Uma nova abordagem de padrões binários em radiografias de tórax para avançar o diagnóstico de tuberculose
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1349Palavras-chave:
Diagnóstico, Inteligência Artificial, TuberculoseResumo
Objetivo: A tuberculose (TB) afeta milhões de pessoas, principalmente as mais miseráveis, revelando desigualdades sociais. Apesar dos avanços da inteligência artificial (IA) no controle da TB, poucos benefícios chegam aos mais necessitados. Este estudo propõe uma IA otimizada para discriminar casos de TB de indivíduos saudáveis. Método: A abordagem incorpora descritores por congruência de fase e padrões binários locais em um modelo de otimização mínima sequencial (SMO) na análise de radiografias de tórax (RXT). Resultados: A IA otimizada apresenta desempenho superior a abordagens existentes na literatura, entregando valor de especificidade superior a 97% em diferentes bases e cenários de segmentação. Conclusão: A aplicação da IA proposta na análise de RXT pode representar um avanço significativo no controle da TB, especialmente em populações mais necessitadas, pois constitui uma solução acessível e eficaz que abre possibilidades para o desenvolvimento de novos sistemas de apoio ao diagnóstico.
Referências
WHO (2023). Global tuberculosis report 2023. World Health Organization, Geneva. License: CC BY-NC-SA 3.0 IGO.
Kulkarni, S. and Jha, S. (2020). Artificial intelligence, radiology, and tuberculosis: a review. Academic radiology, 27(1):71–75. DOI: https://doi.org/10.1016/j.acra.2019.10.003
Lakhani, P. and Sundaram, B. (2017). Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology, 284(2):574–582. DOI: https://doi.org/10.1148/radiol.2017162326
Jaeger, S., Karargyris, A., Candemir, S. et al. (2013). Automatic screening for tuberculosis in chest radiographs: a survey. Quantitative imaging in medicine and surgery, 3(2):89.
Çallı, E., Sogancioglu, E., van Ginneken, B., van Leeuwen, K. G., and Murphy, K. (2021). Deep learning for chest x-ray analysis: A survey. Medical Image Analysis, 72:102125. DOI: https://doi.org/10.1016/j.media.2021.102125
Jaeger, S., Candemir, S., Antani, S. et al. (2014). Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quantitative imaging in medicine and surgery, 4(6):475.
Sousa, R. T., Marques, O., Curado, G. T. et al. (2014). Evaluation of classifiers to a childhood pneumonia computer-aided diagnosis system. In 2014 IEEE 27th International Symposium on Computer-Based Medical Systems, p. 477–478. IEEE. DOI: https://doi.org/10.1109/CBMS.2014.98
Chauhan, A., Chauhan, D., and Rout, C. (2014). Role of Gist and PHOG features in computer-aided diagnosis of tuberculosis without segmentation. PloS one, 9(11):e112980. DOI: https://doi.org/10.1371/journal.pone.0112980
Singh, N. and Hamde, S. (2019). Tuberculosis detection using shape and texture features of chest X-rays. In Innovations in Electronics and Communication Engineering, p. 43–50. Springer. DOI: https://doi.org/10.1007/978-981-13-3765-9_5
Vajda, S., Karargyris, A., Jaeger, S., et al. (2018) Feature selection for automatic tuberculosis screening in frontal chest radiographs. Journal of medical systems, 42(8):1–11. DOI: https://doi.org/10.1007/s10916-018-0991-9
Fonseca, A. U., Rocha, B. M., Nogueira et al. (2022). Tuberculosis detection in chest radiography: A combined approach of local binary pattern features and monarch butterfly optimization algorithm. In 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC), p. 1408–1413. IEEE. DOI: https://doi.org/10.1109/COMPSAC54236.2022.00223
Xu, T., Cheng, I., Long, R., and Mandal, M. (2013). Novel coarse-to-fine dual scale technique for tuberculosis cavity detection in chest radiographs. EURASIP Journal on Image and Video Processing, 2013(1):1–18. DOI: https://doi.org/10.1186/1687-5281-2013-3
Alfadhli, F. H. O., Mand, A. A., Sayeed, M. S. et al. (2017). Classification of tuberculosis with surf spatial pyramid features. In 2017 International Conference on Robotics, Automation and Sciences (ICORAS), p. 1–5. IEEE. DOI: https://doi.org/10.1109/ICORAS.2017.8308044
Lopes, U. and Valiati, J. F. (2017). Pre-trained convolutional neural networks as feature extractors for tuberculosis detection. Computers in biology and medicine, 89:135–143. DOI: https://doi.org/10.1016/j.compbiomed.2017.08.001
Rajaraman, S., Zamzmi, G., Folio, L. et al. (2021). Chest X-ray bone suppression for improving classification of tuberculosis-consistent findings. Diagnostics, 11(5):840. DOI: https://doi.org/10.3390/diagnostics11050840
Rajaraman, S., Folio, L. R., Dimperio, J. et al. (2021). Improved semantic segmentation of tuberculosis—Consistent findings in chest x-rays using augmented training of modality-specific U-Net models with weak localizations. Diagnostics, 11(4):616. DOI: https://doi.org/10.3390/diagnostics11040616
Nafisah, S. I. and Muhammad, G. (2022). Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence. Neural Computing and Applications, p. 1–21. DOI: https://doi.org/10.1007/s00521-022-07258-6
Pasa, F., Golkov, V., Pfeiffer, F. et al. (2019). Efficient deep network architectures for fast chest X-ray tuberculosis screening and visualization. Scientific reports, 9(1):1–9. DOI: https://doi.org/10.1038/s41598-019-42557-4
Alawi, A. E. B., Al-basser, A., Sallam, A. et a. (2021). Convolutional neural networks model for screening tuberculosis disease. In 2021 International Conference of Technology, Science and Administration (ICTSA), p. 1–5. IEEE. DOI: https://doi.org/10.1109/ICTSA52017.2021.9406520
Rajaraman, S., Antani, S., Candemir, S. et al. (2018). Comparing deep learning models for population screening using chest radiography. In Medical Imaging 2018: Computer-Aided Diagnosis, volume 10575, p. 322–332. SPIE.
Srimathi, D. H., Rose, D. P., et al. (2020). A Comparative Study On Performance Of Pre-Trained Convolutional Neural Networks In Tuberculosis Detection. European Journal of Molecular & Clinical Medicine, 7(3):4852–4858.
Oltu, B., Güney, S., Dengiz, B., and Agıldere, M. (2021). Automated Tuberculosis Detection Using Pre-Trained CNN and SVM. In 2021 44th International Conference on Telecommunications and Signal Processing (TSP), p. 92–95. DOI: https://doi.org/10.1109/TSP52935.2021.9522644
Khobragade, S., Tiwari, A., Patil, C., and Narke, V. (2016). Automatic detection of major lung diseases using chest radiographs and classification by feed-forward artificial neural network. In 2016 IEEE 1st International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES), p. 1–5. DOI: https://doi.org/10.1109/ICPEICES.2016.7853683
Fonseca, A. U., Parreira, P. L., da Silva Vieira, G. S. et al. (2024). A novel tuberculosis diagnosis approach using feedforward neural networks and binary pattern of phase congruency. Intelligent Systems with Applications, 21:200317. DOI: https://doi.org/10.1016/j.iswa.2023.200317
Fonseca, A. U., Felix, J. P., Vieira, G. S. et al. (2023). Diagnosticando Tuberculose com Redes Neurais Artificiais e Recursos BPPC. Journal of Health Informatics, 15(Especial). DOI: https://doi.org/10.59681/2175-4411.v15.iEspecial.2023.1106
Platt, J. (1998). Fast training of support vector machines using sequential minimal optimization. In Advances in Kernel Methods - Support Vector Learning. MIT Press. DOI: https://doi.org/10.7551/mitpress/1130.003.0016
Reeves, S. and Zhe, Z. (1999). Sequential algorithms for observation selection. IEEE Transactions on Signal Processing, 47(1):123–132. DOI: https://doi.org/10.1109/78.738245
Gozes, O. and Greenspan, H. (2019). Deep feature learning from a hospital-scale chest x-ray dataset with application to TB detection on a small-scale dataset. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), p. 4076–4079. IEEE. DOI: https://doi.org/10.1109/EMBC.2019.8856729
Downloads
Publicado
Como Citar
Edição
Seção
Licença
Este trabalho está licenciado sob uma licença Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
A submissão de um artigo ao Journal of Health Informatics é entendida como exclusiva e que não está sendo considerada para publicação em outra revista. A permissão dos autores para a publicação de seu artigo no J. Health Inform. implica na exclusiva autorização concedida aos editores para incluí-lo na revista. Ao submeter um artigo, ao autor será solicitada a permissão eletrônica de um Termo de Transferência de Direitos Autorais. Uma mensagem eletrônica será enviada ao autor correspondente confirmando o recibo do manuscrito e o aceite da Declaração de Direito Autoral.
