designing and Comparing Different Color Map Algorithms for Pseudo-Coloring Breast Thermograms Publisher



Aghdam NS¹ ; Amin MM¹ ; Tavakol ME² ; Ng EYK³
Source: Journal of Medical Imaging and Health Informatics Published:2013

Abstract

Breast cancer is the most common cancer in females globally. Early detection of breast cancer plays an important role in reducing mortality rate. Thermography as an adjunctive method has potential to detect early symptoms of growing precancerous and cancerous cells 8 to 10 years sooner than other modalities for early detection. Thermogrms are usually provided in gray-level images. Human eyes can discern only 60 to 90 just noticeable differences (JNDs), but can distinguish thousands of colors. Pseudo-coloring of thermal images gives better visualization and provides more accurate diagnosis for physicians. In this paper, we propose four pseudo-coloring algorithms, the first two algorithms are in HSI color space and the other two are in CIE L*a*b*. Moreover, we compare the results of the four proposed algorithms with each other and with the previously proposed method by Zahedi et al. For a better evaluation, we consider the results both subjectively and objectively. For objective evaluation we use chromatism curve. A flat and uniform chromatism curve is representative of the fact that different colors are perceived equally important. Experimental results show that the algorithm designed in CIE L*a*b* color space is superior to the other methods. Copyright © 2013 American Scientific Publishers All rights reserved.