The paper uses a particle swarm optimization (ab. PSO) algorithm to solve the quadratic assignment problem (ab. QAP), and propose a novel particle presentation for the problem. The experimental results on different QAP instances show that this algorithm is able to find good solutions efficiently. PSO has got many successful applications in many continuous domain optimization problems, but is seldom applied in discrete domain. It is a kind of brand-new attempt that this paper uses PSO algorithm to solve QAP problem. It is undoubtedly enlightening us to utilize PSO algorithm to discrete domain problem (especially combinatorial optimization), and it will establish the foundation of further investigation at the same time.

Mammography is an important detection method of breast cancer, and classification of mammographic masses plays an important role in Computer-aided diagnosis (CAD) for breast cancer. In this paper, one novel multi-view information fusion algorithm based on Multi-Agent (MA) method is proposed to improve the accuracy of classification of masses. 128 ROIs (regions of interest) from DDSM database composed by 64 pairs of cranio-caudal (CC) view and medio-lateral oblique (MLO) view were chosen for the experiments, which demonstrated the proposed algorithm improved the accuracy and reduced the false positive rates rather than the other methods.

Breast cancer is one of the most dangerous malignant tumors of women in the world. A particularly important clue of such disease is the presence of clusters of micro-calcifications. However, it is difficult for radiologists to provide both accurate and uniform evaluation for benign or malignant pathologic modifications of micro-calcifications. The radiologists are usually obtained by using human expertise in recognizing the presence of given patterns and types of microcalcifications. In order to automatically detect such clusters and improve the accuracy, in this paper, K-MEANS-based region growing clustering algorithm is proposed to automatically finding clusters of micro-calcifications in the phase of clustering in mammography. The approach has been successfully tested on a standard database of 30 mammographic images, publicly available.

No abstract

No abstract