Deep Learning Application for Detection of Malaria

Malaria continues to be a significant burden on global health with 247 million clinical episodes and 619,000 deaths. Along with biomedical science, technology, and informatics have begun participating in the quest against malaria. Microscopy techniques are frequently used to detect malaria parasites in infected red blood cells. Giemsa stain has been used to stain blood parasites for over a century. The stain is applied after fixing blood smears in methyl alcohol for 25 to 30 minutes [1]. When stained slides are examined under a microscope, the parasites are easily discernible based on morphology and color. We observed that automating the detection of these slides using deep learning is possible with high accuracy. A comparison between deep learning models reveals ResNets provide better performance.