Image Analysis and Machine Learning in Malaria Parasite Detection: Recent Advances and Future Perspective

Plasmodium parasites cause malaria, a deadly disease that continues to pose a significant global health burden, particularly in resource-limited regions. Detecting and classifying the parasite accurately and promptly are crucial for controlling the progression of the disease. Malaria detection and classification are most frequently performed using a single-class classification approach. Single-class classification approaches include image-based classification, feature-based classification, and machine learning-based classification. Data from multiple classes are used in multi-class classification, which is more complex than single-class classification. These methods are often more extensive than single-class techniques since they can identify and categorize several Plasmodium species and their life stages. Ensemble learning, fuzzy logic-based classification, and deep learning-based classification are some of the common multi-class classification techniques. In addition to their advantages, each approach has its own disadvantages. An in-depth review of existing single-class and multi-class approaches for malaria classification is provided in this paper to gain a better understanding of the different approaches. In the end, this study attempts to present a thorough analysis of the current approaches for classifying malaria.