Malaria Disease Prediction System using Deep Learning with Flask App Project

Malaria is a serious illness. The root cause is insects that infect humans through the bite of female Anopheles mosquitoes. It can be cured if the right steps are taken. Microscopic diagnoses are poorly maintained and rely heavily on microscopist ability and knowledge. It is very common for microscopes to operate alone in low-cost settings, without a solid system in place that can guarantee the conservation of their capabilities and thus curable quality. This results in a wrong diagnostic conclusion in this area. Therefore, these facts have encouraged us to take up this building project. Diagnosis of Malaria through ML will benefit Health Care and assist in our studies as Machine Learning is a new benefit to the industry.
This final-year project is based on Malaria Disease Detection using Deep Learning. We have used MobileNet(150 CNN) and VGG16 to classify images. It was found that 150CNN provides better accuracy than VGG16 in our project. The model is first trained on the training set and then tested to classify the images as Parasitized or Uninfected.
In this project design and implementation of the deep neural networks, and learning are presented. We have used an approach and an algorithm to detect Malaria using Deep Learning. We have implemented an Artificial Neural Network and Convolution Neural Network used for the classification of the infected and uninfected images of blood samples.