Automatic Macrophage Detection in Parasitological Exams Using Clustering and Convolutional Neural Networks

• Armando L. Borges UFPI
• Viviane B. L. Dias UFPI
• Clésio de A. Gonçalves UFPI / IFSertãoPE
• Lucas B. M. de Souza UFPI
• Daniel de A. Viana UECE
• Ana Carolina L. Pacheco UFPI
• Romuere R. V. e Silva UFPI

DOI: https://doi.org/10.5753/sbcas.2024.2796

Abstract

Visceral Leishmaniasis is a parasitic disease that affects the host’s defense system, with dogs being its main urban reservoirs. Early diagnosis in animals is crucial to prevent transmission to humans. The parasitological examination is the gold standard for diagnosing the disease, which is repetitive and tiring work. This article presents a system for detecting and quantifying macrophages in medical images, currently assisting in diagnosis. The regions of interest were segmented using the K-Means clustering, and we used the Densenet201 architecture for detection. The methodology achieved 94.7% accuracy and 89.4% accuracy for the Kappa index. These results indicate the system’s ability to aid diagnosis.

References

Araújo, F. H., Silva, R. R., Medeiros, F. N., Neto, J. F. R., Oliveira, P. H. C., Bianchi, A. G. C., and Ushizima, D. (2021). Active contours for overlapping cervical cell segmentation. International Journal of Biomedical Engineering and Technology, 35(1):70–92.

Aziz, S., Bilal, M., Khan, M. U., and Amjad, F. (2020). Deep learning-based automatic morphological classification of leukocytes using blood smears. In 2020 International Conference on Electrical, Communication, and Computer Engineering (ICECCE), pages 1–5.

Bani-Hani, D., Khan, N., Alsultan, F., Karanjkar, S., and Nagarur, N. (2018). Classification of leucocytes using convolutional neural network optimized through genetic algorithm.

Cook, A. (2017). Using transfer learning to classify images with keras. Retrieved from [link].

da Saúde, M. Situação epidemiológica da leishmaniose visceral.

e Silva, R. R. V., de Araujo, F. H. D., dos Santos, L. M. R., Veras, R. M. S., and de Medeiros, F. N. S. (2016). Optic disc detection in retinal images using algorithms committee with weighted voting. IEEE Latin America Transactions, 14(5):2446–2454.

Eder, K., Kutscher, T., Marzi, A., Barroso, Á., Schnekenburger, J., and Kemper, B. (2021). Automated detection of macrophages in quantitative phase images by deep learning using a mask region-based convolutional neural network. In Label-free Biomedical Imaging and Sensing (LBIS) 2021, volume 11655, pages 88–94. SPIE.

Fleiss, J. L., Levin, B., and Paik, M. C. (2013). Statistical methods for rates and proportions. john wiley & sons.

Gonçalves, C., Andrade, N., Borges, A., Rodrigues, A., Veras, R., Aguiar, B., and Silva, R. (2023). Automatic detection of visceral leishmaniasis in humans using deep learning. Signal, Image and Video Processing, 17(7):3595–3601.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer.

Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708.

Liang, G., Hong, H., Xie, W., and Zheng, L. (2018). Combining convolutional neural network with recursive neural network for blood cell image classification. IEEE Access, 6:36188–36197.

Marcondes, M. and Day, M. J. (2019). Current status and management of canine leishmaniasis in latin america. Research in Veterinary Science, 123:261–272.

Ministério da Saúde, B. (2006). Manual de vigilância e controle da leishmaniose visceral. Série A. Normas e Manuais Técnicos.

Ministério da Saúde. Leishmaniose visceral. Retrieved from [link]. Accessed: 08 mar. 2024.

PAHO (2017). Epidemiological report of the americas. leishmaniases.

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115:211–252.

Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618–626.

Silva, F. S. (2007). Patologia e patogênese da leishmaniose visceral canina. Rev Trop Cienc Agr Biol, 1(1):20–31.

Silva, J. M., Zacarias, D. A., de Figueirêdo, L. C., Soares, M. R. A., Ishikawa, E. A., Costa, D. L., and Costa, C. H. (2014). Bone marrow parasite burden among patients with new world kala-azar is associated with disease severity. The American Journal of Tropical Medicine and Hygiene, 90(4):621.

Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.

Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31.

Trong Luong, D., Duy Anh, D., Xuan Thang, T., Thi Lan Huong, H., Thuy Hanh, T., and Minh Khanh, D. (2022). Distinguish normal white blood cells from leukemia cells by detection, classification, and counting blood cells using yolov5. In 2022 7th National Scientific Conference on Applying New Technology in Green Buildings (ATiGB), pages 156–160.

Xia, R., Wang, P., Chen, R., and Guo, F. (2009). One kind of macrophages images segmentation and labeling method. In 2009 2nd International Congress on Image and Signal Processing, pages 1–5.