Abordagem Computacional Baseada em Deep Learning para o Diagnóstico de Endometriose Profunda através de Imagens de Ressonância Magnética

• Weslley K. R. Figueredo UFMA
• Italo F. S. da Silva UFMA
• João O. B. Diniz IFMA
• Aristófanes C. Silva UFMA
• Anselmo C. de Paiva UFMA
• Alice C. C. Brandão Salomão Clínica Fonte de Imagem
• Marco A. P. de Oliveira UERJ

DOI: https://doi.org/10.5753/sbcas.2023.229567

Abstract

Endometriosis is a disease that affects several organs, especially those in the pelvic structure, and considerably reduces the quality of life of the person affected. The disease mainly affects women of childbearing age. And, it can be identified via imaging exams. A method for automatically identifying the endometriosis lesion in magnetic resonance images using image processing techniques and a modified VGG-16 is proposed in this work. It has the purpose of serving as an aid in the diagnosis and to help to reduce the need to use invasive methods to perform these, the time of diagnosis, and false negative results. It achieved an accuracy of 83.89%, a sensitivity of 84.15%, and a specificity of 83.86%.

References

Alom, M. Z., Hasan, M., Yakopcic, C., Taha, T. M., and Asari, V. K. (2018). Recurrent residual convolutional neural network based on u-net (r2u-net) for medical image segmentation. arXiv preprint arXiv:1802.06955.

Bailey, H. R., Ott, M. T., and Hartendorp, P. (1994). Aggressive surgical management for advanced colorectal endometriosis. Diseases of the colon & rectum, 37:747–753.

Balleyguier, C., Chapron, C., Dubuisson, J., Kinkel, K., Fauconnier, A., Vieira, M., Hélénon, O., and Menu, Y. (2002). Comparison of magnetic resonance imaging and transvaginal ultrasonography in diagnosing bladder endometriosis. The Journal of the American Association of Gynecologic Laparoscopists, 9(1):15–23.

Bazot, M., Darai, E., Hourani, R., Thomassin, I., Cortez, A., Uzan, S., and Buy, J.-N. (2004). Deep pelvic endometriosis: Mr imaging for diagnosis and prediction of extension of disease. Radiology, 232(2):379–389.

Brunelli, R. (2009). Template matching techniques in computer vision: theory and practice. John Wiley & Sons.

Caraça, D., Podgaec, S., Baracat, E., and Abrão, M. (2011). Mecanismos fisiopatológicos da dor pélvica na endometriose profunda. Diagn Tratamento, 16(2):57–61.

Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.

Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., Chen, K., et al. (2015). Xgboost: extreme gradient boosting. R package version 0.4-2, 1(4):1–4.

Coutinho Junior, A. C., Lima, C. M. A. d. O., Coutinho, E. P. D., Ribeiro, É. B., Aidar, M. N., and Gasparetto, E. L. (2008). Ressonância magnética na endometriose pélvica profunda: ensaio iconográfico. Radiologia Brasileira, 41:129–134.

Diniz, J., Ferreira, J., Silva, G., Quintanilha, D., Silva, A., and Paiva, A. (2021). Segmentação de coração em tomografias computadorizadas utilizando atlas probabilístico e redes neurais convolucionais. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 83–94, Porto Alegre, RS, Brasil. SBC.

DINIZ, J. O. B. et al. (2021). Métodos para segmentação de medula espinhal e esôfago em tomografia computadorizada de planejamento à radioterapia.

Júnior, D. D., Cruz, L., Diniz, J., Júnior, G. B., and Silva, A. (2021). Classificação automática de glóbulos brancos usando descritores de forma e textura e extreme gradient boosting. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 95–106, Porto Alegre, RS, Brasil. SBC.

Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Leibetseder, A., Kletz, S., Schoeffmann, K., Keckstein, S., and Keckstein, J. (2020). GLENDA: gynecologic laparoscopy endometriosis dataset. In MultiMedia Modeling - 26th International Conference, MMM 2020, Daejeon, South Korea, January 5-8, 2020, Proceedings, Part II, volume 11962 of Lecture Notes in Computer Science, pages 439–450. Springer.

Leibetseder, A., Schoeffmann, K., Keckstein, J., and Keckstein, S. (2022). Endometriosis detection and localization in laparoscopic gynecology. Multimedia Tools and Applications, pages 1–25.

Liang, M. and Hu, X. (2015). Recurrent convolutional neural network for object recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3367–3375. IEEE Computer Society.

Moura, A. P. C., Ribeiro, H. S. A. A., Bernardo, W. M., Simões, R., Torres, U. S., D’Ippolito, G., Bazot, M., and Ribeiro, P. A. A. G. (2019). Accuracy of transvaginal sonography versus magnetic resonance imaging in the diagnosis of rectosigmoid endometriosis: Systematic review and meta-analysis. PLoS One, 14(4):e0214842.

Pontes, I. F. and Claudino, E. L. (2021). Dor pélvica e achados indiretos da endometriose na ecografia pélvica: Uma correlação estatística. Research, Society and Development, 10(8):e49210817709–e49210817709.

Scardapane, A., Lorusso, F., Bettocchi, S., Moschetta, M., Fiume, M., Vimercati, A., Pepe, M., Angelelli, G., and Stabile Ianora, A. (2013). Deep pelvic endometriosis: accuracy of pelvic mri completed by mr colonography. La Radiologia Medica, pages 1–16.

Silva, G., Oliveira, F., Diniz, J., Diniz, P., Quintanilha, D., Silva, A., Paiva, A., and Cavalcanti, E. (2021). An automatic method for prostate segmentation on 3d mri scans using local phylogenetic indexes and xgboost. In Anais do XXI Simpósio Brasileiro de Computação Aplicada à Saúde, pages 165–176, Porto Alegre, RS, Brasil. SBC.

Simonyan, K. and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

SOUZA, L. G., BARROS, A. M. D. A., and Monteiro, M. R. S. (2020). A importância do ca-125 para o diagnóstico precoce da endometriose. Revista de Patologia do Tocantins, 7(1):66–70.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826.

Visalaxi, S. and Muthu, T. S. (2021). Automated prediction of endometriosis using deep learning. International Journal of Nonlinear Analysis and Applications, 12(2):2403–2416.

Visalaxi, S. and Sudalaimuthu, T. (2022). Automated segmentation of endometriosis using transfer learning technique. F1000Research, 11(360):360.

Wong, T.-T. (2015). Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 48(9):2839–2846.

Yang, M., Liu, M., Chen, Y., He, S., and Lin, Y. (2021). Diagnostic efficacy of ultrasound combined with magnetic resonance imaging in diagnosis of deep pelvic endometriosis under deep learning. The Journal of Supercomputing, 77(7):7598–7619.