Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10216/135741
Autor(es): | Justino Duarte Santos Rodrigo de M. S. Veras Romuere R. V. Silva Nayze L. S. Aldeman Flávio H. D. Araújo Angelo A. Duarte João Manuel R. S. Tavares |
Título: | A hybrid of deep and textural features to differentiate glomerulosclerosis and minimal change disease from glomerulus biopsy images |
Data de publicação: | 2021-09 |
Resumo: | The minimal change disease (MCD) and glomerulosclerosis (GS) are two common kidney diseases. Unless adequately treated, these diseases leads to chronic kidney diseases. Accurate differentiation of these two diseases is of paramount importance as their methods of treatment and prognoses are different. Thus, this article propose a method capable of differentiating MCD from GS in glomerulus biopsies images based on a new hybrid deep and texture feature space. We conducted an extensive study to determine the best set of features for image representation. Our feature extraction methodology, which includes Haraliks and geostatistics texture descriptors and pre-trained CNNs, resulted in 13,476 characteristics. We then used mutual information to order the elements by importance and select the best set for differentiating MCD from GS using the random forest classifier. The proposed method achieved an accuracy of 90.3% and a Kappa index of 80.5%. Representation of glomerulus biopsy images with a hybrid of deep and textural features facilitates the accurate differentiation of GS and MCD. |
Assunto: | Ciências Tecnológicas, Ciências médicas e da saúde Technological sciences, Medical and Health sciences |
Áreas do conhecimento: | Ciências médicas e da saúde Medical and Health sciences |
URI: | https://hdl.handle.net/10216/135741 |
Tipo de Documento: | Artigo em Revista Científica Internacional |
Condições de Acesso: | openAccess |
Aparece nas coleções: | FEUP - Artigo em Revista Científica Internacional |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
488780.png | 1st Page | 238.81 kB | image/png | Ver/Abrir |
488780.1.pdf | Paper draft | 8.28 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.