An optimised YOLOv4 deep learning model for efficient malarial cell detection in thin blood smear images.

BACKGROUND: Malaria is a serious public health concern worldwide. Early and accurate diagnosis is essential for controlling the disease's spread and avoiding severe health complications. Manual examination of blood smear samples by skilled technicians is a time-consuming aspect of the conventional malaria diagnosis toolbox. Malaria persists in many parts of the world, emphasising the urgent need for sophisticated and automated diagnostic instruments to expedite the identification of infected cells, thereby facilitating timely treatment and reducing the risk of disease transmission. This study aims to introduce a more lightweight and quicker model-but with improved accuracy-for diagnosing malaria using a YOLOv4 (You Only Look Once v. 4) deep learning object detector. METHODS: The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed. RESULTS: The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23 MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone. CONCLUSIONS: The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.

Spatio-temporal distribution and hotspots of Plasmodium knowlesi infections in Sarawak, Malaysian Borneo.

Plasmodium knowlesi infections in Malaysia are a new threat to public health and to the national efforts on malaria elimination. In the Kapit division of Sarawak, Malaysian Borneo, two divergent P. knowlesi subpopulations (termed Cluster 1 and Cluster 2) infect humans and are associated with long-tailed macaque and pig-tailed macaque hosts, respectively. It has been suggested that forest-associated activities and environmental modifications trigger the increasing number of knowlesi malaria cases. Since there is a steady increase of P. knowlesi infections over the past decades in Sarawak, particularly in the Kapit division, we aimed to identify hotspots of knowlesi malaria cases and their association with forest activities at a geographical scale using the Geographic Information System (GIS) tool. A total of 1064 P. knowlesi infections from 2014 to 2019 in the Kapit and Song districts of the Kapit division were studied. Overall demographic data showed that males and those aged between 18 and 64 years old were the most frequently infected (64%), and 35% of infections involved farming activities. Thirty-nine percent of Cluster 1 infections were mainly related to farming surrounding residential areas while 40% of Cluster 2 infections were associated with activities in the deep forest. Average Nearest Neighbour (ANN) analysis showed that humans infected with both P. knowlesi subpopulations exhibited a clustering distribution pattern of infection. The Kernel Density Analysis (KDA) indicated that the hotspot of infections surrounding Kapit and Song towns were classified as high-risk areas for zoonotic malaria transmission. This study provides useful information for staff of the Sarawak State Vector-Borne Disease Control Programme in their efforts to control and prevent zoonotic malaria.

Plasmodium knowlesi infection in humans, Cambodia, 2007-2010.

Two cases of Plasmodium knowlesi infection in humans were identified in Cambodia by 3 molecular detection assays and sequencing. This finding confirms the widespread distribution of P. knowlesi malaria in humans in Southeast Asia. Further wide-scale studies are required to assess the public health relevance of this zoonotic malaria parasite.