Skip to main navigation menu Skip to main content Skip to site footer
cjpl

Articles

CJPLS: VOL. 12, NO. 2, DECEMBER 2024 (Ongoing)

AUTOMATED DIAGNOSIS OF SCHISTOSOMIASIS USING CONVOLUTIONAL NEURAL NETWORKS: A COMPARATIVE STUDY WITH K-NEAREST NEIGHBORS

Submitted
August 26, 2024
Published
2024-11-22

Abstract

Schistosomiasis, a prevalent neglected tropical disease, continues to burden populations in resource-constrained regions globally. Conventional diagnostic methodologies are labour-intensive and demand significant time and resources. This study investigates the efficacy of advanced machine learning algorithms, particularly Convolutional Neural Networks (CNNs) and K-Nearest Neighbors (KNN), for automating the detection of Schistosoma eggs in microscopic images. Comparative performance analysis revealed that although the KNN algorithm achieved superior metrics in accuracy, precision, recall, and F1 score, its limitations in feature extraction and handling complex image patterns hindered its applicability as the primary diagnostic tool. Conversely, despite slightly lower
preliminary metrics, the CNN model demonstrated robust feature extraction capabilities and adaptability to intricate patterns, making it the optimal choice for the automated diagnosis of Schistosomiasis. The selected CNN model exhibited high diagnostic performance, with significant accuracy, precision, recall, and F1 scores, thereby offering a viable solution for enhancing the efficiency and accuracy of Schistosomiasis diagnostics. This approach could revolutionize diagnostic workflows, particularly in low-resource settings, by minimizing procedural complexity and improving diagnostic outcomes.

References

  1. P. J. Hotez, D. H. Molyneux, A. Fenwick, “Control of neglected tropical diseases", N. Engl J Med. 357:1018–1057, 2007.
  2. B. Chala, “Advances in Diagnosis of Schistosomiasis: Focus on Challenges and Future Approaches”, International journal of general medicine. 16, 983–995, 2023.https://doi.org/10.2147/IJGM.S391017.
  3. O. Bärenbold, G. Raso, J. T. Coulibaly, E. K. N'Goran, J. Utzinger, and P. Vounatsou, “Estimating sensitivity of the Kato-Katz technique for the diagnosis of Schistosoma mansoni and hookworm in relation to infection intensity”, PLoS neglected tropical diseases. 11(10), e0005953.https://doi.org/10.1371/journal.pntd.0005953.
  4. O. Holmström, N. Linder, B. Ngasala, A. Mårtensson, E. Linder, M. Lundin, and J. Lundin, “Point-of-care mobile digital microscopy and deep learning for the detection of soil-transmitted helminths and Schistosoma haematobium”, Global health action. 10(sup3), 1337325, 2017.
  5. D. N. M. Osakunor, M. E. J. Woolhouse, F. Mutapi, “Pediatric schistosomiasis: What we know and what we need to know”. PLoS Negl. Trop. Dis., 12, e0006144, 2018.
  6. Schistosoma haematobium. (2024, May 19). In Wikipedia. https://en.wikipedia.org/wiki/Schistosoma_haematobium
  7. A. Tariq, M. J. Awan, J. Alshudukhi, T. M. Alam, K. T. Alhamazani, Z. Meraf, “Software Measurement by Using Artificial Intelligence”, J. Nanomater, 2022, 72, 83 - 97, 2022.
  8. X. Yin, K., E., Ouattara, M. Aka, N. Diakité, N. R.,Bassa, F. K. Tappert, A. Yalkinoglu, Ö. Huber, E. Bezuidenhout, D. Bagchus, and W. M. Hayward, “Comparison of POC-CCA with Kato-Katz in Diagnosing Schistosoma mansoni Infection in a Pediatric L-Praziquantel Clinical Trial”, Frontiers in Tropical Diseases, 2, 686288. https://doi.org/10.3389/fitd.2021.686288.
  9. Schistosomiasis (Bilharzia). Available online: https://www.who.int/health-topics/schistosomiasis#tab=tab_1 (accessed on 1 May 2024).
  10. A. A. Abdulrazzaq, A. T. Al-Douri, A. A. Hamad, M. M. Jaber and Z. Meraf, “Assessing Deep Learning Techniques for the Recognition of Tropical Disease in Images from Parasitological Exams”, Bioinorganic Chemistry and Applications, 2022. https://doi.org/10.1155/2022/2682287
  11. P. Hagemann, “World Health Organization Manual of Basic Techniques for a Health Laboratory”, Clin. Chem., 49, 1712–1713, 2003.
  12. D. McManus, D. David, M. Sacko, J. Utzinger, B. Vennervald, and X. N. Zhou, “Schistosomiasis”, Nature Reviews Disease Primers. 4. 10.1038/s41572018-0013-8.
  13. A. Dwomoa, and O. Akinlolu, “Ethnicity and Chronic Kidney Disease in Africa” 2020. https://www.sciencedirect.com/topics/medicine-and-dentistry/schistosoma-haematobium
  14. T. Fusco, Y. Bi, H. Wang, and F. Browne, “Data mining and machine learning approaches for prediction modelling of schistosomiasis disease vectors: Epidemic disease prediction modelling”, International Journal of Machine Learning and Cybernetics, 11(6), 1159-1178, 2020.https://doi.org/10.1007/s13042-019-01029-x.
  15. O. Olasunkanmi, O. Odunayo, and Odunayo, O., “Comparison of Support Vector Machine Models in the Classification of Susceptibility to Schistosomiasis”, Balkan Journal of Electrical and Computer Engineering, 8. pp 76, 2020. 10.17694/bajece.651784.
  16. S. Jujjavarapu, “Automating the Diagnosis and Quantification of Urinary Schistosomiasis” Master Thesis, Delft University of Technology, Delft, The Netherlands, pp. 189, 2020.
  17. N. A. Switz, M. V. D’Ambrosio, D. A. Fletcher, “Low-Cost Mobile Phone Microscopy with a Reversed Mobile Phone Camera Lens” PLoS ONE, 9, e95330, 2014.
  18. S. J. Sowerby, J. A. Crump, M. C. Johnstone, K. L. Krause, P .C. Hill, “Smartphone microscopy of parasite eggs accumulated into a single field of view” Am. J. Trop. Med. Hyg. 94, 227–230, 2016.
  19. J. T. Coulibaly, M. Ouattara, M. V. D’Ambrosio, D. A. Fletcher, J. Keiser, J. Utzinger, E. K. N’Goran, J. R. Andrews, I. I. Bogoch, “Accuracy of mobile phone and handheld light microscopy for the diagnosis of schistosomiasis and intestinal protozoa infections in Côte d’Ivoire, PLoS Neglected Trop. Dis., 10, e0004768, 2016.
  20. A. M. Chagas, L. L. Prieto-Godino, A. B. Arrenberg, T. Baden, “The 100 Lab: A 3D-Printable Open-Source Platform for Fluorescence Microscopy, Optogenetics, and Accurate Temperature Control during Behaviour of Zebrafish, Drosophila, and Caenorhabditis Elegans” PLoS Biol., 15, e2002702, 2017.
  21. P. Oyibo, S. Jujjavarapu, B., Agbana, T., Braakman, I., Bengtson, M., Oyibo, W., Vdovine, G., and C. Diehl, “Schistoscope: An Automated Microscope with Artificial Intelligence for Detection of Schistosoma haematobium Eggs in Resource-Limited Settings”, Micromachines, 13(5), 2022,https://doi.org/10.3390/mi13050643
  22. World Health Organization. Ending the Neglect. to Attain the Sustainable Development Goals: A Global Strategy on Water, Sanitation and Hygiene to Combat Neglected Tropical Diseases, 2021–2030; World Health Organization: Geneva, Switzerland, 2021.
  23. T. Aidukas, R. Eckert, A. R. Harvey, L. Waller, P. C. Konda, “Low-cost, sub-micron resolution, wide-field computational microscopy using open source hardware”, Sci. Rep., 9, 7457, 2019.
  24. I. I. Bogoch, J. R. Andrews, B. Speich, J. Utzinger, S. M. Ame, S. M. Ali, J. Keiser, “Mobile phone microscopy for the diagnosis of soil-transmitted helminth infections: A proof-of-concept study”, Am. J. Trop. Med. Hyg., 88, 626–629, 2013.
  25. L. Le, M. H. Hsieh, “Diagnosing urogenital schistosomiasis: Dealing with diminishing returns” Trends Parasitol. 33, 378–387, 2017.
  26. T. Krti, L. Y. Zac, C. Andrew, J. Isabel, S. Pretom, R. Gilles, N. Raphael, B. Lydie, J. Nicolas, E. Paul, N. Ton, S. Susanne, D. Giulio, “Identification of Snails and Schistosoma of Medical Importance via Convolutional Neural Networks: A Proof-of-Concept Application for Human Schistosomiasis”, Frontiers in Public Health. 9. 642895. 10.3389/fpubh.2021.642895.
  27. Z, Ali, M. F. Hayat, K. Shaukat T. M. Alam, I. A. Hameed, S. Luo, S. Basheer, M. Ayadi, A. Ksibi, “A Proposed Framework for Early Prediction of Schistosomiasis. Diagnostics”, Trends in Parasitology 12(12):3138, 2022.