Diagnóstico Automático de Cardiopatia Reumática em Exames Ecocardiográficos
Resumo
A cardiopatia reumática (CR) afeta aproximadamente 39 milhões de pessoas no mundo e é a doença cardíaca adquirida mais comum entre crianças e adolescentes. Ecocardiogramas são o padrão-ouro para o diagnóstico de CR, mas uma escassez de profissionais qualificados impede a implementação em larga escala de programas de prevenção e identificação precoce da doença. Nessa direção, esse trabalho propõe um arcabouço baseado em aprendizado de máquina para lidar com os desafios de identificação automática de CR em exames ecocardiográficos, obtendo uma acurácia de 71,18%. O método também gera informação sobre o processo de diagnóstico através de visualizações temporais (estruturas relevantes em um vídeo) e espaciais (estruturas relevantes em um quadro), facilitando a tomada de decisão de diagnóstico clínico.Referências
Ghorbani, A. et al. (2020). Deep learning interpretation of echocardiograms. npj Digital Medicine, 3(1):1–10.
James, S. et al. (2018). Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the global burden of disease study 2017. The Lancet, 392(10159):1789–1858.
Madani, A., Ong, J. R., Tibrewal, A., and Mofrad, M. R. K. (2018). Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ digital medicine, 1(1):1–11.
Martin-Isla, C. et al. (2020). Image-based cardiac diagnosis with machine learning: A review. Frontiers in Cardiovascular Medicine, 7:1.
Martins, J. et al. (2021). Towards automatic diagnosis of rheumatic heart disease on echocardiographic exams through video-based deep learning. Journal of the American Medical Informatics Association. doi:10.1093/jamia/ocab061.
Martins, J. F. et al. (2022). A multi-task learning approach to classify rheumatic heart disease on echocardiographic imaging. Artificial Intelligence in Medicine (under review).
Nascimento, B. et al. (2016). Echocardiographic prevalence of rheumatic heart disease in brazilian schoolchildren: Data from the provar study. Int. journal of cardiology, 219:439–445.
Nascimento, B. et al. (2020). Deep learning for automatic identification of rheumatic heart disease in echocardiographic screening images: data from the atmosphere-provar study. Journal of the American College of Cardiology, 75(11 Supplement 1):3577–3577.
Nascimento, B. et al. (2021). Spatial-temporal deep-learning for automatic identification of rheumatic heart disease in echocardiographic screening images - data from the provar-atmosphere study. Journal of the American College of Cardiology, 77(18 Supplement 1):3243–3243.
Okello, E. et al. (2013). Cardiovascular complications in newly diagnosed rheumatic heart disease patients at mulago hospital, uganda. Cardiovascular journal of Africa, 24(3):82.
Reményi, B. et al. (2012). World heart federation criteria for echocardiographic diagnosis of rheumatic heart disease—an evidence-based guideline. Nature reviews cardiology, 9(5):297.
Ribeiro, A., Duncan, B., Brant, L., Lotufo, P., Mill, J., and Barreto, S. (2016). Cardiovascular health in brazil: trends and perspectives. Circulation, 133(4):422–433.
Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In Proc. ICCV, pages 4489–4497.
Vos, T. et al. (2015). Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990–2013: a systematic analysis for the global burden of disease study 2013. The Lancet, 386(9995):743–800.
Zhang, J. et al. (2018). Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation, 138(16):1623–1635.
James, S. et al. (2018). Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the global burden of disease study 2017. The Lancet, 392(10159):1789–1858.
Madani, A., Ong, J. R., Tibrewal, A., and Mofrad, M. R. K. (2018). Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. NPJ digital medicine, 1(1):1–11.
Martin-Isla, C. et al. (2020). Image-based cardiac diagnosis with machine learning: A review. Frontiers in Cardiovascular Medicine, 7:1.
Martins, J. et al. (2021). Towards automatic diagnosis of rheumatic heart disease on echocardiographic exams through video-based deep learning. Journal of the American Medical Informatics Association. doi:10.1093/jamia/ocab061.
Martins, J. F. et al. (2022). A multi-task learning approach to classify rheumatic heart disease on echocardiographic imaging. Artificial Intelligence in Medicine (under review).
Nascimento, B. et al. (2016). Echocardiographic prevalence of rheumatic heart disease in brazilian schoolchildren: Data from the provar study. Int. journal of cardiology, 219:439–445.
Nascimento, B. et al. (2020). Deep learning for automatic identification of rheumatic heart disease in echocardiographic screening images: data from the atmosphere-provar study. Journal of the American College of Cardiology, 75(11 Supplement 1):3577–3577.
Nascimento, B. et al. (2021). Spatial-temporal deep-learning for automatic identification of rheumatic heart disease in echocardiographic screening images - data from the provar-atmosphere study. Journal of the American College of Cardiology, 77(18 Supplement 1):3243–3243.
Okello, E. et al. (2013). Cardiovascular complications in newly diagnosed rheumatic heart disease patients at mulago hospital, uganda. Cardiovascular journal of Africa, 24(3):82.
Reményi, B. et al. (2012). World heart federation criteria for echocardiographic diagnosis of rheumatic heart disease—an evidence-based guideline. Nature reviews cardiology, 9(5):297.
Ribeiro, A., Duncan, B., Brant, L., Lotufo, P., Mill, J., and Barreto, S. (2016). Cardiovascular health in brazil: trends and perspectives. Circulation, 133(4):422–433.
Tran, D., Bourdev, L., Fergus, R., Torresani, L., and Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In Proc. ICCV, pages 4489–4497.
Vos, T. et al. (2015). Global, regional, and national incidence, prevalence, and years lived with disability for 301 acute and chronic diseases and injuries in 188 countries, 1990–2013: a systematic analysis for the global burden of disease study 2013. The Lancet, 386(9995):743–800.
Zhang, J. et al. (2018). Fully automated echocardiogram interpretation in clinical practice: feasibility and diagnostic accuracy. Circulation, 138(16):1623–1635.
Publicado
07/06/2022
Como Citar
MARTINS, João Francisco B. S; NASCIMENTO, Erickson R.; PAPPA, Gisele L..
Diagnóstico Automático de Cardiopatia Reumática em Exames Ecocardiográficos. In: CONCURSO DE TESES E DISSERTAÇÕES - SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 22. , 2022, Teresina/PI.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 50-55.
ISSN 2763-8987.
DOI: https://doi.org/10.5753/sbcas_estendido.2022.222716.
