Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.04.22.16
%2 sid.inpe.br/sibgrapi/2017/09.04.22.16.45
%T Análise de Imagens de Termografia Dinâmica para Classificação de Alterações na Mama Usando Séries Temporais
%D 2017
%A Andrade, Felipe Jordão Pinheiro de,
%A Paiva, Anselmo Cardoso,
%A Silva, Aristófanes Corrêa,
%@affiliation Universidade Federal do Maranhão
%@affiliation Universidade Federal do Maranhão
%@affiliation Universidade Federal do Maranhão
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ
%8 Oct. 17-20, 2017
%S Proceedings
%I Sociedade Brasileira de Computação
%J Porto Alegre
%K Termografia Dinâmica, Séries Temporais.
%X With the increase in the number of cases of breast cancer in the last years, the need for auxiliary techniques for the detection of the disease is evident. Dynamic thermography can be used as an auxiliary method to the gold standard, the mammography screening. The thermography exam takes advantage of the fact that the lesions present a higher temperature than the healthy neighboring tissues. In this work, we propose a methodology for the transformation of thermal signals into time series, from which features for the classification task will be extracted. In the paper we compare the K-Star and Support Vector Machine classifiers with results of 95.8% accuracy, 93.6% sensitivity and 95.9% specificity.
%@language pt
%3 CameraReady_Sibigrapi_termica.pdf


Close