A Wavelet Neural Network for SAR Image Segmentation

Segmentation of dermoscopy images using wavelet networks

This paper introduces a new approach for the segmentation of skin lesions in dermoscopic images based on wavelet network (WN). The WN presented here is a member of fixed-grid WNs that is formed with no need of training. In this WN, after formation of wavelet lattice, determining shift and scale parameters of wavelets with two screening stage and selecting effective wavelets, orthogonal least squares algorithm is used to calculate the network weights and to optimize the network structure. The existence of two stages of screening increases globality of the wavelet lattice and provides a better estimation of the function especially for larger scales. R, G, and B values of a dermoscopy image are considered as the network inputs and the network structure formation. Then, the image is segmented and the skin lesions exact boundary is determined accordingly. The segmentation algorithm were applied to 30 dermoscopic images and evaluated with 11 different metrics, using the segmentation result obtained by a skilled pathologist as the ground truth. Experimental results show that our method acts more effectively in comparison with some modern techniques that have been successfully used in many medical imaging problems.

An adaptive single-well stochastic resonance algorithm applied to trace analysis of clenbuterol in human urine

Based on the theory of stochastic resonance, an adaptive single-well stochastic resonance (ASSR) coupled with genetic algorithm was developed to enhance the signal-to-noise ratio of weak chromatographic signals. In conventional stochastic resonance algorithm, there are two or more parameters needed to be optimized and the proper parameters values were obtained by a universal searching within a given range. In the developed ASSR, the optimization of system parameter was simplified and automatic implemented. The ASSR was applied to the trace analysis of clenbuterol in human urine and it helped to significantly improve the limit of detection and limit of quantification of clenbuterol. Good linearity, precision and accuracy of the proposed method ensure that it could be an effective tool for trace analysis and the improvement of detective sensibility of current detectors.