author = "Silva, Joacy Mesquita da and Angelo, Michele F{\'u}lvia and 
                         Santos, Washington L. C. dos and Loula, Angelo C",
          affiliation = "{Universidade Estadual de Feira de Santana (UEFS)} and 
                         {Universidade Estadual de Feira de Santana (UEFS)} and 
                         {Funda{\c{c}}{\~a}o Oswaldo Cruz - Instituto Gon{\c{c}}alo 
                         Moniz} and {Universidade Estadual de Feira de Santana (UEFS)}",
                title = "Aprendizado Profundo na Classifica{\c{c}}{\~a}o de Les{\~o}es 
                         Crescentes Glomerulares: modelos e condi{\c{c}}{\~o}es",
            booktitle = "Proceedings...",
                 year = "2021",
               editor = "Paiva, Afonso and Menotti, David and Baranoski, Gladimir V. G. and 
                         Proen{\c{c}}a, Hugo Pedro and Junior, Antonio Lopes Apolinario 
                         and Papa, Jo{\~a}o Paulo and Pagliosa, Paulo and dos Santos, 
                         Thiago Oliveira and e S{\'a}, Asla Medeiros and da Silveira, 
                         Thiago Lopes Trugillo and Brazil, Emilio Vital and Ponti, Moacir 
                         A. and Fernandes, Leandro A. F. and Avila, Sandra",
         organization = "Conference on Graphics, Patterns and Images, 34. (SIBGRAPI)",
            publisher = "IEEE Computer Society",
              address = "Los Alamitos",
             keywords = "deep learning, glomerular crescent, nephropathology.",
             abstract = "Glomeruli are structures in the kidneys, responsible for filtering 
                         the blood, that can be affected by several lesions, such as the 
                         glomerular crescent, which is characterized by abnormal cell 
                         proliferation. In this work, different models and conditions for 
                         the application of deep learning are to evaluated in the task of 
                         classifying glomerular crescent histopathological images. The 
                         pre-trained networks Xception, InceptionV3, MobileNet, VGG16 and 
                         ResNet50 were compared, by applying to the classification of 
                         images with crescent vs normal glomeruli. Comparing the accuracy, 
                         precision, recall and f1-score of the models, the ResNet50 showed 
                         significantly better performance than the other networks, in all 
                         measures. The application of data augmentation did not result in a 
                         significant improvement in the results in this case. In an 
                         experiment of classification of crescent vs non-crescent 
                         glomeruli, adding images of three other lesions to the database, 
                         the application of Focal Loss presented greater accuracy and 
  conference-location = "Gramado (Virtual), Brazil",
      conference-year = "October 18th to October 22nd, 2021",
             language = "pt",
           targetfile = "
        urlaccessdate = "2022, Jan. 24"