| Autor: |
Pedro Augusto Pinho Ferraz, Bernardo Augusto Godinho de Oliveira, Alexei Manso Correa Machado, Álvaro Henrique de Araújo Rungue, Willian Antônio Dos Santos, Thiago Melo Machado-Coelho |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
Proceedings XXII Congresso Brasileiro de Automática. |
| ISSN: |
2525-8311 |
| DOI: |
10.20906/cps/cba2018-1178 |
| Popis: |
Studies indicate that breast density is related to the risk of developing cancer since dense breasttissue can hide lesions, causing cancer to be detected at later stages. In this paper we classi cation method using support vector machines (SVM) associated to data reduction techniques to classify mammographic texture. An analysis of the parameters that influence the efectiveness of texture classi cation is also provided. Experiments were conducted on a set of 4,000 mammographic exams from which regions of interest representing the most signi cantly part of the texture of the breast tissue were extracted. Compared to other quantitative results found in the literature, the proposed multi-class SVM method using the radial basis function kernel and tuned parameters proved to be superior while classifying mammographic texture, reaching up to 99% of precision for 10% of recall. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
