Deep learning-based computer assisted detection techniques for malaria parasite using blood smear images

Abstract

Malaria remains a significant global health concern, impacting various regions worldwide. Achieving effective treatment and reducing mortality rates hinges on early and accurate diagnosis. In the year 2021, the World Health Organization (WHO) reported a staggering 619,000 deaths attributed to malaria. Additionally, approximately 214 million individuals were afflicted by this disease during that period. Hence, this study introduces two distinct deep-learning algorithms tailored for malaria disease classification. The first method employs a binary classifier convolutional neural network (CNN) model, attaining an accuracy (ACC) of 90.20%. The second method introduces a customized CNN model that exhibits even greater ACC, reaching an impressive 96.02%. These advanced deep learning (DL) techniques hold the potential to enhance the precision (PRE) and efficiency of malaria diagnosis, ultimately facilitating early disease detection. The study provides comprehensive insights into the proposed models. Model 1 involves malaria disease classification employing a CNN-based binary classifier, while Model 2 adopts a customized CNN architecture. The methodology section elucidates the details of these models, their design, and the execution of experiments undertaken to evaluate their performance. Notably, the proposed method is juxtaposed with the state-of-the-art approach, demonstrating superior results in accurately discerning infected and uninfected malaria blood cell images.