Open Access Open Access  Restricted Access Subscription Access

Advances in Automated Malaria Diagnosis Using Image Processing and Machine Learning: A Comprehensive Review

Saurabh Pandey, Rohitashwa Pandey

Abstract


Malaria remains a critical global health issue, especially in tropical and subtropical regions, with over 249 million cases and 608,000 deaths reported in 2022. Early and accurate diagnosis is vital for reducing mortality and controlling transmission. Although manual microscopy of stained blood smears is the diagnostic gold standard, it is labour-intensive, time-consuming, and prone to human error. Recent advances in image processing and machine learning have enabled automated, reliable, and efficient malaria detection through digital blood smear analysis. This review summarizes recent developments in image segmentation, feature extraction, and classification techniques for malaria diagnosis. It discusses traditional methods such as thresholding, watershed, and clustering, alongside deep learning approaches like CNNs and U-Net for enhanced accuracy. Furthermore, it highlights challenges including image variability, dataset imbalance, and the need for real-time, clinically validated systems, while suggesting future research directions to improve scalability and practical deployment.

Full Text:

PDF

References


Bhatt, S., Weiss, D. J., Cameron, E., Bisanzio, D., Mappin, B., Dalrymple, U., ... & Gething, P. W. (2015). The global distribution and burden of malaria. Nature, 526(7572), 207–211. https://doi.org/10.1038/nature15535

Bibin, D., Nair, M. S., & Punitha, P. (2017). Malaria detection using deep belief networks. Computers in Biology and Medicine, 89, 306–312. https://doi.org/10.1016/j.compbiomed.2017.08.022

Das, D. K., Ghosh, M., Pal, M., Maiti, A. K., & Mandal, M. (2013). Computer-aided diagnosis of malaria disease using microscopic images. Procedia Technology, 10, 681–687. https://doi.org/10.1016/j.protcy.2013.12.421

Dong, Y., Jiang, Z., Shen, H., Huang, P., & Wang, W. (2017). Evaluating convolutional neural networks for malaria parasite classification. BMC Bioinformatics, 18(1), 1–10. https://doi.org/10.1186/s12859-017-1804-0

Liang, Z., Powell, A., Ersoy, I., Poostchi, M., Sameer, A., & Maude, R. J. (2019). CNN-based segmentation of blood smear images for malaria diagnosis. IEEE Access, 7, 118142–118149. https://doi.org/10.1109/ACCESS.2019.2936366

Maltha, J., Gillet, P., & Jacobs, J. (2013). Malaria rapid diagnostic tests in travel medicine. Clinical Microbiology and Infection, 19(5), 408–415. https://doi.org/10.1111/1469-0691.12152

Moody, A. (2002). Rapid diagnostic tests for malaria parasites. Clinical Microbiology Reviews, 15(1), 66–78. https://doi.org/10.1128/CMR.15.1.66-78.2002

NIH. (2018). Labeled dataset for parasitized and uninfected blood smear images. National Library of Medicine. https://lhncbc.nlm.nih.gov/LHC-publications/pubs/MalariaDatasets.html

Pant, K., Singh, M., & Anand, R. S. (2018). SVM-based malaria diagnosis using texture and color features. Journal of Biomedical Engineering, 40(3), 342–351. https://doi.org/10.1049/joe.2018.0024

Poostchi, M., Silamut, K., Maude, R. J., Jaeger, S., & Thoma, G. (2018). Image analysis and machine learning for detecting malaria. Malaria Journal, 17, 1–22. https://doi.org/10.1186/s12936-018-2140-9


Refbacks

  • There are currently no refbacks.