Estudo e Implementação de Algoritmos de Agrupamento e de Rotulação Aplicados no Diagnóstico por Imagens de Patologias Renais

• Arthur Basílio UFPI
• Pedro da Silva UFPI
• Vinícius Machado UFPI
• Nayze Aldemann UFPI

DOI: https://doi.org/10.5753/ercemapi.2020.11484

Abstract

This article proposes the application of clustering and labeling algorithms to aid in the diagnosis of renal pathologies. The information is extracted from the renal images provided in conjunction with the database containing nephrology diagnostic records. Through unsupervised learning algorithms, different groups are formed. Through the labeling algorithm, the main attributes that characterize each group are revealed, facilitating their understanding. The article also demonstrates the influence of such information extracted from the images, as well as the aid in the knowledge acquisition process promoted by the grouping and labeling.

References

Fayyad, U.M., Piatetsky-shapiro, G., Smyth, P. (1996) “Data Mining to Knowledge in Databases”, AI Magazine, Menlo Park, v.17.

Gonzalez, R.C., Woods, R.E. (2009) “Digital image processing”, Prentice Hall, Nova Jersey, v.2.

Santos, C.N. (2005) “Aprendizado de máquina na identificação de sintagmas nominais: O caso do português brasileiro”

Barber, D. (2012) “Bayesian Reasoning and Machine Learning”, Cambridge University, New York, NY.

Lucas, A.L., Vinicius, P.M. and Ricardo, A.L.R (2014) “Automatic Cluster Labeling through Artificial Neural Networks” International Joint Conference on Neural Networks (IJCNN), Beijin, China. Pedregosa, et al. (2011) “Scikit-learn: Machine Learning in Python”, JMLR 12, pp. 2825-2830, https://scikit-learn.org/stable/modules/clustering.html#

Weiner, E. B.O., Alisson, F.P., Sandro, R.F., Silvana, T.F. (2014) “Classificação de Padrões Utilizando Descritores de Textura”, SIMMEC/EMMCOMP, Juiz de Fora, MG.