Using Support Vector Machine and Features Selection on Classification of Early Lung Nodules
Resumo
O cancer de pulmão é o câncer que mais mata no mundo. No entanto, se o diagnóstico for feito no início da doença, as taxas de sobrevida em 1 ano são de aproximadamente 81-85%. Ferramentas de Auxílio ao Diagnóstico por Computador tem um grande potencial para auxiliar os especialistas na determinação da malignidade de um nódulo pulmonar. Neste trabalho, foram utilizados 4 grupos de atributos: Textura 3D, Nitidez da margem 3D, Forma 3D e Intensidade 3D; dois algoritmos de aprendizado de máquina: Support Vector Machine (SVM) e Multilayer Perceptron; e duas técnicas para selecionar os recursos mais relevantes: Relief e Algoritmo Genético Evolucionário (AGE). A classificação com SVM, Relief e AGE alcançou a melhor AUC de 0,856.
Referências
Aerts, H. J. W. L. and et al (2014). Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. In Nature communications, volume 5, n. 4006, pages 1–8.
Akgul, C. B. and et. al. (2011). Content-based image retrieval in radiology: current status and future directions. J Digit Imaging, 24(2):208–222.
Alilou, M. and et al (2014). A Comprehensive Framework for Automatic Detection of Pulmonary Nodules in lung CT Images. Image Analysis & Stereology, 33(1):13–27.
Armato, S. G. and et al (2011). The lung image database consortium (lidc) and image database resource initiative (idri): A completed reference database of lung nodules on ct scans. Medical Physics, 38(2):915–931.
Bartholmai, B. J. and et al (2015). Pulmonary nodule characterization, including computer analysis and quantitative features. Journal of Thoracic Imaging, 30(2):139–156.
Chandrashekar, G. and Sahin, F. (2014). A survey on feature selection methods. Computer and Electrical Engineering, 40:16–28.
Choi, W. and Choi, T. (2013). Automated pulmonary nodule detection system in computed tomography images: A hierarchical block classification approach. Entropy, 15:507–523.
Choi, W. and T., C. (2014). Automated pulmonary nodule detection based on threedimensional shape-based feature descriptor. Computer Methods and Programs in Biomedicine, 113:37–54.
Chuquicusma, M. and et al (2017). How to fool radiologists with generative adversarial networks? a visual turing test for lung cancer diagnosis. CoRR, abs/1710.09762.
Ciompi, F. and et al (2017). Towards automatic pulmonary nodule management in lung cancer screening with deep learning. In Scientific reports.
Dhara, A. K. and et al (2016). A combination of shape and texture features for classification of pulmonary nodules in lung ct images. Journal of Digital Imaging, pages 1–10.
Dilger, S. K. and et al (2015). Improved pulmonary nodule classification utilizing lung parenchyma texture features. Proc. SPIE, 9414:94142T–10.
Felix, A., Juior, J., Oliveira, M., and Machado, A. (2016). Using 3d texture and margin sharpness features on classification of small pulmonary nodules. Patterns amd Images (SIBGRAPI).
Ferreira-Junior, J. R., Oliveira, M. C., and de Azevedo-Marques, P. M. (2016). Cloudbased nosql open database of pulmonary nodules for computer-aided lung cancer diagnosis and reproducible research. Journal of Digital Imaging, pages 1–14.
Gillies, R., Kinahan, P., and Hricak, H. (2016). Radiomics: Images are more than pictures, they are data. Radiology, 278(2):563–577. PMID: 26579733.
Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6):610– 621.
INCA (2020). Inca, http://www.inca.gov.br/. Acesssado em 08-02-2020. junior, J., Oliveira, M., and Azevedo-Marques, P. (2016). Cloud-based nosql open database of pulmonary nodules for computer-aided lung cancer diagnosis and reproducible research. J Digit Imaging, 29(6):716–729.
Knight, S. and et, a. (2017). Progress and prospects of early detection in lung cancer. Royal Society Journals, 7(9):170070.
Lee, P. and et al. Rapidminer studio. Available in https://rapidminer.com/ products/studio/.
Madero Orozco, H. and et al (2015). Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. BioMedical Engineering OnLine, 14(1).
Neal, R., Sun, F., Herman, J., and Callister, M. (2019). Lung cancer. BMJ, 365.
Reeves, A., Xie, Y., and Jirapatnakul, A. (2015). Automated pulmonary nodule ct image characterization in lung cancer screening. International Journal of Computer Assisted Radiology and Surgery, 11(1):73–88.
Revees, A. P. and et al (2006). On measuring the change in size of pulmonary nodules. IEEE Transactions on Medical Imaging, 25(4):435–450.
Scholkopf, B. and Smola, A. J. (2001). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, MA, USA.
Shewaye, T. N. and Mekonnen, A. A. (2016). Benign-malignant lung nodule classification with geometric and appearance histogram features. CoRR, abs/1605.08350.
Siegel, R. L., Miller, K. D., and DMV, A. J. (2017). Cancer statistics, 2017. Journal CA CANCER, 67(1):7–30.
Tammemagi, M. and Lam, S. (2014). Screening for Lung Cancer Using Low Dose Computed Tomography. BMJ, 348.
Wu, H. and et. al. (2013). Combination of radiological and gray level co-occurrence matrix textural features used to distinguish solitary pulmonary nodules by computed tomography. J Digit Imaging, 26(4):797–802.
Xu, J. and et al (2012). Quantifying the margin sharpness of lesions on radiological images for content-based image retrieval. Medical Physics, 39(9):5405–5418.
Yan, R. and et, a. (2018). The use of low-dose ct intra- and extra-nodular image texture features to improve small lung nodule diagnosis in lung cancer screening. In 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 Conference Proceedings, pages 1–4. Institute of Electrical and Electronics Engineers Inc.
Zappa, C. and Mousa, S. (2016). Non-small cell lung cancer: current treatment and future advances. Translational Lung Cancer Research, 5(3):288–300.
Akgul, C. B. and et. al. (2011). Content-based image retrieval in radiology: current status and future directions. J Digit Imaging, 24(2):208–222.
Alilou, M. and et al (2014). A Comprehensive Framework for Automatic Detection of Pulmonary Nodules in lung CT Images. Image Analysis & Stereology, 33(1):13–27.
Armato, S. G. and et al (2011). The lung image database consortium (lidc) and image database resource initiative (idri): A completed reference database of lung nodules on ct scans. Medical Physics, 38(2):915–931.
Bartholmai, B. J. and et al (2015). Pulmonary nodule characterization, including computer analysis and quantitative features. Journal of Thoracic Imaging, 30(2):139–156.
Chandrashekar, G. and Sahin, F. (2014). A survey on feature selection methods. Computer and Electrical Engineering, 40:16–28.
Choi, W. and Choi, T. (2013). Automated pulmonary nodule detection system in computed tomography images: A hierarchical block classification approach. Entropy, 15:507–523.
Choi, W. and T., C. (2014). Automated pulmonary nodule detection based on threedimensional shape-based feature descriptor. Computer Methods and Programs in Biomedicine, 113:37–54.
Chuquicusma, M. and et al (2017). How to fool radiologists with generative adversarial networks? a visual turing test for lung cancer diagnosis. CoRR, abs/1710.09762.
Ciompi, F. and et al (2017). Towards automatic pulmonary nodule management in lung cancer screening with deep learning. In Scientific reports.
Dhara, A. K. and et al (2016). A combination of shape and texture features for classification of pulmonary nodules in lung ct images. Journal of Digital Imaging, pages 1–10.
Dilger, S. K. and et al (2015). Improved pulmonary nodule classification utilizing lung parenchyma texture features. Proc. SPIE, 9414:94142T–10.
Felix, A., Juior, J., Oliveira, M., and Machado, A. (2016). Using 3d texture and margin sharpness features on classification of small pulmonary nodules. Patterns amd Images (SIBGRAPI).
Ferreira-Junior, J. R., Oliveira, M. C., and de Azevedo-Marques, P. M. (2016). Cloudbased nosql open database of pulmonary nodules for computer-aided lung cancer diagnosis and reproducible research. Journal of Digital Imaging, pages 1–14.
Gillies, R., Kinahan, P., and Hricak, H. (2016). Radiomics: Images are more than pictures, they are data. Radiology, 278(2):563–577. PMID: 26579733.
Haralick, R. M., Shanmugam, K., and Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6):610– 621.
INCA (2020). Inca, http://www.inca.gov.br/. Acesssado em 08-02-2020. junior, J., Oliveira, M., and Azevedo-Marques, P. (2016). Cloud-based nosql open database of pulmonary nodules for computer-aided lung cancer diagnosis and reproducible research. J Digit Imaging, 29(6):716–729.
Knight, S. and et, a. (2017). Progress and prospects of early detection in lung cancer. Royal Society Journals, 7(9):170070.
Lee, P. and et al. Rapidminer studio. Available in https://rapidminer.com/ products/studio/.
Madero Orozco, H. and et al (2015). Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. BioMedical Engineering OnLine, 14(1).
Neal, R., Sun, F., Herman, J., and Callister, M. (2019). Lung cancer. BMJ, 365.
Reeves, A., Xie, Y., and Jirapatnakul, A. (2015). Automated pulmonary nodule ct image characterization in lung cancer screening. International Journal of Computer Assisted Radiology and Surgery, 11(1):73–88.
Revees, A. P. and et al (2006). On measuring the change in size of pulmonary nodules. IEEE Transactions on Medical Imaging, 25(4):435–450.
Scholkopf, B. and Smola, A. J. (2001). Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, MA, USA.
Shewaye, T. N. and Mekonnen, A. A. (2016). Benign-malignant lung nodule classification with geometric and appearance histogram features. CoRR, abs/1605.08350.
Siegel, R. L., Miller, K. D., and DMV, A. J. (2017). Cancer statistics, 2017. Journal CA CANCER, 67(1):7–30.
Tammemagi, M. and Lam, S. (2014). Screening for Lung Cancer Using Low Dose Computed Tomography. BMJ, 348.
Wu, H. and et. al. (2013). Combination of radiological and gray level co-occurrence matrix textural features used to distinguish solitary pulmonary nodules by computed tomography. J Digit Imaging, 26(4):797–802.
Xu, J. and et al (2012). Quantifying the margin sharpness of lesions on radiological images for content-based image retrieval. Medical Physics, 39(9):5405–5418.
Yan, R. and et, a. (2018). The use of low-dose ct intra- and extra-nodular image texture features to improve small lung nodule diagnosis in lung cancer screening. In 2017 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2017 Conference Proceedings, pages 1–4. Institute of Electrical and Electronics Engineers Inc.
Zappa, C. and Mousa, S. (2016). Non-small cell lung cancer: current treatment and future advances. Translational Lung Cancer Research, 5(3):288–300.
Publicado
15/09/2020
Como Citar
LIMA, Lucas; VIEIRA, Thales; COSTA, Evandro; AZEVEDO-MARQUES, Paulo; OLIVEIRA, Marcelo.
Using Support Vector Machine and Features Selection on Classification of Early Lung Nodules. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 20. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 60-71.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2020.11502.
