Paludism Diagnosis Using Deep Learning
Fadia Baissi, Elhadj Abdelkader Abdelbaki, Laïd Kahloul, Amira Mohammedi, Asma Ammari · Advances in intelligent systems research/Advances in Intelligent Systems Research · 2024
Medical experts rely on various methods to detect diseases, aiming to identify the presence of parasites in blood samples.This research focuses on crafting a sophisticated deep-learning model tailored for paludism detection, leveraging microscopic images of blood smears.By surpassing the constraints of conventional diagnostic methods, our model seeks to enhance the precision of malaria detection.Our used approache is convolutional neural networks (CNNs).Evaluation is conducted on a publicly accessible dataset of malaria-infected blood smears, affirming the effectiveness of our approach over existing techniques with achieving results in accuracy, precision, F1-score, specificity, recall, sensitivity, and AUC, with values of 0.9975, 0.