Análise e comparação de algoritmos de classificação para o diagnóstico de câncer de mama
Abstract
The medical diagnosis based on images presents several computational challenges, including the phases of acquisition, pre-processing, segmentation and classification of the images. This work starts from the analysis of a database of magnetic resonance images of breast tumors (mammograms) and implementation of machine learning algorithms for the comparison of the best classifying model for the diagnosis of breast cancer.
References
INCA 2019, INSTITUTO NACIONAL DE CÂNCER. Disponível em: https://www.inca.gov.br/tipos-de-cancer/cancer-de-mama
FLORIDA, U. of S. DDSM: Digital Database for Screening Mammography. Disponível em: http://www.eng.usf.edu/cvprg/Mammography/Database.html.
SBM 2019, SOCIEDADE BRASILEIRA DE MASTOLOGIA. Disponível em: http://www.sbmastologia.com.br/
HARALICK, R. M. Statistical and structural approaches to texture. Proc. IEEE, vol. 67, no. 5, pp. 786-804, 1979., 1979.
HERBRICH, G. Machine Learning: An Algorithmic Perspective. second edition. [S.l.]: Chapman & Hall/CRC, 2015.
OJALA, M. P. T.; HARWOOD, D. A comparative study of texture measures with classification based on feature distributions. Pattern Recoonition, Vol. 29, No. l, pp. 51 59, 1996., 1996.
