Segmentação de Região Auricular em Imagens Termográficas para Aplicações Médicas em Cardiologia
Resumo
A termografia infravermelha é uma técnica promissora para análise não invasiva da perfusão microvascular, com potencial aplicação na identificação da doença arterial coronariana (DAC), mas que ainda depende de processos manuais e subjetivos para sua análise. Este trabalho propõe um método baseado em aprendizado profundo para segmentação automática do pavilhão auricular em imagens termográficas, permitindo a extração padronizada de características térmicas. A abordagem utiliza a arquitetura U-Net e é avaliada com as métricas IoU, Dice e acurácia. Os resultados indicam alta acurácia (96,24%), com valores moderados de IoU (0,3750) e Dice (0,5258), refletindo limitações na precisão das bordas. Ainda assim, as medidas térmicas extraídas apresentaram baixa variabilidade entre as amostras.Referências
Atamañuk, A. N., Gandino, I. J., Miranda, M. N., Cardozo, L. M., Escalante, S. E., Villalba, C., Abalovich Bernal, D., Ross, G., Perna, E., and Delgado, D. (2025). Artificial intelligence–enabled analysis of thermography to diagnose acute decompensated heart failure. JACC: Advances, 4(7):101888.
Banerjee, R., Ghose, A., Sinha, A., Pal, A., and Mandana, K. (2019). A multi-modal approach for non-invasive detection of coronary artery disease. In Adjunct proceedings of the 2019 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2019 ACM international symposium on wearable computers, pages 543–550.
Branco, J. H., Branco, R. L., Siqueira, T. C., de Souza, L. C., Dalago, K. M., and Andrade, A. (2022). Clinical applicability of infrared thermography in rheumatic diseases: A systematic review. Journal of thermal biology, 104:103172.
Fernández-Cuevas, I., Marins, J. C. B., Lastras, J. A., Carmona, P. M. G., Cano, S. P., García-Concepción, M. Á., and Sillero-Quintana, M. (2015). Classification of factors influencing the use of infrared thermography in humans: A review. Infrared Physics & Technology, 71:28–55.
Ferreira, D. C. and Machado, A. M. C. (2025). Classificação de doença arterial coronariana através de redes neurais profundas. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 116–127. SBC.
Gakovic, B., Neskovic, S. A., Vranic, I., Grujicic, K., Mijatovic, S., Ljubojevic, A., and Stankovic, I. (2023). The relationship of diagonal earlobe crease (frank’s sign) and obstructive coronary artery disease in patients undergoing coronary angiography. Wiener klinische Wochenschrift, 135(23):667–673.
Garcea, F., Serra, A., Lamberti, F., and Morra, L. (2023). Data augmentation for medical imaging: A systematic literature review. Computers in biology and medicine, 152:106391.
Groenewegen, A., Zwartkruis, V. W., Rienstra, M., Zuithoff, N. P., Hollander, M., Koffijberg, H., Oude Wolcherink, M., Cramer, M. J., van der Schouw, Y. T., Hoes, A. W., et al. (2024). Diagnostic yield of a proactive strategy for early detection of cardiovascular disease versus usual care in adults with type 2 diabetes or chronic obstructive pulmonary disease in primary care in the netherlands (red-cvd): a multicentre, pragmatic, cluster-randomised, controlled trial. The Lancet Public Health, 9(2):e88–e99.
Huang, C.-L., Wu, Y.-W., Hwang, C.-L., Jong, Y.-S., Chao, C.-L., Chen, W.-J., Wu, Y.-T., and Yang, W.-S. (2011). The application of infrared thermography in evaluation of patients at high risk for lower extremity peripheral arterial disease. Journal of vascular surgery, 54(4):1074–1080.
Kung, M., Zeng, J., Lin, S., Yu, X., Liu, C., Shi, M., Sun, R., Yuan, S., Lian, X., Su, X., et al. (2024). Prediction of coronary artery disease based on facial temperature information captured by non-contact infrared thermography. BMJ Health & Care Informatics, 31(1):e100942.
Lahiri, B. B., Bagavathiappan, S., Jayakumar, T., and Philip, J. (2012). Medical applications of infrared thermography: a review. Infrared physics & technology, 55(4):221–235.
Loarce-Martos, J., Bachiller-Corral, J., Cuevas, I. F., Quintana, M. S., and Díaz, M. V. (2019). Thu0087 utility of infrared thermography for the evaluation of rheumatoid arthritis. Annals of the Rheumatic Diseases, 78:313–314.
Mashekova, A., Zhao, Y., Ng, E. Y., Zarikas, V., Fok, S. C., and Mukhmetov, O. (2022). Early detection of the breast cancer using infrared technology–a comprehensive review. Thermal science and engineering progress, 27:101142.
Meng, Z., Han, K., He, Y., He, Y., Li, X., and Zou, Y. (2025). Modeling detail feature connections for infrared image enhancement. Neurocomputing, 639:130200.
Motta, L. S., Conci, A., Lima, R. C., and Diniz, E. M. (2010). Automatic segmentation on thermograms in order to aid diagnosis and 2d modeling. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 1610–1619. SBC.
Ring, E. and Ammer, K. (2012). Infrared thermal imaging in medicine. Physiological measurement, 33(3):R33–R46.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Shimizu, M., Matsumoto, Y., Itakura, N., Mito, K., and Mizuno, T. (2023). Evaluation of methods for estimating autonomic nervous activity using a web camera. Artificial Life and Robotics, 28(4):718–725.
Tajbakhsh, N., Jeyaseelan, L., Li, Q., Chiang, J. N., Wu, Z., and Ding, X. (2020). Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Medical image analysis, 63:101693.
Tang, B. and Sato, W. (2025). Ear thermal imaging for emotion sensing. Scientific Reports, 15(1):41571.
World Health Organization (2021). Cardiovascular diseases (cvds).
Yli-Harja, O., Pakarinen, T., Peltola, E., Hämäläinen, M., Vehkaoja, A., and Oksala, N. (2025). The utility of infrared thermography and hyperspectral imaging in peripheral artery disease: A systematic review. Heart, Lung and Circulation.
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., and Liang, J. (2019). Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE transactions on medical imaging, 39(6):1856–1867.
Banerjee, R., Ghose, A., Sinha, A., Pal, A., and Mandana, K. (2019). A multi-modal approach for non-invasive detection of coronary artery disease. In Adjunct proceedings of the 2019 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2019 ACM international symposium on wearable computers, pages 543–550.
Branco, J. H., Branco, R. L., Siqueira, T. C., de Souza, L. C., Dalago, K. M., and Andrade, A. (2022). Clinical applicability of infrared thermography in rheumatic diseases: A systematic review. Journal of thermal biology, 104:103172.
Fernández-Cuevas, I., Marins, J. C. B., Lastras, J. A., Carmona, P. M. G., Cano, S. P., García-Concepción, M. Á., and Sillero-Quintana, M. (2015). Classification of factors influencing the use of infrared thermography in humans: A review. Infrared Physics & Technology, 71:28–55.
Ferreira, D. C. and Machado, A. M. C. (2025). Classificação de doença arterial coronariana através de redes neurais profundas. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 116–127. SBC.
Gakovic, B., Neskovic, S. A., Vranic, I., Grujicic, K., Mijatovic, S., Ljubojevic, A., and Stankovic, I. (2023). The relationship of diagonal earlobe crease (frank’s sign) and obstructive coronary artery disease in patients undergoing coronary angiography. Wiener klinische Wochenschrift, 135(23):667–673.
Garcea, F., Serra, A., Lamberti, F., and Morra, L. (2023). Data augmentation for medical imaging: A systematic literature review. Computers in biology and medicine, 152:106391.
Groenewegen, A., Zwartkruis, V. W., Rienstra, M., Zuithoff, N. P., Hollander, M., Koffijberg, H., Oude Wolcherink, M., Cramer, M. J., van der Schouw, Y. T., Hoes, A. W., et al. (2024). Diagnostic yield of a proactive strategy for early detection of cardiovascular disease versus usual care in adults with type 2 diabetes or chronic obstructive pulmonary disease in primary care in the netherlands (red-cvd): a multicentre, pragmatic, cluster-randomised, controlled trial. The Lancet Public Health, 9(2):e88–e99.
Huang, C.-L., Wu, Y.-W., Hwang, C.-L., Jong, Y.-S., Chao, C.-L., Chen, W.-J., Wu, Y.-T., and Yang, W.-S. (2011). The application of infrared thermography in evaluation of patients at high risk for lower extremity peripheral arterial disease. Journal of vascular surgery, 54(4):1074–1080.
Kung, M., Zeng, J., Lin, S., Yu, X., Liu, C., Shi, M., Sun, R., Yuan, S., Lian, X., Su, X., et al. (2024). Prediction of coronary artery disease based on facial temperature information captured by non-contact infrared thermography. BMJ Health & Care Informatics, 31(1):e100942.
Lahiri, B. B., Bagavathiappan, S., Jayakumar, T., and Philip, J. (2012). Medical applications of infrared thermography: a review. Infrared physics & technology, 55(4):221–235.
Loarce-Martos, J., Bachiller-Corral, J., Cuevas, I. F., Quintana, M. S., and Díaz, M. V. (2019). Thu0087 utility of infrared thermography for the evaluation of rheumatoid arthritis. Annals of the Rheumatic Diseases, 78:313–314.
Mashekova, A., Zhao, Y., Ng, E. Y., Zarikas, V., Fok, S. C., and Mukhmetov, O. (2022). Early detection of the breast cancer using infrared technology–a comprehensive review. Thermal science and engineering progress, 27:101142.
Meng, Z., Han, K., He, Y., He, Y., Li, X., and Zou, Y. (2025). Modeling detail feature connections for infrared image enhancement. Neurocomputing, 639:130200.
Motta, L. S., Conci, A., Lima, R. C., and Diniz, E. M. (2010). Automatic segmentation on thermograms in order to aid diagnosis and 2d modeling. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 1610–1619. SBC.
Ring, E. and Ammer, K. (2012). Infrared thermal imaging in medicine. Physiological measurement, 33(3):R33–R46.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Shimizu, M., Matsumoto, Y., Itakura, N., Mito, K., and Mizuno, T. (2023). Evaluation of methods for estimating autonomic nervous activity using a web camera. Artificial Life and Robotics, 28(4):718–725.
Tajbakhsh, N., Jeyaseelan, L., Li, Q., Chiang, J. N., Wu, Z., and Ding, X. (2020). Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation. Medical image analysis, 63:101693.
Tang, B. and Sato, W. (2025). Ear thermal imaging for emotion sensing. Scientific Reports, 15(1):41571.
World Health Organization (2021). Cardiovascular diseases (cvds).
Yli-Harja, O., Pakarinen, T., Peltola, E., Hämäläinen, M., Vehkaoja, A., and Oksala, N. (2025). The utility of infrared thermography and hyperspectral imaging in peripheral artery disease: A systematic review. Heart, Lung and Circulation.
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., and Liang, J. (2019). Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE transactions on medical imaging, 39(6):1856–1867.
Publicado
01/06/2026
Como Citar
NUNES, Gabriella Pompeu Domingos; SEIXAS, Elaine F. Rangel; SEIXAS, Flávio Luiz; ALVES, Leonardo de Souza Moreira; MESQUITA, Claudio Tinoco.
Segmentação de Região Auricular em Imagens Termográficas para Aplicações Médicas em Cardiologia. In: WORKSHOP DE TERMOGRAFIA COMPUTACIONAL E IA PARA APLICAÇÕES MÉDICAS - SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 26. , 2026, Ouro Preto/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 522-533.
ISSN 2763-8987.
DOI: https://doi.org/10.5753/sbcas_estendido.2026.26530.
