Breast thermogram analysis using entropy minimization based multilevel color thresholding

Authors: Manoj Kumar Naik et al.

Journal: Applied Soft Computing, Elsevier

Article download link: https://authors.elsevier.com/c/1dvSN5aecSjwE4

Source code: MATLAB Central

DOI: https://doi.org/10.1016/j.asoc.2021.107955

Abstract: Breast cancer is one of the leading causes of death in women due to the abnormal growth of cells known as a tumour. Thermography is an imaging technique used to capture infrared radiation and generate a thermogram. The major advantages of thermography are contactless, radiation-free, painless, and real-time screening. The thermogram is used further in a pathological investigation. However, in the modern-day,?machine intelligence?technologies are used for the analysis of breast thermograms, which assist the expert in decision making. The machine intelligence technique requires a thresholding image during the?preprocessing stage, which warrants an efficient thresholding method. Here, we investigate the multilevel thresholding objective function to minimize the information regarding the entropic dependence on various classes. A new Equilibrium Slime Mould Algorithm (ESMA) is proposed for colour image thresholding, an improvement of the Slime Mould Algorithm (SMA), by integrating the equilibrium practice in updating the slime mould positions from an equilibrium pool concept of Equilibrium Optimizer (EO). The ESMA performance is compared with well know optimization algorithms and ranked one based on Friedman’s mean rank, when evaluated using 53 test problems. Further, the ESMA is used for the development of an entropy minimization based multilevel colour thresholding method for the analysis of breast thermograms. It is applied in two sets of experiments using grey components and the RGB components of breast thermograms. The encouraging results on the thermogram image analysis are presented. Even more interesting results are seen while evaluating our proposal in terms of different metrics—the peak?signal to noise ratio?(PSNR), the feature similarity (FSIM), and the structure similarity (SSIM). Statistical a nalysis provided reveals the suitability of the technique for the analysis of breast thermograms. The method may assist the medical practitioners, as an additional tool. The ESMA may be useful for solving different optimization problems in the world of engineering.

Citation details: Manoj Kumar Naik, Rutuparna Panda, Ajith Abraham, An entropy minimization based multilevel colour thresholding technique for analysis of breast thermograms using equilibrium slime mould algorithm, Applied Soft Computing, Volume 113, Part B, 2021, 107955. (https://www.sciencedirect.com/science/article/pii/S1568494621008772)