Malaria remains one of the major public health problems in Africa, contributing significantly to highmorbidity and mortality rate in the region. Nigeria suffers the world’s greatest malaria burden. Out of thevarious methods of diagnosing malaria, microscopy remains the gold standard for laboratory confirmationof malaria parasite in endemic countries. However, the process requires a trained personnel, it is timeconsuming, labour intensive, and depends on the quality of the microscope thus the need for a computeraided approach. In this article, we explore a deep learning model (convolutional neural network) fordetecting malaria in blood samples with high validation accuracy and sensitivity.