Classification of Malaria-Infected Cells using Convolutional Neural Network

Project Code :TCMAPY1267

Objective

Develop a CNN model to accurately classify malaria-infected cells in microscopic images, enhancing rapid and cost-effective diagnosis, especially in resource-limited regions, by evaluating accuracy, sensitivity, and specificity.

Abstract

Malaria remains a significant global health concern, necessitating accurate and efficient diagnostic methods. This study proposes a novel approach for malaria-infected cell classification employing Convolutional Neural Networks (CNNs). We curated a diverse dataset of microscopic images of blood smears, comprising both infected and uninfected cells. Our CNN model, leveraging deep learning techniques, achieved remarkable accuracy in discriminating between the two cell types. The use of transfer learning further improved results by leveraging pre-trained models. This innovative approach offers a rapid and reliable solution for malaria diagnosis, with the potential to revolutionize disease detection in resource-constrained regions.

KEYWORDS: Malaria image dataset,cnn and Mobile net algorithm

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.