Classificação de Doenças Intersticiais Pulmonares Difusas através de Tomografia Computadorizada de Alta-Resolução

• Isadora Cardoso UFAL
• Heitor Ramos UFAL
• Eliana Almeida UFAL

DOI: https://doi.org/10.5753/sbcas.2016.9908

Abstract

The goal of this work is to help the development of a computer-aided diagnosis of lung diseases. In this first stage we used principal component analysis (PCA), linear discriminant analysis (LDA) and k-nearest neighbors algorithm (KNN) to classify 3252 regions of interest (ROI) of High-resolution computed tomography of the chest into 6 lung patterns. From each ROI we extracted 28 features, which were used to evaluate the performance of two dimensionality reduction techniques (PCA and LDA). We further applied KNN (K = 5) to classify the ROI into the correspondent lung pattern. We achieved 80,82% correct classification rate using 13 dimensions with PCA and 83,74% using 5 dimensions with LDA.

References

Almeida, E., Rangayyan, R. M., and Azevedo-Marques, P. M. (2015a). Fuzzy membership functions for analysis of high-resolution CT images of diffuse pulmonary diseases. In 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2015, Milan, Italy, August 25-29, 2015, pages 719–722.

Almeida, E., Rangayyan, R. M., and Azevedo-Marques, P. M. (2015b). Gaussian mixture modeling for statistical analysis of features of high-resolution CT images of diffuse pulmonary diseases. In 2015 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2015, Torino, Italy, May 7-9, 2015, pages 1–5.

Elicker, B., de Castro Pereira, C. A., Webb, R., and Leslie, K. O. (2008). Padr˜oes tomográficos das doenças intersticiais pulmonares difusas com correlação clínica e patológica. In Jornal Brasileiro de Pneumologia, Volume 34, number 9, pages 715–744.

Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural Features for Image Classification. Systems, Man and Cybernetics, IEEE Transactions on, SMC-3(6):610– 621.

James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning: with Applications in R. Springer Texts in Statistics. Springer.

Pereyra, L. C., Rangayyan, R. M., Ponciano-Silva, M., and de Azevedo Marques, P. M. (2014). Fractal analysis for computer-aided diagnosis of diffuse pulmonary diseases in HRCT images. In 2014 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2014, Lisboa, Portugal, June 11-12, 2014, pages 455–460.

Rangayyan, R. (2004). Biomedical Image Analysis. Biomedical Engineering. CRC Press.

Tan, P.-N., Steinbach, M., and Kumar, V. (2005). Introduction to Data Mining, (First Edition). Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA.

Zaki, M. J. and Wagner Meira, J. (2014). Data Mining and Analysis: Fundamental Concepts and Algorithms. Cambridge University Press.