Design and Implementation of Malaria Disease Detection System Using Convolutional Neural Network

Student: Mujitaba ADAM KABIR (Project, 2025)
Department of Computer Science
Northwest University, Kano, Kano State

Abstract

Malaria remains a significant global health challenge, particularly in resource-limited regions where traditional diagnostic methods like microscopy and Rapid Diagnostic Tests (RDTs) are time-consuming, labor-intensive, and prone to errors. This project aims to address these limitations by developing an AI-driven malaria detection system using Convolutional Neural Networks (CNNs). The system analyzes blood smear images to classify them as malaria-positive or negative. A dataset of 27,558 images from Kaggle was used to train and evaluate the model. The system achieved high accuracy, precision, recall, and F1-score, demonstrating its potential to improve malaria diagnosis. Usability testing revealed a 93% task completion rate and a 4.5/5 user satisfaction score, indicating the system's effectiveness and user-friendliness. The project highlights the potential of deep learning in healthcare and provides a foundation for future work, including clinical validation and real-time deployment.

Keywords
malaria detection convolutional neural network deep learning medical image analysis healthcare AI blood smear diagnostic system computer vision
Filters
Institutions