Trypanosoma cruzi Detection using LSTM Convolutional Autoencoder

  • Geovani L. Martins UFOP
  • Daniel S. Ferreira IFCE
  • Claudia M. Carneiro UFOP
  • Andrea G. C. Bianchi UFOP

Resumo


The presence of Trypanosoma cruzi (T. cruzi) parasites in blood samples is proof of the medical diagnosis of Chagas disease. Since the motion of these microorganisms is conspicuous in optical microscopy videos, we propose a spatio-temporal autoencoder for anomaly detection caused by parasite motility. This approach includes a spatial feature extractor and a temporal sequencer ConvLSTM for learning the temporal evolution of the spatial features. We trained the autoencoder with no parasites videos to learn the normal pattern and measured the regularity score in test videos with parasites. Our results showed that an LSTM-based autoencoder may identify T. cruzi anomalous motion, being a promising method for detecting parasites in microscopy videos.

Referências

Alanis, E., Romero, G., Alvarez, L., Martinez, C. C., and Basombrio, M. A. (2004). Optical detection of Trypanosoma cruzi in blood samples for diagnosis purpose. In 5th Iberoamerican Meeting on Optics and 8th Latin American Meeting on Optics, Lasers, and Their Applications, volume 5622, pages 24–28, Porlamar, Venezuela. SPIE.

Ba, J. L., Kiros, J. R., and Hinton, G. E. (2016). Layer normalization. arXiv:1607.06450.

Chong, Y. S. and Tay, Y. H. (2017). Abnormal event detection in videos using spatiotemporal autoencoder. In Cong, F., Leung, A., and Wei, Q., editors, Advances in Neural Networks ISNN 2017, volume 10262, pages 189–196, Cham. Springer International Publishing.

Hasan, M., Choi, J., Neumann, J., Roy-Chowdhury, A. K., and Davis, L. S. (2016). Learning temporal regularity in video sequences. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 733–742, Los Alamitos, CA, USA. IEEE Computer Society.

Hassan, E., Shams, M., Hikal, N., and Elmougy, S. (2023). The effect of choosing optimizer algorithms to improve computer vision tasks: A comparative study. Multimed. Tools. Appl., 82:16591–16633.

Kingma, D. P. and Ba, J. (2015). Adam: A method for stochastic optimization. In Bengio, Y. and LeCun, Y., editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA.

Lakshmi, V. S., Tebby, S. G., Shriranjani, D., and Rajinikanth, V. (2016). Chaotic cuckoo search and kapur/tsallis approach in segmentation of T. cruzi from blood smear images. Int. J. Comp. Sci. Infor. Sec., 14:51–56.

Martins, G. L., Ferreira, D. S., and Ramalho, G. L. B. (2021). Collateral motion saliency-based model for Trypanosoma cruzi detection in dye-free blood microscopy. Comput. Biol. Med., 132:104220.

Maza-Sastre, H., Ochoa-Montiel, R., Sánchez-López, C., Pérez-Corona, C., Carrasco-Aguilar, M. A., and Morales-López, F. E. (2014). Identification of trypanosoma with digital image processing. In Proceedings of the 2014 IEEE Central America and Panama Convention (CONCAPAN XXXIV), pages 1–4, Panama City, Panama. IEEE.

Moon, S., Siqueira-Neto, J. L., Moraes, C. B., Yang, G., Kang, M., Freitas-Junior, L. H., and Hansen, M. A. E. (2014). An image-based algorithm for precise and accurate high throughput assessment of drug activity against the human parasite Trypanosoma cruzi. PLoS One, 9(2):e87188.

Nohara, L. L., Lema, C., Bader, J. O., Aguilera, R. J., and Almeida, I. C. (2010). High-content imaging for automated determination of host-cell infection rate by the intracellular parasite Trypanosoma cruzi. Parasitol. Int., 59(4):565–570.

Ojeda-Pat, A., Martin-Gonzalez, A., and Soberanis-Mukul, R. (2020). Convolutional neural network U-Net for Trypanosoma cruzi segmentation. In Intelligent Computing Systems, volume 1187, pages 118–131, Cham. Springer.

Pereira, A., Pyrrho, A., Vanzan, D., Mazza, L., and Gomes, J. G. (2019). Deep convolutional neural network applied to chagas disease parasitemia assessment. In Anais do 14 Congresso Brasileiro de Inteligência Computacional, pages 1–8, Curitiba, Brazil. ABRICOM.

Pérez-Molina, J. A. and Molina, I. (2018). Chagas disease. The Lancet, 391(10115):82–94.

Relli, C. D. S., Facon, J., Ayala, H. L., and Britto, A. D. S. (2017). Automatic counting of trypanosomatid amastigotes in infected human cells. Comput. Biol. Med., 89:222–235.

Romero, G. G., Monaldi, A. C., and Alanís, E. E. (2012). Digital holographic microscopy for detection of Trypanosoma cruzi parasites in fresh blood mounts. Opt. Commun., 285(6):1613–1618.

Sabokrou, M., Fathy, M., Hoseini, M., and Klette, R. (2015). Real-time anomaly detection and localization in crowded scenes. In 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 56–62, Los Alamitos, CA, USA. IEEE Computer Society.

Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-k., and Woo, W.-c. (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Proceedings of the 28th International Conference on Neural Information Processing Systems Volume 1, NIPS’15, page 802–810, Cambridge, MA, USA. MIT Press.

Soberanis-Mukul, R., Uc-Cetina, V., Brito-Loeza, C., and Ruiz-Piña, H. (2013). An automatic algorithm for the detection of Trypanosoma cruzi parasites in blood sample images. Comput. Meth. Prog Bio., 112(3):633–639.

Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15(1):1929–1958.

Takagi, Y., Nosato, H., Doi, M., Furukawa, K., and Sakanashi, H. (2019). Development of a motion-based cell-counting system for trypanosoma parasite using a pattern recognition approach. Biotechniques., 66(4):179–185.

Uc-Cetina, V., Brito-Loeza, C., and Ruiz-Piña, H. (2013). Chagas parasites detection through gaussian discriminant analysis. Abstr. Appl., 8:6–17.

Uc-Cetina, V., Brito-Loeza, C., and Ruiz-Piña, H. (2015). Chagas parasite detection in blood images using adaboost. Comput. Math. Methods Med., 2015:1–13.

Vega-Alvarado, L., Caballero-Ruiz, A., Ruiz-Huerta, L., Heredia-López, F., and RuizPiña, H. (2020). Images analysis method for the detection of Chagas parasite in blood image. In Pattern Recognition Techniques Applied to Biomedical Problems, pages 63–72, Cham. Springer.

Wang, L., Zhou, F., Li, Z., Zuo, W., and Tan, H. (2018). Abnormal event detection in videos using hybrid spatio-temporal autoencoder. In 2018 25th IEEE International Conference on Image Processing (ICIP), pages 2276–2280.

Zeiler, M. D., Krishnan, D., Taylor, G. W., and Fergus, R. (2010). Deconvolutional networks. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 2528–2535.

Zhang, Y., Koydemir, H. C., Shimogawa, M. M., Yalcin, S., Guziak, A., Liu, T., Oguz, I., Huang, Y., Bai, B., Luo, Y., et al. (2018). Motility-based label-free detection of parasites in bodily fluids using holographic speckle analysis and deep learning. Light Sci. Appl., 7(1):108.
Publicado
27/06/2023
MARTINS, Geovani L.; FERREIRA, Daniel S.; CARNEIRO, Claudia M.; BIANCHI, Andrea G. C.. Trypanosoma cruzi Detection using LSTM Convolutional Autoencoder. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO APLICADA À SAÚDE (SBCAS), 23. , 2023, São Paulo/SP. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2023 . p. 443-454. ISSN 2763-8952. DOI: https://doi.org/10.5753/sbcas.2023.230153.

##plugins.generic.recommendByAuthor.heading##