%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2010/08.28.15.30
%2 sid.inpe.br/sibgrapi/2010/08.28.15.30.01
%@doi 10.1109/SIBGRAPI.2010.51
%T Segmentation and classification of histological images - application of graph analysis and machine learning methods
%D 2010
%A Zampirolli, Francisco de Assis,
%A Stransky, Beatriz,
%A Lorena, Ana Carolina,
%A Paulon, Fábio Luis de Melo,
%@affiliation Universidade Federal do ABC
%@affiliation Universidade Federal do ABC
%@affiliation Universidade Federal do ABC
%@affiliation Universidade Federal do ABC
%E Bellon, Olga,
%E Esperança, Claudio,
%B Conference on Graphics, Patterns and Images, 23 (SIBGRAPI)
%C Gramado, RS, Brazil
%8 30 Aug.-3 Sep. 2010
%I IEEE Computer Society
%J Los Alamitos
%S Proceedings
%K image analysis, mathematical morphology, graph analysis, machine learning, tissue.
%X The characterization and quantitative description of histological images is not a simple problem. To reach a final diagnosis, usually the specialist relies on the analysis of characteristics easily observed, such as cells size, shape, staining and texture, but also depends on the hidden information of tissue localization, physiological and pathological mechanisms, clinical aspects, or other etiological agents. In this paper, Mathematical Morphology (MM) and Machine Learning (ML) methods were applied to characterize and classify histological images. MM techniques were employed for image analysis. The measurements obtained from image and graph analysis were fed into Machine Learning algorithms, which were designed and developed to automatically learn to recognize complex patterns and make intelligent decisions based on data. Specifically, a linear Support Vector Machine (SVM) was used to evaluate the discriminatory power of the used measures. The results show that the methodology was successful in characterizing and classifying the differences between the architectural organization of epithelial and adipose tissues. We believe that this approach can be also applied to classify and help.
%@language en
%3 article_sibgrapi_v8.pdf