Support vector machine (SVM) is a new statistical learning method. Compared with the classical machine learning methods, SVM learning discipline is to minimize the structural risk instead of the empirical risk of the classical methods, and it gives better generative performance. Because SVM algorithm is a convex quadratic optimization problem, the local optimal solution is certainly the global optimal one. In this paper a SVM algorithm is applied to detect the micro-calcifications (MCCs) in mammograms for the diagnostics of breast cancer that has not been reported yet. It had been tested with 10 mammograms and the results show that the algorithm can achieve a higher true positive in comparison with artificial neural network (ANN) based on the empirical risk minimization, and is valuable for further study and application in the clinical engineering.
In this paper a novel method for the chromatic analysis of burn scar is proposed. The aim of the algorithm is to evaluate the curative effect and set up the treatment plan pertinently, because the scar color is an impersonal parameter reflects the degree of scar hypertrophy. The method is based on artificial neural network (ANN) by using photoelectrical technique, and composed of three main parts: firstly capture the digital color images of the burn scar using CCD camera, then change the RGB color data of the burn scar into that of HSB color space and emend it using ANN, lastly judge the degree of burn scar hypertrophy by chromatic analysis using ANN again. The experimental results were good conformed to the degrees of scar hypertrophy given by clinical evaluations. It suggests that the chromatic analysis technique of the burn scar is valuable for further study and apply to the clinical engineering.