Automated Malaria Detection Using Deep Learning: A Convolutional Neural Network Approach for Microscopic Cell Image Analysis

This study explores using a Convolutional Neural Network (CNN) for automated malaria detection from microscopic cell images. A dataset of 27,558 images was split into training, validation and testing subsets, all with balanced class representation. The testing dataset was then used to evaluate the model, which achieved an overall accuracy of 94.81% and precision, recall and F1 scores of 0.94 and 0.94 for classes “Uninfected” and “Parasitized”, respectively. The confusion matrix showed that it was reliable, especially for minimizing the false negatives for infected cases. These results highlight the potential of the model to decrease dependence on manual microscopy, increase diagnostic consistency and enable large-scale malaria screening. Through this research, we show the feasibility of integrating deep learning into malaria detection workflows while expanding access to healthcare in underserved regions. Future works include deployment optimization, integration with mobile applications, and validation on multiple site datasets to increase generalizability. The results of this work pave the way for artificial intelligence-powered diagnostics, a burgeoning field, and present a cost-effective, efficient, and scalable solution to combat malaria in high-burden areas.