Malaria Detection in Microscopic Blood Smears Using Deep Learning: A CNN-Based Framework

Still a life-threatening illness brought on by parasites spread by mosquito bites, malaria presents a major danger to world health. Effective therapy and disease control depend on timely and precise identification of malaria-infected cells in blood smears since delays can cause major health problems or death. In this work, we constructed a convolutional neural network (CNN) model to identify malaria in microscopic images of blood smears. The training set consisted of 220 photos of parasite-infected cells and 196 uninfected cells from a smaller dataset; the test set included 91 images of infected cells and 43 uninfected cells. Trained to identify cells as either “Parasite” or “Uninfected” depending on visual patterns, the model Our approach proved potential in helping malaria diagnosis since it achieved 97% validation accuracy and 87% testing accuracy. This study fits objectives of world health, poverty elimination, lower inequality, and creative solutions to solve health disparities. Although there is always room for development, the suggested CNN model shows promise as a means of enhancing diagnosis capacity, especially in environments with low resources where professional pathologists might not be easily accessible. This paper emphasizes the need of using machine learning to handle worldwide health issues.