%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.13.14.11
%2 sid.inpe.br/sibgrapi/2015/07.13.14.11.14
%T PathoSpotter: Um Sistema para Classificação de Glomerulopatias a partir de Imagens Histológicas Renais
%D 2015
%A Barros, George Oliveira,
%A Duarte, Ângelo Amâncio,
%A Santos, Washington Luis Conrado dos,
%@affiliation Programa de Pós-Graduação em Computação Aplicada - Universidade Estadual de Feira de Santana
%@affiliation Programa de Pós-Graduação em Computação Aplicada - Universidade Estadual de Feira de Santana
%@affiliation Centro de Pesquisas Gonçalo Muniz - Fundação Osvaldo Cruz
%E Rios, Ricardo Araujo,
%E Paiva, Afonso,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador, BA, Brazil
%8 26-29 Aug. 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K kidney histologycal images, nefropatia, image processing, computer vision, medical image analysis.
%X This paper describes the current state of the research and implementation of PathoSpotter-K, a classification system of glomerulopathies based on histological images from kidney. The process of identify such pathologies from images requires pathologists with great expertise in image classification, because the features of the histological images lead to a subjective analysis. Currently, the PathoSpotter-K yields classifications with 67% accuracy. Other improvements are being implemented to increase the accuracy as also as to collect more images to build a larger dataset in order to assess robustness of the system.
%@language pt
%3 pathospotter.pdf