Detecção de Doenças em Imagens de Raios-X da Coluna Lombo-Sacra com Convnets

  • Pablo Vieira UFPI /
  • Luis Vogado UFPI /
  • Lucas Lopes UFPI /
  • Ricardo Lira UFPI /
  • Pedro Santos Neto UFPI /
  • Deborah Magalhães UFPI
  • Romuere Silva UFPI


Ao longo dos anos, o uso de sistemas CAD no auxilio a diagnósticos vem se tornado mais importante. Um exame que possibilita várias aplicações CAD é o de Lombo-Sacra. Esse exame fornece radiografias detalhadas da coluna vertebral, especificamente das regiões lombar, sacral e coccígea permitindo detectar doenças como artrose, escoliose, espondilartrose, lordose, osteófitos, redução do espaço discal, dentre outras. Nesse contexto, desenvolvemos uma metodologia de sistema CAD baseado em Deep-learning para atuar em Lombo-sacra. Para tal, utilizamos um conjunto de dados contendo 16,024 exames, mais heterogêneo que os do estado da arte. Além disso, desenvolvemos um ensemble na classificação utilizando imagens frontais e laterais do mesmo exame, o que permite classificar um número maior de patologias, o que torna o processo ainda mais preciso diminuindo assim os falsos positivos.


Anouar, O. I. B. P. L. C. C. D. B. L. B. (2019). Classification of coronal imbalance in adult scoliosis and spine deformity: a treatment-oriented guideline. European Spine Journal.

Breiman, L. (2001). Random forests. Machine Learning, 45(1):5-32.

Chen, T. and Guestrin, C. (2016). Xgboost. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

Cherukuri, M., Stanley, R., Long, R., Antani, S., and Thoma, G. (2004). Anterior osteophyte discrimination in lumbar vertebrae using size-invariant features. Computerized Medical Imaging and Graphics, 28(1):99 - 108.

Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3):273-297.

Drake, R., Vogl, W., and Mitchell, A. (2019). Gray's Anatomy for Students. Gray's Anatomy Series. Elsevier.

Esmail, K. M., El-Din, H. E., and A., S. M. (2020). Cascaded deep learning classifiers for computer-aided diagnosis of covid-19 and pneumonia diseases in x-ray scans. Complex Intelligent Systems.

Food, U. and Administration, D. (2019). Medical x-ray imaging. [link].

Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., and Wichmann, F. A. (2020). Shortcut learning in deep neural networks.

Gibson, E., Hu, Y., Huisman, H. J., and Barratt, D. C. (2017). Designing image segmentation studies: Statistical power, sample size and reference standard quality. Medical Image Analysis, 42:44-59.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770-778.

Jaremko Jacob, Poncet Philippe, R. J. H. J. D. J. L. H. Z. R. (2001). Estimation of spinal deformity in scoliosis from torso surface cross sections. Spine, 26:1583-1591.

Kingma, D. P. and Ba, J. (2017). Adam: A method for stochastic optimization.

Lee, S., Choe, E., Kang, H., Yoon, J., and Kim, H. (2019). The exploration of feature extraction and machine learning for predicting bone density from simple spine x-ray images in a korean population. Skeletal Radiology, 49.

Li, X., Shen, L., Xie, X., Huang, S., Xie, Z., Hong, X., and Yu, J. (2020). Multi-resolution convolutional networks for chest x-ray radiograph based lung nodule detection. Artificial Intelligence in Medicine, 103:101744.

O.A., Y. A. D. A. P. (2019). Spondyloarthrosis: pathogenesis, clinic, diagnosis and treatment (literature review and own experience). Journal of Clinical Practice, 10(4):61- 73.

Otsu, N. (1979). A Threshold Selection Method from Gray-level Histograms. IEEE Transactions on Systems, Man and Cybernetics, 9(1):62-66.

Pan Yaling, Chen Qiaoran, C. T. W. H. Z. X. F. Z. L. Y. (2019). Evaluation of a computeraided method for measuring the cobb angle on chest x-rays. European Spine Journal, 28.

Paras., L. (2017). Deep Convolutional Neural Networks for Endotracheal Tube Position and X-ray Image Classification: Challenges and Opportunities. Journal of Digital Imaging.

Perrone, M. and Cooper, L. (1993). When networks disagree: Ensemble methods for hybrid neural networks. Neural networks for speech and image processing.

Pizer, S. M., Johnston, R. E., Ericksen, J. P., Yankaskas, B. C., and Muller, K. E. (1990). Contrast-limited adaptive histogram equalization: Speed and effectiveness. IEEE.

Popescu, M.-C., Balas, V. E., Perescu-Popescu, L., and Mastorakis, N. (2009). Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems, 8(7):579-588.

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., and Fei-Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3):211-252.

Selvaraju, R. R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., and Batra, D. (2016). Grad-cam: Why did you say that? Shorten Connor, K. T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data.

Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556.

Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.

Stanley Ronald, L. R. (2001). A radius of curvature-based approach to cervical spine vertebra image analysis. Biomedical sciences instrumentation, 37:385-90.

Tajbakhsh, N., Shin, J., Gurudu, S., Hurst, R., Kendall, C., Gotway, M., and Liang, J. (2016). Convolutional neural networks for medical image analysis: Full training or fine tuning? IEEE Transactions on Medical Imaging, 35(5):1299-1312.

Telea, A. (2004). An image inpainting technique based on the fast marching method. Journal of Graphics Tools, 9(1):23-34.

Tsantili-Kakoulidou Anna, Horng Ming-Huwi, K. C.-P. F. M.-J. L. C.-J. S. Y.-N. (2019). Cobb angle measurement of spine from x-ray images using convolutional neural network. Computational and Mathematical Methods in Medicine, pages 195 - 199.

Veronezi, C. C. D., Simã, P. W. T. d. A., Santos, R. L. d., Rocha, E. L. d., Melã, S., Mattos, M. C. A. d., and Cechinel, C. (2011). Computational analysis based on artificial neural networks for aiding in diagnosing osteoarthritis of the lumbar spine. Revista Brasileira de Ortopedia, 46:195 - 199.

Vieira, P., Sousa, O., Magalhães, D., Rabêlo, R., and Silva, R. (2021a). Detecting pulmonary diseases using deep features in x-ray images. Pattern Recognition, 119:108081.

Vieira, P. A., Magalhães, D. M., Carvalho-Filho, A. O., Veras, R. M., Rabêlo, R. A., and Silva, R. R. (2021b). Classification of covid-19 in x-ray images with genetic finetuning. Computers Electrical Engineering, 96:107467.

Weng, C.-H., Wang, C.-L., Huang, Y.-J., Yeh, Y.-C., Fu, C.-J., Yeh, C.-Y., and Tsai, T.-T. (2019). Artificial intelligence for automatic measurement of sagittal vertical axis using resunet framework. Journal of Clinical Medicine, 8:1826.

Zech, J. R., Badgeley, M. A., Liu, M., Costa, A. B., Titano, J. J., and Oermann, E. K. (2018). Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLOS Medicine, 15(11):1-17.

Zeng, Y., Liu, X., Xiao, N., Li, Y., Jiang, Y., Feng, J., and Guo, S. (2020). Automatic diagnosis based on spatial information fusion feature for intracranial aneurysm. IEEE Transactions on Medical Imaging, 39(5):1448-1458.
Como Citar

Selecione um Formato
VIEIRA, Pablo; VOGADO, Luis; LOPES, Lucas; LIRA, Ricardo; SANTOS NETO, Pedro; MAGALHÃES, Deborah; SILVA, Romuere. Detecção de Doenças em Imagens de Raios-X da Coluna Lombo-Sacra com Convnets. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 22. , 2022, Teresina. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 . p. 299-310. ISSN 2763-8952. DOI:

Artigos mais lidos do(s) mesmo(s) autor(es)