Malaria Parasite Detection using 2D CNN

doi:10.1109/ICICT60155.2024.10544705

Paper

Malaria Parasite Detection using 2D CNN

Published Apr 24, 2024 · P. Tejakumarreddy, M.Sunil, C. S. C. N. Senthamilarasi Student

2024 International Conference on Inventive Computation Technologies (ICICT)

2

Citations

0

Influential Citations

Full text

Abstract

Malaria continues to be a major worldwide health issue, especially in areas with poor access to medical treatment. This project presents a novel approach to malaria parasite detection utilizing a 2D Convolutional Neural Network (CNN) framework. The objective is to automate the diagnosis process, reducing the reliance on manual microscopy examination and expediting the identification of infected blood samples. The CNN model is trained on a comprehensive dataset of blood smear images, encompassing both infected and uninfected samples, and is designed to accurately identify the presence of malaria parasites. By leveraging deep learning techniques, this system demonstrates promising results in terms of sensitivity and specificity. This attempts to prevent malaria by offering a reliable and effective instrument for early diagnosis, enabling timely intervention and ultimately, saving lives.

Study Snapshot

This 2D Convolutional Neural Network (CNN) model effectively detects malaria parasites in blood samples, reducing manual microscopy reliance and enabling early diagnosis, potentially saving lives.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Malaria Parasite Detection using 2D CNN

References

Citations