Applying a Conditional GAN for Bone Suppression in Chest Radiography Images
Resumo
Bone suppression in radiography is a suitable technique to evaluate the health of soft tissues in exams. For instance, these techniques are essential in evaluating chest radiography images during the COVID-19 outbreak. The purpose of this work is to propose an alternative to solve the bone suppression task in chest radiography images using Generative Adversarial Networks (GANs). Specifically, we used a conditional GAN type (cGAN) to provide a bone-suppressed version of the initial image. To quantify the results, it was necessary to review the main metrics and some state-of-the-art papers related to ours. We compared our result to works from the literature that used the same dataset as the proposal or related techniques. The most used dataset was the Japanese Society of Radiological Technology (JSRT) in these works. With this set of images, we reached a PSNR index of 34.96, which was better than that reviewed in the literature, and a similarity coefficient, known as SSIM, of 0.94. As for the loss calculated by MS-SSIM, we obtained the lowest compared to the reviewed works.
Palavras-chave:
Bone Suppression, Generative Adversarial Networks, cGAN's
Referências
Chen, Y., Gou, X., Feng, X., Liu, Y., Qin, G., Feng, Q., Yang, W., and Chen, W. (2019). Bone suppression of chest radiographs with cascaded convolutional networks in wavelet domain. IEEE Access, 7:8346–8357.
Eslami, M., Tabarestani, S., Albarqouni, S., Adeli, E., Navab, N., and Adjouadi, M. (2020). Image-to-images translation for multi-task organ segmentation and bone suppression in chest x-ray radiography. IEEE transactions on medical imaging, 39(7):2553–2565.
Gozes, O. and Greenspan, H. (2020). Bone structures extraction and enhancement in chest radiographs via cnn trained on synthetic data. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pages 858–861. IEEE.
Gusarev, M., Kuleev, R., Khan, A., Rivera, A. R., and Khattak, A. M. (2017). Deep learning models for bone suppression in chest radiographs. In 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pages 1–7. IEEE.
Hore, A. and Ziou, D. (2010). Image quality metrics: Psnr vs. ssim. In 2010 20th international conference on pattern recognition, pages 2366–2369. IEEE.
Hyunh, M.-C. (2021). X-ray bone shadow suppression dataset. IEEE Dataport.
Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134.
Juhász, S., Horváth, Á., Nikházy, L., and Horváth, G. (2010). Segmentation of anatomical structures on chest radiographs. In XII Mediterranean Conference on Medical and Biological Engineering and Computing 2010, pages 359–362. Springer.
Liang, J., Tang, Y.-X., Tang, Y.-B., Xiao, J., and Summers, R. M. (2020). Bone suppression on chest radiographs with adversarial learning. In Medical Imaging 2020: Computer-Aided Diagnosis, volume 11314, page 1131409. International Society for Optics and Photonics.
Matsubara, N., Teramoto, A., Saito, K., and Fujita, H. (2020). Bone suppression for chest x-ray image using a convolutional neural filter. Physical and Engineering Sciences in Medicine, 43(1):97–108.
Matters, I. (2014). Carestream’s new bone suppression software receives fda clearance, now available worldwide.
Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.
Oh, D. Y. and Yun, I. D. (2018). Learning bone suppression from dual energy chest x-rays using adversarial networks. arXiv preprint arXiv:1811.02628.
Oliveira, B., Ziviani, H., Oliveira, J., Viegas, A., and Calvo, D. (2021). Suporte para diagnóstico de covid-19 por meio de classificação automática de imagens de raio-x e modelos explicáveis. In Filho, C. J. A. B., Siqueira, H. V., Ferreira, D. D., Bertol, D. W., and ao de Oliveira, R. C. L., editors, Anais do 15 Congresso Brasileiro de Inteligência Computacional, pages 1–8, Joinville, SC. SBIC.
Pratt, H., Williams, B., Coenen, F., and Zheng, Y. (2017). Fcnn: Fourier convolutional neural networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 786–798. Springer.
Rajaraman, S., Cohen, G., Antani, S., et al. (2021a). A bone suppression model ensemble to improve covid-19 detection in chest x-rays. arXiv preprint arXiv:2111.03404.
Rajaraman, S., Zamzmi, G., Folio, L., Alderson, P., and Antani, S. (2021b). Chest xray bone suppression for improving classification of tuberculosis-consistent findings. Diagnostics, 11(5):840.
Sirazitdinov, I., Kubrak, K., Kiselev, S., Tolkachev, A., Kholiavchenko, M., and Ibragimov, B. (2020). Evaluation of deep learning methods for bone suppression from dual energy chest radiography. In International Conference on Artificial Neural Networks, pages 247–257. Springer.
Sujath, R., Chatterjee, J. M., and Hassanien, A. E. (2020). A machine learning forecasting model for covid-19 pandemic in india. Stochastic Environmental Research and Risk Assessment, 34:959–972.
Wang, S., Yang, D. M., Rong, R., Zhan, X., Fujimoto, J., Liu, H., Minna, J.,Wistuba, I. I., Xie, Y., and Xiao, G. (2019). Artificial intelligence in lung cancer pathology image analysis. Cancers, 11(11):1673.
Yang, W., Chen, Y., Liu, Y., Zhong, L., Qin, G., Lu, Z., Feng, Q., and Chen, W. (2017). Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain. Medical image analysis, 35:421–433.
Zarshenas, A., Liu, J., Forti, P., and Suzuki, K. (2019). Separation of bones from soft tissue in chest radiographs: Anatomy-specific orientation-frequency-specific deep neural network convolution. Medical physics, 46(5):2232–2242.
Zhou, B., Lin, X., Eck, B., Hou, J., and Wilson, D. (2018). Generation of virtual dual energy images from standard single-shot radiographs using multi-scale and conditional adversarial network. In Asian Conference on Computer Vision, pages 298–313. Springer.
Zhou, Z., Zhou, L., and Shen, K. (2020). Dilated conditional gan for bone suppression in chest radiographs with enforced semantic features. Medical Physics, 47(12):6207–6215.
Eslami, M., Tabarestani, S., Albarqouni, S., Adeli, E., Navab, N., and Adjouadi, M. (2020). Image-to-images translation for multi-task organ segmentation and bone suppression in chest x-ray radiography. IEEE transactions on medical imaging, 39(7):2553–2565.
Gozes, O. and Greenspan, H. (2020). Bone structures extraction and enhancement in chest radiographs via cnn trained on synthetic data. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), pages 858–861. IEEE.
Gusarev, M., Kuleev, R., Khan, A., Rivera, A. R., and Khattak, A. M. (2017). Deep learning models for bone suppression in chest radiographs. In 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pages 1–7. IEEE.
Hore, A. and Ziou, D. (2010). Image quality metrics: Psnr vs. ssim. In 2010 20th international conference on pattern recognition, pages 2366–2369. IEEE.
Hyunh, M.-C. (2021). X-ray bone shadow suppression dataset. IEEE Dataport.
Isola, P., Zhu, J.-Y., Zhou, T., and Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134.
Juhász, S., Horváth, Á., Nikházy, L., and Horváth, G. (2010). Segmentation of anatomical structures on chest radiographs. In XII Mediterranean Conference on Medical and Biological Engineering and Computing 2010, pages 359–362. Springer.
Liang, J., Tang, Y.-X., Tang, Y.-B., Xiao, J., and Summers, R. M. (2020). Bone suppression on chest radiographs with adversarial learning. In Medical Imaging 2020: Computer-Aided Diagnosis, volume 11314, page 1131409. International Society for Optics and Photonics.
Matsubara, N., Teramoto, A., Saito, K., and Fujita, H. (2020). Bone suppression for chest x-ray image using a convolutional neural filter. Physical and Engineering Sciences in Medicine, 43(1):97–108.
Matters, I. (2014). Carestream’s new bone suppression software receives fda clearance, now available worldwide.
Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784.
Oh, D. Y. and Yun, I. D. (2018). Learning bone suppression from dual energy chest x-rays using adversarial networks. arXiv preprint arXiv:1811.02628.
Oliveira, B., Ziviani, H., Oliveira, J., Viegas, A., and Calvo, D. (2021). Suporte para diagnóstico de covid-19 por meio de classificação automática de imagens de raio-x e modelos explicáveis. In Filho, C. J. A. B., Siqueira, H. V., Ferreira, D. D., Bertol, D. W., and ao de Oliveira, R. C. L., editors, Anais do 15 Congresso Brasileiro de Inteligência Computacional, pages 1–8, Joinville, SC. SBIC.
Pratt, H., Williams, B., Coenen, F., and Zheng, Y. (2017). Fcnn: Fourier convolutional neural networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 786–798. Springer.
Rajaraman, S., Cohen, G., Antani, S., et al. (2021a). A bone suppression model ensemble to improve covid-19 detection in chest x-rays. arXiv preprint arXiv:2111.03404.
Rajaraman, S., Zamzmi, G., Folio, L., Alderson, P., and Antani, S. (2021b). Chest xray bone suppression for improving classification of tuberculosis-consistent findings. Diagnostics, 11(5):840.
Sirazitdinov, I., Kubrak, K., Kiselev, S., Tolkachev, A., Kholiavchenko, M., and Ibragimov, B. (2020). Evaluation of deep learning methods for bone suppression from dual energy chest radiography. In International Conference on Artificial Neural Networks, pages 247–257. Springer.
Sujath, R., Chatterjee, J. M., and Hassanien, A. E. (2020). A machine learning forecasting model for covid-19 pandemic in india. Stochastic Environmental Research and Risk Assessment, 34:959–972.
Wang, S., Yang, D. M., Rong, R., Zhan, X., Fujimoto, J., Liu, H., Minna, J.,Wistuba, I. I., Xie, Y., and Xiao, G. (2019). Artificial intelligence in lung cancer pathology image analysis. Cancers, 11(11):1673.
Yang, W., Chen, Y., Liu, Y., Zhong, L., Qin, G., Lu, Z., Feng, Q., and Chen, W. (2017). Cascade of multi-scale convolutional neural networks for bone suppression of chest radiographs in gradient domain. Medical image analysis, 35:421–433.
Zarshenas, A., Liu, J., Forti, P., and Suzuki, K. (2019). Separation of bones from soft tissue in chest radiographs: Anatomy-specific orientation-frequency-specific deep neural network convolution. Medical physics, 46(5):2232–2242.
Zhou, B., Lin, X., Eck, B., Hou, J., and Wilson, D. (2018). Generation of virtual dual energy images from standard single-shot radiographs using multi-scale and conditional adversarial network. In Asian Conference on Computer Vision, pages 298–313. Springer.
Zhou, Z., Zhou, L., and Shen, K. (2020). Dilated conditional gan for bone suppression in chest radiographs with enforced semantic features. Medical Physics, 47(12):6207–6215.
Publicado
31/07/2022
Como Citar
ZIVIANI, Hugo Eduardo; CHÁVEZ, Guillermo Cámara; SILVA, Mateus Coelho.
Applying a Conditional GAN for Bone Suppression in Chest Radiography Images. In: SEMINÁRIO INTEGRADO DE SOFTWARE E HARDWARE (SEMISH), 49. , 2022, Niterói.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 25-36.
ISSN 2595-6205.
DOI: https://doi.org/10.5753/semish.2022.222540.
