A Performance Analysis of Machine Learning Algorithms for Malaria Parasite Detection using Microscopic Images

Plasmodium parasites are the cause of malaria, a blood-borne disease spread by mosquitoes. Preparing a blood sample, staining it, then using a microscope to look at the stained blood smear to determine which parasite genus is Plasmodium. is the standard method for detecting malaria, a promising area of research is computer-aided Plasmodium detection. For the purpose of detecting Plasmodium on blood smear images obtained through conventional microscopy, this study examines the efficacy of various machine learning strategies in this paper. To target effected blood smears for detection of malaria, this research work employs different algorithms of machine learning in contrast to the conventional approach and has some issues with sensitivity and specificity. Most malaria diagnoses are made using standard microscopy. Microscopy has also shown a range of clinical and transmission situations to have varied sensitivity and specificity. The suggested method does not require experts or blood stains; instead, it uses images of patient to detect malaria.