Impact of Feature Selection on Clustering Images ofVertebral Compression Fractures

• Raquel Candido Universidade de São Paulo
• Rafael Lama Universidade de São Paulo
• Natália Chiari Universidade de São Paulo
• Marcello Nogueira-Barbosa Universidade de São Paulo
• Paulo Azevedo Marques Universidade de São Paulo
• Renato Tinós Universidade de São Paulo

DOI: https://doi.org/10.5753/eniac.2020.12176

Resumo

Non-traumatic Vertebral Compression Fractures (VCFs) are generally
caused by osteoporosis (benign VCFs) or metastatic cancer (malignant
VCFs) and the success of the medical treatment strongly depends on a fast and
correct classification of VCFs. Recently, methods for computer-aided diagnosis
(CAD) based on machine learning have been proposed for classifying VCFs. In
this work, we investigate the problem of clustering images of VCFs and the impact
of feature selection by genetic algorithms, comparing the clustering i)with
all features and ii)with feature selection through the purity results. The analysis
of the clusters helps to understand the results of classifiers and difficulties
of differentiating images of different classes by an expert. The results indicate
that features selection improved the separability of clusters and purity. Feature
selection also helps to understand which attributes are most important for
analysing the images of vertebral bodies.

Palavras-chave: Feature Selection, Genetic Algorithms, Clustering, Vertebral Compression Fractures, Magnetic Resonance Images

Referências

Alelyani, S., Tang, J., and Liu, H. (2018). Feature Selection for Clustering: A Review, pages 29–60.

Azevedo-Marques, P. M. (2001). Diagnóstico auxiliado por computador na radiologia. Radiologia Brasileira, 34(5):285–293.

Berkhin, P. (2002). Survey of Clustering Data Mining Techniques. Accrue Software.

Frighetto-Pereira, L., Menezes-Reis, R., Metzner, G. A., Rangayyan, R. M., NogueiraBarbosa, M. H., and Azevedo-Marques, P. M. (2015). Classification of vertebral compression fractures in magnetic resonance images using shape analysis. In 2015 E-Health and Bioengineering Conference (EHB), pages 1–4. IEEE.

Genant, H. K., Wu, C. Y., Van Kuijk, C., and Nevitt, M. C. (1993). Vertebral fracture assessment using a semiquantitative technique. Journal of bone and mineral research, 8(9):1137–1148.

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

Hruschka, E. R., Campello, R. J. G. B., Freitas, A., and Carvalho, A. C. P. L. F. (2009). A survey of evolutionary algorithms for clustering. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 39(2):133–155.

Kasai, S., Li, F., Shiraishi, J., Li, Q., and Doi, K. (2006). Computerized detection of vertebral compression fractures on lateral chest radiographs: Preliminary results with a tool for early detection of osteoporosis. Medical Physics, 33(12):4664–4674.

Lama, R. S. D. (2018). Uso de redes neurais convolucionais para classificação de fraturas vertebrais por compressão. Undergraduate Thesis, University of São Paulo, Ribeirão Preto, Brazil.

MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, pages 281–297.

Raineri, L. T. (2018). Seleção de atributos baseada em algoritmos genéticos para o plema de predição de fraturas vertebrais por compressão. Undergraduate Thesis,versity of São Paulo, Ribeirão Preto, Brazil.

Ribeiro, E., Nogueira-Barbosa, M. H., Rangayyan, R., and Azevedo-Marques, P. M. d. (2012). Detection of vertebral compression fractures in lateral lumbar x-ray images. In XXIII Congresso Brasileiro em Engenharia Biomédica (CBEB), pages 1–4.

Shen, D., Wu, G., and Suk, H.-I. (2017). Deep learning in medical image analysis. Annual review of biomedical engineering, 19:221–248.

Tehranzadeh, J. and Tao, C. (2004). Advances in MR Imaging of Vertebral Collapse. Seminars in Ultrasound, CT and MRI, 25(6 SPEC. ISS.):440–460.

Tinós, R., Zhao, L., Chicano, F., and Whitley, D. (2018). Nk hybrid genetic algorithm for clustering. IEEE Transactions on Evolutionary Computation, 22(5):748–761.

Van Griethuysen, J. J., Fedorov, A., Parmar, C., Hosny, A., Aucoin, N., Narayan, V., Beets-Tan, R. G., Fillion-Robin, J.-C., Pieper, S., and Aerts, H. J. (2017). Computational radiomics system to decode the radiographic phenotype. Cancer Research, 77(21):e104–e107.

Vasconcelos, J. T. S. (2004). Anatomia Aplicada e Biomecânica da Coluna Vertebral, volume 2 of serie. Etcetera, São Paulo, 2 edition.

Xu, R., W. D. (2005). Survey of clustering algorithms. IEEE Transactions on Neural Networks.

Xue, B., Zhang, M., Browne, W. N., and Yao, X. (2015). A survey on evolutionary computation approaches to feature selection. IEEE Transactions on Evolutionary Computation, 20(4):606–626.