Development of low cost, automated digital microscopes allowing rapid whole slide imaging for detecting malaria

Plasmodium parasites are responsible for the life-threatening illness known as malaria, which remains a significant public health problem across the world, especially in areas with limited access to resources. Traditional techniques for diagnosing malaria, such as microscopy, may take a significant amount of time and need workers with specific training. The development of digital imaging technology has presented a window of opportunity to enhance malaria diagnosis. In this chapter, we discuss the development of low-cost, automated digital microscopes that are meant to allow quick whole slide imaging for the detection of malaria. These microscopes are intended to be used in community clinics in the low resource countries. Automating blood cell imaging, processing and classification require deep learning based approaches for faster and more accurate identification. The proposed system has three major components: (i) blood preparation module, (ii) 400× zooming microscope and control mechanism, and (iii) Malaria detection module. This automated system acquires high-resolution images of blood cells, then subjecting them to image recognition algorithms for the purpose of identifying and categorising distinct cell types. We explore the difficulties associated with the creation of digital microscopes that are both inexpensive and automated, and we provide novel methods and technologies that have the potential to make the diagnosis of malaria on a wide scale both cost-effective and efficient. We incorporated the YOLOv5 (You Only Look Once) model in simplifying detection, minimising human error, and speeding up the identification of malaria-infected blood smears. The model has an approximate overall accuracy rate of 92% in correctly classifying samples as either infected or non infected. In addition, we emphasize the potential effect that these improvements might have in terms of increasing healthcare delivery and monitoring efforts in areas that are prone to malaria.