Malaria Parasite Detection Using Deep Learning : (Beneficial to humankind)

Abstract

Malaria is one of the deadliest diseases across the globe. This is caused by the bite of female Anopheles mosquito that transmits the Plasmodium parasites. Some current malaria detection techniques include manual microscopic examination and RDT. These approaches are vulnerable to human mistakes. Early detection of malaria can help in reducing the death rates across the globe. Deep Learning can emerge as a highly beneficial solution in the diagnosis of disease. This model gives a faster and cheaper method for detecting plasmodium parasites. The custom convolutional neural network is primarily designed to distinguish between healthy and infected blood samples. The proposed model consists of three convolutional layers and fully connected layers each. The neural network presented is a cascade of several convolutional layers having multiple filters present in layers, which yields the exceptionally good accuracy as per the available resources. The model is trained and later several blood sample images are fed to test the accuracy of the designed system. The CNN classifier has performed exceptionally well under limited computational resources giving an accuracy of 95%. Blood smear sample analysis can also aid in the detection of certain other illnesses and the application of deep learning models will help in the greater good of humankind.