Comparative performance analysis of machine learning classifiers and dimensionality reduction algorithms in detection of childhood pneumonia

• Rafael T. Sousa UFG
• Oge Marques Florida Atlantic University
• Iwens I. G. Sene Jr Anderson Soares UFG
• Leandro L. G. de Oliveira UFG

Resumo

Este trabalho complementa o PneumoCAD, um sistema de auxílio a diagnóstico para detecção de pneumonia infantil usando imagens radiográficas [Oliveira et al. 2008], com o objetivo de aprimorar a acurácia e robustez do sistema. Nós implementamos e comparamos três classificadores conteporâneos, que são: Naı̈ve Bayes, K-Nearest Neighbor (KNN), e Support Vector Machines (SVM), combinados com três algoritmos de redução de dimensionalidade: Sequential Forward Elimination (SFE), Principal Component Analysis (PCA), e Kernel Principal Component Analysis (KPCA). Os resultados demonstram que o Naı̈ve Bayes combinado com o KPCA produz os melhores resultados.

Referências

Abe, S. (2010). Support Vector Machines for Pattern Classification. Springer.

Bashar, M. K., Matsumoto, T., and Ohnishi, N. (2003). Wavelet transform-based locally orderless images for texture segmentation. Pattern Recogn. Lett., 24(15):2633–2650.

Burges, C. J. C. (1998). A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov., 2(2):121–167.

Cheng, S.-C. (2003). Content-based image retrieval using moment-preserving edge detection. Image and Vision Computing, 21(9):809 – 826.

Cherian, T., Mulholland, E., Carlin, J., Ostensen, H., Amin, R., de Campo, M., Greenberg, D., Lagos, R., Lucero, M., Madhi, S., O′Brien, K., Obaro, S., and Steinhoff, M. (2005). Standardized interpretation of paediatric chest radiographs for the diagnosis of pneumonia in epidemiological studies. Bull. World Health Organ., 83(5):353–359.

Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. Information Theory, IEEE Transactions on, 13(1):21–27.

Depeursinge, A., Iavindrasana, J., Hidki, A., Cohen, G., Geissbuhler, A., Platon, A., Poletti, P.-A., and Müller, H. (2012). Comparative performance analysis of state-of-the-art classification algorithms applied to lung tissue categorization. Journal Digit Imaging, 23(1):1830.

Doi, K., MacMahon, H., Katsuragawa, S., Nishikawa, R. M., and Jiang, Y. (1999). Computer-aided diagnosis in radiology: potential and pitfalls. European Journal of Radiology, 31(2):97 – 109.

Guyon, I. and Elisseeff, A. (2003). An introduction to variable and feature selection. J. Mach. Learn. Res., 3:1157–1182.

Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The weka data mining software: an update. SIGKDD Explor. Newsl., 11(1):10–18.

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.

Hotelling, H. (1933). Analysis of complex statistical variables into principal components. Journal of Educational Psychology, 24(6):417–441.

Huang, J. and Ling, C. (2005). Using auc and accuracy in evaluating learning algorithms. Knowledge and Data Engineering, IEEE Transactions on, 17(3):299–310.

Huang, P. W. and Dai, S. K. (2004). Design of a two-stage content-based image retrieval system using texture similarity. Inf. Process. Manage., 40(1):81–96.

Kokare, M., Biswas, P. K., and Chatterji, B. N. (2005). Texture image retrieval using new rotated complex wavelet filters. Trans. Sys. Man Cyber. Part B, 35(6):1168–1178.

Kokare, M., Chatterji, B. N., and Biswas, P. K. (2004). Cosine-modulated wavelet based texture features for content-based image retrieval. Pattern Recogn. Lett., 25(4):391–398.

Ladha, L. and Deepa, T. (2011). feature selection methods and algorithms. International Journal on Computer Science and Engineering, 3(5):1787–1797.

Levine, O. S., Lagos, R., Munoz, A., Villaroel, J., Alvarez, A. M., Abrego, P., and Levine, M. M. (1999). Defining the burden of pneumonia in children preventable by vaccination against haemophilus influenzae type b. Pediatr. Infect. Dis. J., 18(12):1060–1064.

Macedo, S. O. d. and Oliveira, L. L. G. d. (2012). Desenvolvimento de um sistema de auxílio ao diagnóstico de pneumonia na infância utilizando visão computacional. In Workshop de Visão Computacional.

Oliveira, L. L. G., e Silva, S. A., Ribeiro, L. H. V., de Oliveira, R. M., Coelho, C. J., and Andrade, A. L. S. S. (2008). Computer-aided diagnosis in chest radiography for detection of childhood pneumonia. I. J. Medical Informatics, 77(8):555–564.

Schölkopf, B., Smola, A., and Müller, K.-R. (1998). Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput., 10(5):1299–1319.

van der Maaten, L. (2013). Matlab toolbox for dimensionality reduction. v0.8.1.

van der Maaten, L. J. P., Postma, E. O., and van den Herik, H. J. (2009). Dimensionality Reduction: A Comparative Review. Technical report, Tilburg University.

WHO (2001). Standardization of interpretation of chest radiographs for the diagnosis of pneumonia in children. Technical report, World Health Organization: Department of Vaccines and Biologicals.

WHO (2012). Pneumonia, fact sheet n◦331. Technical report, World Health Organization.

Yao, J., Dwyer, A., Summers, R. M., and Mollura, D. J. (2011). Computer-aided diagnosis of pulmonary infections using texture analysis and support vector machine classification. Academic Radiology, 18(3):306–14.

Young, M. and Marrie, T. J. (1994). Interobserver variability in the interpretation of chest roentgenograms of patients with possible pneumonia. Arch Intern Med, 154:2729–32.