Classificação e Recuperação de Imagens Baseada em Conteúdo Aplicada a Imagens de Tomografia do Tórax
Resumo
O diagnóstico e o tratamento precoce de nódulos pulmonares podem melhorar significativamente a taxa de sobrevida do paciente. Para um exame do câncer de pulmão, os pacientes são submetidos a exames de raio X, tomografia computadorizada ou ressonância magnética para diferenciar os desenvolvimentos de anomalias no pulmão, possibilitando o uso de computadores para classificação autônoma. Neste trabalho realizamos testes de performance entre métodos baseados em Redes Neurais Convolucionais previamente treinados com a base de imagens ImageNet para a extração de atributos dos nódulos pulmonares. As caracterı́sticas foram classificadas através de modelos de recuperação de imagens baseada em conteúdo.
Referências
Breiman, L. (2001a). Random forests. Machine learning, 45(1):5–32.
Breiman, L. (2001b). Random forests. Mach. Learn., 45(1):5–32.
Chollet, F. (2016). Xception: Deep learning with depthwise separable convolutions.
CoRR, abs/1610.02357.
Gudivada, V. N. and Raghavan, V. V. (1995). Content based image retrieval systems. Computer, 28(9):18–22.
Huang, G., Liu, Z., and Weinberger, K. Q. (2016). Densely connected convolutional networks. CoRR, abs/1608.06993.
Hussain, M., Bird, J. J., and Faria, D. R. (2018). A study on cnn transfer learning for image classification. In UK Workshop on Computational Intelligence, pages 191–202. Springer.
INCA (2019). Câncer de pulmão.
LeCun, Y., Bengio, Y., et al. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10):1995.
Nishio, M., Sugiyama, O., Yakami, M., Ueno, S., Kubo, T., Kuroda, T., and Togashi, K. (2018). Computer-aided diagnosis of lung nodule classification between benign nodule, primary lung cancer, and metastatic lung cancer at different image size using deep convolutional neural network with transfer learning. PloS one, 13(7):e0200721.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Szegedy, C., Ioffe, S., and Vanhoucke, V. (2016). Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR, abs/1602.07261.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567.
Tajbakhsh, N. and Suzuki, K. (2017). Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: Mtanns vs. cnns. Pattern recognition, 63:476–486.
Yuan, J., Liu, X., Hou, F., Qin, H., and Hao, A. (2018). Hybrid-feature-guided lung nodule type classification on ct images. Computers & Graphics, 70:288–299.
Breiman, L. (2001b). Random forests. Mach. Learn., 45(1):5–32.
Chollet, F. (2016). Xception: Deep learning with depthwise separable convolutions.
CoRR, abs/1610.02357.
Gudivada, V. N. and Raghavan, V. V. (1995). Content based image retrieval systems. Computer, 28(9):18–22.
Huang, G., Liu, Z., and Weinberger, K. Q. (2016). Densely connected convolutional networks. CoRR, abs/1608.06993.
Hussain, M., Bird, J. J., and Faria, D. R. (2018). A study on cnn transfer learning for image classification. In UK Workshop on Computational Intelligence, pages 191–202. Springer.
INCA (2019). Câncer de pulmão.
LeCun, Y., Bengio, Y., et al. (1995). Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10):1995.
Nishio, M., Sugiyama, O., Yakami, M., Ueno, S., Kubo, T., Kuroda, T., and Togashi, K. (2018). Computer-aided diagnosis of lung nodule classification between benign nodule, primary lung cancer, and metastatic lung cancer at different image size using deep convolutional neural network with transfer learning. PloS one, 13(7):e0200721.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Szegedy, C., Ioffe, S., and Vanhoucke, V. (2016). Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR, abs/1602.07261.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the inception architecture for computer vision. CoRR, abs/1512.00567.
Tajbakhsh, N. and Suzuki, K. (2017). Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: Mtanns vs. cnns. Pattern recognition, 63:476–486.
Yuan, J., Liu, X., Hou, F., Qin, H., and Hao, A. (2018). Hybrid-feature-guided lung nodule type classification on ct images. Computers & Graphics, 70:288–299.
Publicado
26/12/2019
Como Citar
COUTO JÚNIOR, Helio R. V.; V. E SILVA, Romuere R..
Classificação e Recuperação de Imagens Baseada em Conteúdo Aplicada a Imagens de Tomografia do Tórax. In: ESCOLA REGIONAL DE COMPUTAÇÃO APLICADA À SAÚDE (ERCAS), 7. , 2019, Teresina.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 306-311.
