Optimization of the Fused-DenseNet-Tiny Model Applied to the Detection of COVID-19 and Pneumonia in Chest X-Ray Images
Resumo
The COVID-19 pandemic, faced in recent years, has highlighted the need for new forms of testing that help in the early diagnosis of the disease. An alternative gaining more and more prominence is the use of Artificial Neural Networks, algorithms capable of being trained to identify this and other diseases. However, these architectures have a high demand for hardware resources, making their implementation difficult. In this work, we propose the optimization of the Fused-DenseNet-Tiny Convolutional Neural Network for the detection of COVID-19 and Pneumonia in x-ray images, using the pruning technique. After pruning, a model with a size about 3 times smaller and an accuracy of 97.17% was obtained, without significant loss.
Referências
Abbas, A., Abdelsamea, M. M., and Gaber, M. M. (2021). Classification of covid-19 in chest x-ray images using detrac deep convolutional neural network. Applied Intelligence, 51:854–864.
Al-Falluji, R. A., Katheeth, Z. D., and Alathari, B. (2021). Automatic detection of covid19 using chest x-ray images and modified resnet18-based convolution neural networks. Computers, Materials, & Continua, pages 1301–1313.
Almeida, B. (2021). Covid-19: Mesmo com a vacina, ainda é importante a testagem. Disponível em: https://medicinasa.com.br/importancia-testagem/. Acesso em: 19 de fevereiro de 2023.
Beduin, I. R. O. (2021). Detecção da covid-19 em imagens de raio-x: construindo um novo modelo de aprendizado profundo utilizando automl.
Braga, I. O., Cunha, C. C., Palácio, M. A. V., Brito, S. B. P., and Takenami, I. (2020). Pandemia da covid-19: o maior desafio do século xxi. Vigilância Sanitária em Debate: Sociedade, Ciência & Tecnologia, 8(2):54–63.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258.
Garg, A., Salehi, S., La Rocca, M., Garner, R., and Duncan, D. (2022). Efficient and visualizable convolutional neural networks for covid-19 classification using chest ct. Expert Systems with Applications, 195:116540.
Goldbarg, M. A. S. d. S. (2021). Análise de técnicas de compressão em redes neurais profundas por poda em dataset de imagens. B.S. thesis, Universidade Federal do Rio Grande do Norte.
Haykin, S. (2001). Redes neurais: princípios e prática. Bookman Editora.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.
Hosaki, G. Y. G. Y. and Ribeiro, D. F. (2021). Deep learning: ensinando a aprender.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Iqbal, A. and Aftab, S. (2020). A classification framework for software defect prediction using multi-filter feature selection technique and mlp. International Journal of Modern Education & Computer Science, 12(1).
LeCun, Y., Denker, J., and Solla, S. (1989). Optimal brain damage. Advances in neural information processing systems, 2.
Luz, E., Silva, P., Silva, R., Silva, L., Guimarães, J., Miozzo, G., Moreira, G., and Menotti, D. (2021). Towards an effective and efficient deep learning model for covid-19 patterns detection in x-ray images. Research on Biomedical Engineering, pages 1–14.
Monard, M. C. and Baranauskas, J. A. (2003). Conceitos sobre aprendizado de máquina. Sistemas inteligentes-Fundamentos e aplicações, 1(1):32.
Montalbo, F. J. P. (2021). Diagnosing covid-19 chest x-rays with a lightweight truncated densenet with partial layer freezing and feature fusion. Biomedical Signal Processing and Control, 68:102583.
Montes, G. C., Lattari, L. G., and Coelho, A. M. (2021). Redes neurais convolucionais otimizadas para a detecçao de supernovas. In Anais do XV Brazilian e-Science Workshop, pages 1–8. SBC.
Oliveira, F. M. d. J. et al. (2016). Impacto da pneumonia grave no sistema nervoso centralefeitos de curto e longo prazo. PhD thesis.
Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., and Acharya, U. R. (2020). Automated detection of covid-19 cases using deep neural networks with x-ray images. Computers in biology and medicine, 121:103792.
Sait, U. (2020). Curated chest x-ray image dataset for covid-19. Kaggle Repository.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.
Santos Júnior, E. S. d. (2022). Classificação de pneumonia e covid-19 em imagens de raio-x do tórax através de técnicas de deep learning.
Silva, J. V. S., Matos, L. M., Santos, F., Cerqueira, H. O. M., Macedo, H., Prado, B. O. P., da Silva, G. J. F., and Bispo, K. A. (2022). Combinação de técnicas de compressão de modelos profundos. IEEE Latin America Transactions, 20(3):458–464.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, K. K., Siddhartha, M., and Singh, A. (2020). Diagnosis of coronavirus disease (covid-19) from chest x-ray images using modified xceptionnet. Romanian Journal of Information Science and Technology, 23(657):91–115.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
Wang, L., Lin, Z. Q., and Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific reports, 10(1):1–12.
Al-Falluji, R. A., Katheeth, Z. D., and Alathari, B. (2021). Automatic detection of covid19 using chest x-ray images and modified resnet18-based convolution neural networks. Computers, Materials, & Continua, pages 1301–1313.
Almeida, B. (2021). Covid-19: Mesmo com a vacina, ainda é importante a testagem. Disponível em: https://medicinasa.com.br/importancia-testagem/. Acesso em: 19 de fevereiro de 2023.
Beduin, I. R. O. (2021). Detecção da covid-19 em imagens de raio-x: construindo um novo modelo de aprendizado profundo utilizando automl.
Braga, I. O., Cunha, C. C., Palácio, M. A. V., Brito, S. B. P., and Takenami, I. (2020). Pandemia da covid-19: o maior desafio do século xxi. Vigilância Sanitária em Debate: Sociedade, Ciência & Tecnologia, 8(2):54–63.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1251–1258.
Garg, A., Salehi, S., La Rocca, M., Garner, R., and Duncan, D. (2022). Efficient and visualizable convolutional neural networks for covid-19 classification using chest ct. Expert Systems with Applications, 195:116540.
Goldbarg, M. A. S. d. S. (2021). Análise de técnicas de compressão em redes neurais profundas por poda em dataset de imagens. B.S. thesis, Universidade Federal do Rio Grande do Norte.
Haykin, S. (2001). Redes neurais: princípios e prática. Bookman Editora.
He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.
Hosaki, G. Y. G. Y. and Ribeiro, D. F. (2021). Deep learning: ensinando a aprender.
Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.
Iqbal, A. and Aftab, S. (2020). A classification framework for software defect prediction using multi-filter feature selection technique and mlp. International Journal of Modern Education & Computer Science, 12(1).
LeCun, Y., Denker, J., and Solla, S. (1989). Optimal brain damage. Advances in neural information processing systems, 2.
Luz, E., Silva, P., Silva, R., Silva, L., Guimarães, J., Miozzo, G., Moreira, G., and Menotti, D. (2021). Towards an effective and efficient deep learning model for covid-19 patterns detection in x-ray images. Research on Biomedical Engineering, pages 1–14.
Monard, M. C. and Baranauskas, J. A. (2003). Conceitos sobre aprendizado de máquina. Sistemas inteligentes-Fundamentos e aplicações, 1(1):32.
Montalbo, F. J. P. (2021). Diagnosing covid-19 chest x-rays with a lightweight truncated densenet with partial layer freezing and feature fusion. Biomedical Signal Processing and Control, 68:102583.
Montes, G. C., Lattari, L. G., and Coelho, A. M. (2021). Redes neurais convolucionais otimizadas para a detecçao de supernovas. In Anais do XV Brazilian e-Science Workshop, pages 1–8. SBC.
Oliveira, F. M. d. J. et al. (2016). Impacto da pneumonia grave no sistema nervoso centralefeitos de curto e longo prazo. PhD thesis.
Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., and Acharya, U. R. (2020). Automated detection of covid-19 cases using deep neural networks with x-ray images. Computers in biology and medicine, 121:103792.
Sait, U. (2020). Curated chest x-ray image dataset for covid-19. Kaggle Repository.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520.
Santos Júnior, E. S. d. (2022). Classificação de pneumonia e covid-19 em imagens de raio-x do tórax através de técnicas de deep learning.
Silva, J. V. S., Matos, L. M., Santos, F., Cerqueira, H. O. M., Macedo, H., Prado, B. O. P., da Silva, G. J. F., and Bispo, K. A. (2022). Combinação de técnicas de compressão de modelos profundos. IEEE Latin America Transactions, 20(3):458–464.
Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Singh, K. K., Siddhartha, M., and Singh, A. (2020). Diagnosis of coronavirus disease (covid-19) from chest x-ray images using modified xceptionnet. Romanian Journal of Information Science and Technology, 23(657):91–115.
Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31.
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.
Tan, M. and Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR.
Wang, L., Lin, Z. Q., and Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific reports, 10(1):1–12.
Publicado
06/08/2023
Como Citar
SANTOS JÚNIOR, Eder Silva dos; MAFALDA, Salomão Machado; CHAVEZ, Roger Fredy Larico; ALVAREZ, Ana Beatriz.
Optimization of the Fused-DenseNet-Tiny Model Applied to the Detection of COVID-19 and Pneumonia in Chest X-Ray Images. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 50. , 2023, João Pessoa/PB.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2023
.
p. 320-331.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2023.230771.
