RESUMO
In neuroimage analysis, the automatic identification of symmetry plane has various applications. Despite the considerable amount of research, this remains an open problem. Most of the existing work based on image intensity is either sensitive to strong noise or not applicable to different imaging modalities. This paper presents a novel approach for identifying symmetry plane in three-dimensional brain magnetic resonance (MR) images based on the concepts of fractal dimension and lacunarity analysis which characterizes the complexity and homogeneity of an object. Experimental results, evaluation, and comparison with two other state-of-the-art techniques show the accuracy and the robustness of our method.
Assuntos
Inteligência Artificial , Encéfalo/anatomia & histologia , Fractais , Interpretação de Imagem Assistida por Computador/métodos , Imageamento Tridimensional/métodos , Imageamento por Ressonância Magnética/métodos , Reconhecimento Automatizado de Padrão/métodos , Algoritmos , Humanos , Aumento da Imagem/métodos , Reprodutibilidade dos Testes , Sensibilidade e EspecificidadeRESUMO
UNLABELLED: BiVisu is an open-source software tool for detecting and visualizing biclusters embedded in a gene expression matrix. Through the use of appropriate coherence relations, BiVisu can detect constant, constant-row, constant-column, additive-related as well as multiplicative-related biclusters. The biclustering results are then visualized under a 2D setting for easy inspection. In particular, parallel coordinate (PC) plots for each bicluster are displayed, from which objective and subjective cluster quality evaluation can be performed. AVAILABILITY: BiVisu has been developed in Matlab and is available at http://www.eie.polyu.edu.hk/~nflaw/Biclustering/.