Um Classificador Explicável para Transtorno de Estresse Pós-Traumático Utilizando Redes Neurais Convolucionais Tridimensionais
Resumo
O Transtorno de Estresse Pós-Traumático (TEPT) é uma condição psiquiátrica caracterizada por sintomas persistentes de reexperiência, evitação e hiperexcitabilidade em resposta a eventos traumáticos. A identificação precisa de indivíduos com TEPT a partir de dados neurobiológicos permanece um desafio, motivando o uso de abordagens baseadas em aprendizado profundo. Neste estudo, empregamos redes neurais convolucionais tridimensionais (3D-CNNs) para a classificação de TEPT a partir de dados de ressonância magnética funcional (fMRI). Utilizamos uma amostra de 43 participantes (20 com TEPT) expostos a estímulos visuais aversivos e avaliamos o desempenho do modelo por meio de validação cruzada, obtendo uma acurácia média de 86,25%. Além disso, empregamos a técnica de oclusão, baseada no Atlas Harvard-Oxford, para identificar as regiões cerebrais mais relevantes para a classificação. Os resultados destacam o envolvimento de áreas associadas ao processamento visual e emocional, incluindo o giro fusiforme occipital, a divisão superior do córtex occipital lateral e o córtex pré-cúneo.Referências
Abdalla, S. M., Ettman, C. K., Cohen, G. H., and Galea, S. (2021). Mental health consequences of covid-19: a nationally representative cross-sectional study of pandemic-related stressors and anxiety disorders in the usa. BMJ Open, 11(8).
Abrol, A., Fu, Z., Salman, M., Silva, R., Du, Y., Plis, S., and Calhoun, V. (2021). Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning. Nature Communications, 12(1):353.
Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-Dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., et al. (2023). A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1):46.
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2020). Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Information fusion, 58:82–115.
Bastos, A., Silva, L., Oliveira, J., Oliveira, L., Pereira, M., Figueira, I., Mendlowicz, M., Berger, W., Luz, M., Campos, B., Marques-Portella, C., Moll, J., Bramati, I., Volchan, E., and Erthal, F. (2022). Beyond fear: patients with posttraumatic stress disorder fail to engage in safety cues. Journal of Affective Disorders Reports, 10:100380.
Chao, L. L., Lenoci, M., and Neylan, T. C. (2012). Effects of post-traumatic stress disorder on occipital lobe function and structure. Neuroreport, 23(7):412–419.
Harricharan, S., Nicholson, A. A., Thome, J., Densmore, M., McKinnon, M. C., Théberge, J., Frewen, P. A., Neufeld, R. W., and Lanius, R. A. (2020). Ptsd and its dissociative subtype through the lens of the insula: Anterior and posterior insula resting-state functional connectivity and its predictive validity using machine learning. Psychophysiology, 57(1):e13472.
Harricharan, S., Rabellino, D., Frewen, P. A., Densmore, M., Théberge, J., McKinnon, M. C., Schore, A. N., and Lanius, R. A. (2016). fmri functional connectivity of the peri-aqueductal gray in ptsd and its dissociative subtype. Brain and behavior, 6(12):e00579.
Hu, J., Kuang, Y., Liao, B., Cao, L., Dong, S., and Li, P. (2019). A multichannel 2d convolutional neural network model for task-evoked fmri data classification. Computational Intelligence and Neuroscience, 2019(1):5065214.
Jenkinson, M., Beckmann, C. F., Behrens, T. E., Woolrich, M. W., and Smith, S. M. (2012). Fsl. Neuroimage, 62(2):782–790.
Jia, Y., Yang, B., Yang, Y., Zheng, W., Wang, L., Huang, C., Lu, J., and Chen, N. (2024). Application of machine learning techniques in the diagnostic approach of ptsd using mri neuroimaging data: A systematic review. Heliyon.
Koenen, K. C., Ratanatharathorn, A., Ng, L., McLaughlin, K. A., Bromet, E. J., Stein, D. J., Karam, E. G., Ruscio, A. M., Benjet, C., Scott, K., Atwoli, L., Petukhova, M., Lim, C. C. W., Aguilar-Gaxiola, S., Al-Hamzawi, A., Alonso, J., Bunting, B., Ciutan, M., de Girolamo, G., Degenhardt, L., Gureje, O., Haro, J. M., Huang, Y., Kawakami, N., Lee, S., Navarro-Mateu, F., Pennell, B.-E., Piazza, M., Sampson, N., Ten Have, M., Torres, Y., Viana, M. C., Williams, D., Xavier, M., and Kessler, R. C. (2017). Posttraumatic stress disorder in the world mental health surveys. Psychological Medicine, 47(13):2260–2274. Epub 2017 Apr 7.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.
Portugal, L. C. L., Ramos, T. C., Fernandes, O., Bastos, A. F., Campos, B., Mendlowicz, M. V., da Luz, M., Portella, C., Berger, W., Volchan, E., David, I. A., Erthal, F., Pereira, M. G., and de Oliveira, L. (2023). Machine learning applied to fmri patterns of brain activation in response to mutilation pictures predicts ptsd symptoms. BMC Psychiatry, 23(1):719.
Qureshi, M. N. I., Oh, J., and Lee, B. (2019). 3d-cnn based discrimination of schizophrenia using resting-state fmri. Artificial Intelligence in Medicine, 98:10–17.
Shin, L. M., Rauch, S. L., and Pitman, R. K. (2006). Amygdala, medial prefrontal cortex, and hippocampal function in ptsd. Annals of the New York Academy of Sciences, 1071(1):67–79.
Soares, D. C. S., dos Santos, L. A., and Donadon, M. F. (2021). Transtorno de estresse pós-traumático e prejuízos cognitivos, intervenções e tratamentos: uma revisão de literatura. Revista Eixo, 10(2):15–24.
Summerfield, J. J., Hassabis, D., and Maguire, E. A. (2009). Cortical midline involvement in autobiographical memory. Neuroimage, 44(3):1188–1200.
Suo, X., Lei, D., Li, W., Sun, H., Qin, K., Yang, J., Li, L., Kemp, G. J., and Gong, Q. (2022). Psychoradiological abnormalities in treatment-naive noncomorbid patients with posttraumatic stress disorder. Depression and Anxiety, 39(1):83–91.
Wen, D., Wei, Z., Zhou, Y., Li, G., Zhang, X., and Han, W. (2018). Deep learning methods to process fmri data and their application in the diagnosis of cognitive impairment: A brief overview and our opinion. Frontiers in Neuroinformatics, 12:23.
Yang, J., Lei, D., Qin, K., Pinaya, W. H., Suo, X., Li, W., Li, L., Kemp, G. J., and Gong, Q. (2021). Using deep learning to classify pediatric posttraumatic stress disorder at the individual level. BMC psychiatry, 21:1–10.
Yin, W., Li, L., and Wu, F.-X. (2022). Deep learning for brain disorder diagnosis based on fmri images. Neurocomputing, 469:332–345.
Zeiler, M. D. and Fergus, R. (2014). Visualizing and understanding convolutional networks. In Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T., editors, Computer Vision – ECCV 2014, pages 818–833, Cham. Springer International Publishing.
Zhu, Z., Lei, D., Qin, K., Suo, X., Li, W., Li, L., DelBello, M. P., Sweeney, J. A., and Gong, Q. (2021). Combining deep learning and graph-theoretic brain features to detect posttraumatic stress disorder at the individual level. Diagnostics, 11(8):1416.
Zilcha-Mano, S., Zhu, X., Suarez-Jimenez, B., Pickover, A., Tal, S., Such, S., Marohasy, C., Chrisanthopoulos, M., Salzman, C., Lazarov, A., et al. (2020). Diagnostic and predictive neuroimaging biomarkers for posttraumatic stress disorder. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 5(7):688–696.
Abrol, A., Fu, Z., Salman, M., Silva, R., Du, Y., Plis, S., and Calhoun, V. (2021). Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning. Nature Communications, 12(1):353.
Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-Dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., et al. (2023). A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1):46.
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2020). Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Information fusion, 58:82–115.
Bastos, A., Silva, L., Oliveira, J., Oliveira, L., Pereira, M., Figueira, I., Mendlowicz, M., Berger, W., Luz, M., Campos, B., Marques-Portella, C., Moll, J., Bramati, I., Volchan, E., and Erthal, F. (2022). Beyond fear: patients with posttraumatic stress disorder fail to engage in safety cues. Journal of Affective Disorders Reports, 10:100380.
Chao, L. L., Lenoci, M., and Neylan, T. C. (2012). Effects of post-traumatic stress disorder on occipital lobe function and structure. Neuroreport, 23(7):412–419.
Harricharan, S., Nicholson, A. A., Thome, J., Densmore, M., McKinnon, M. C., Théberge, J., Frewen, P. A., Neufeld, R. W., and Lanius, R. A. (2020). Ptsd and its dissociative subtype through the lens of the insula: Anterior and posterior insula resting-state functional connectivity and its predictive validity using machine learning. Psychophysiology, 57(1):e13472.
Harricharan, S., Rabellino, D., Frewen, P. A., Densmore, M., Théberge, J., McKinnon, M. C., Schore, A. N., and Lanius, R. A. (2016). fmri functional connectivity of the peri-aqueductal gray in ptsd and its dissociative subtype. Brain and behavior, 6(12):e00579.
Hu, J., Kuang, Y., Liao, B., Cao, L., Dong, S., and Li, P. (2019). A multichannel 2d convolutional neural network model for task-evoked fmri data classification. Computational Intelligence and Neuroscience, 2019(1):5065214.
Jenkinson, M., Beckmann, C. F., Behrens, T. E., Woolrich, M. W., and Smith, S. M. (2012). Fsl. Neuroimage, 62(2):782–790.
Jia, Y., Yang, B., Yang, Y., Zheng, W., Wang, L., Huang, C., Lu, J., and Chen, N. (2024). Application of machine learning techniques in the diagnostic approach of ptsd using mri neuroimaging data: A systematic review. Heliyon.
Koenen, K. C., Ratanatharathorn, A., Ng, L., McLaughlin, K. A., Bromet, E. J., Stein, D. J., Karam, E. G., Ruscio, A. M., Benjet, C., Scott, K., Atwoli, L., Petukhova, M., Lim, C. C. W., Aguilar-Gaxiola, S., Al-Hamzawi, A., Alonso, J., Bunting, B., Ciutan, M., de Girolamo, G., Degenhardt, L., Gureje, O., Haro, J. M., Huang, Y., Kawakami, N., Lee, S., Navarro-Mateu, F., Pennell, B.-E., Piazza, M., Sampson, N., Ten Have, M., Torres, Y., Viana, M. C., Williams, D., Xavier, M., and Kessler, R. C. (2017). Posttraumatic stress disorder in the world mental health surveys. Psychological Medicine, 47(13):2260–2274. Epub 2017 Apr 7.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436–444.
Portugal, L. C. L., Ramos, T. C., Fernandes, O., Bastos, A. F., Campos, B., Mendlowicz, M. V., da Luz, M., Portella, C., Berger, W., Volchan, E., David, I. A., Erthal, F., Pereira, M. G., and de Oliveira, L. (2023). Machine learning applied to fmri patterns of brain activation in response to mutilation pictures predicts ptsd symptoms. BMC Psychiatry, 23(1):719.
Qureshi, M. N. I., Oh, J., and Lee, B. (2019). 3d-cnn based discrimination of schizophrenia using resting-state fmri. Artificial Intelligence in Medicine, 98:10–17.
Shin, L. M., Rauch, S. L., and Pitman, R. K. (2006). Amygdala, medial prefrontal cortex, and hippocampal function in ptsd. Annals of the New York Academy of Sciences, 1071(1):67–79.
Soares, D. C. S., dos Santos, L. A., and Donadon, M. F. (2021). Transtorno de estresse pós-traumático e prejuízos cognitivos, intervenções e tratamentos: uma revisão de literatura. Revista Eixo, 10(2):15–24.
Summerfield, J. J., Hassabis, D., and Maguire, E. A. (2009). Cortical midline involvement in autobiographical memory. Neuroimage, 44(3):1188–1200.
Suo, X., Lei, D., Li, W., Sun, H., Qin, K., Yang, J., Li, L., Kemp, G. J., and Gong, Q. (2022). Psychoradiological abnormalities in treatment-naive noncomorbid patients with posttraumatic stress disorder. Depression and Anxiety, 39(1):83–91.
Wen, D., Wei, Z., Zhou, Y., Li, G., Zhang, X., and Han, W. (2018). Deep learning methods to process fmri data and their application in the diagnosis of cognitive impairment: A brief overview and our opinion. Frontiers in Neuroinformatics, 12:23.
Yang, J., Lei, D., Qin, K., Pinaya, W. H., Suo, X., Li, W., Li, L., Kemp, G. J., and Gong, Q. (2021). Using deep learning to classify pediatric posttraumatic stress disorder at the individual level. BMC psychiatry, 21:1–10.
Yin, W., Li, L., and Wu, F.-X. (2022). Deep learning for brain disorder diagnosis based on fmri images. Neurocomputing, 469:332–345.
Zeiler, M. D. and Fergus, R. (2014). Visualizing and understanding convolutional networks. In Fleet, D., Pajdla, T., Schiele, B., and Tuytelaars, T., editors, Computer Vision – ECCV 2014, pages 818–833, Cham. Springer International Publishing.
Zhu, Z., Lei, D., Qin, K., Suo, X., Li, W., Li, L., DelBello, M. P., Sweeney, J. A., and Gong, Q. (2021). Combining deep learning and graph-theoretic brain features to detect posttraumatic stress disorder at the individual level. Diagnostics, 11(8):1416.
Zilcha-Mano, S., Zhu, X., Suarez-Jimenez, B., Pickover, A., Tal, S., Such, S., Marohasy, C., Chrisanthopoulos, M., Salzman, C., Lazarov, A., et al. (2020). Diagnostic and predictive neuroimaging biomarkers for posttraumatic stress disorder. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 5(7):688–696.
Publicado
09/06/2025
Como Citar
FERNANDES, Raphael M. M.; CARVALHO, Rodrigo J. de; F. JUNIOR, Orlando; PORTUGAL, Liana C. L.; RAMOS, Taiane C..
Um Classificador Explicável para Transtorno de Estresse Pós-Traumático Utilizando Redes Neurais Convolucionais Tridimensionais. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 25. , 2025, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 236-247.
ISSN 2763-8952.
DOI: https://doi.org/10.5753/sbcas.2025.7005.