Figure - available from: Scientific Reports
This content is subject to copyright. Terms and conditions apply.
Map of Sarawak state, Malaysian Borneo, showing major rivers and tributaries. Kapit division (in yellow) is located at the central region of Sarawak, bordering Kalimantan of Indonesia. Major cities/towns are shown in red dots. Map was constructed using ArcMap® software v10.3 by Esri (www.esri.com).
Source publication
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, respect...
Citations
... Wild primates are host reservoirs of bacteria, helminths, protozoa, retroviruses, and viruses such as the simian immunodeficiency virus, HIV/AIDS, simian-T-lymphotrophic virus, adult T-cell leukaemia (HTLV-1), and simian foamy virus (Barre-Sinoussi et al., 1983;Cooper and Nunn, 2013;Devaux et al., 2019). Examples of pathogen exchange between humans and African great apes include outbreaks of Ebola and the global HIV/AIDS pandemic (Calvignac-Spencer et al., 2012), cross-species transmission of diarrhea causing enteric pathogens between humans and lemurs inhabiting anthropogenic landscapes (Bublitz et al., 2015), Cryptosporidium parasite infections between humans and chimpanzees (Pan troglodytes) (Parsons et al., 2015), yellow fever (Flavivirus spp.) outbreaks affecting lion tamarins, marmosets, howler monkeys, titi monkeys, capuchins, and humans in Brazil and Argentina (Bicca-Marques and de Freitas, 2010;de Azevedo Fernandes et al., 2017;Dietz et al., 2019;Berthet et al., 2021;Possamai et al., 2022), and the increased prevalence of malaria-carrying mosquitos (Plasmodium knowlesi) in urban areas inhabited by long-tailed macaques, southern pig-tailed macaques, and humans in Borneo (Yunos et al., 2022). In this later case, anthropogenic modifications to the natural environment have resulted in an expanding public health threat associated with an increase in malarial infections. ...
... Macaques serve as hosts for the malarial parasite, Plasmodium knowles. The movement of people into forested areas traditionally inhabited by the macaques "…expose them to wild macaques and mosquitoes that feed on these animals, resulting in potential zoonoses" (Yunos et al., 2022). ...
A growing global human population, habitat conversion, and the indiscriminate exploitation of natural resources have created unsustainable demands on nature, resulting in widespread biodiversity loss. Primates, which represent the third most specious Order of mammals, are facing an extinction crisis. Currently, 69% of primate species are listed by the IUCN as threatened (Vulnerable, Endangered, or Critically Endangered) and 94% have declining populations. Here, we examine two primary threats to primate population persistence, namely the commercialized hunting and capturing of wild primates and their body parts for food, traditional medicine, pets, and use in biomedical research. Both the legal wildlife trade and illegal wildlife trafficking represent multibillion-dollar industries that contribute to primate population decline, a reduction in genetic diversity, and local extirpation. Trade and trafficking also can lead to the emergence of infectious diseases, increasing biosecurity risks to humans. Between 2015 and 2021, CITES reported 337,511 live primates representing at least 99 species were legally traded, with 6.5% sourced directly from the wild. The recent indictment of Cambodian officials for allegedly laundering wild-caught long-tailed macaques into the U.S. by labelling them as captive-bred, highlights the need for greater transparency and accountability. Comprehensive data on the illegal trafficking of primates are extremely difficult to obtain. However, between 2009 and 2017, primates accounted for 20% of all seizures of illegally traded mammals in the air transport sector. International wildlife trafficking is dominated by criminal networks, corruption, and driven by the demands of Frontiers in Conservation Science wealthy consumers. In addition, the internet has expanded international opportunities to connect buyers and sellers of wild-caught primates and their body parts. Despite explicit bans on selling endangered primates, social media sites continue to do so. Moreover, data on the global food security index (GFSI) indicate that as the international demand for wild live primates, their meat, and other body parts has continued to increase, the majority of people in primate range nations have remained food insecure. Given that almost 70% of primate species are negatively impacted by hunting and trapping, we offer a set of recommendations to reduce the trade and trafficking of wild primates.
... Researchers continue to explore and characterize spill-over infections of Plasmodium knowlesi in areas with long-tailed macaque populations and mosquito vectors that can and do feed on humans if macaques are not available (Lee et al., 2022;Stark et al., 2019). Between 2010 and 2020 the detection of P. knowlesi, the malaria parasite associated with long-tailed and pig-tailed macaques in Malaysian Borneo, surged among humans living and working near towns, while the prevalence of infections caused by the "human" malaria parasites P. vivax, P. falciparum, P. malariae, and P. ovale plummeted (Yunos et al., 2022). ...
In 2022, long‐tailed macaques (Macaca fascicularis), a once ubiquitous primate species, was elevated to Endangered on the International Union for Conservation of Nature (IUCN) Red List of Threatened Species. In 2023, recognizing that the longtailed
macaque is threatened by multiple factors: (1) declining native habitats across Southeast Asia; (2) overutilization for scientific, commercial, and recreational purposes; (3) inadequate regulatory mechanisms; and (4) culling due to human–macaque conflicts, a petition for rulemaking was submitted to the United States Fish and Wildlife Service to add the species to the US Endangered Species Act, the nation's most effective law to protect at risk species. The long‐tailed macaque remains unprotected across much of its geographical range despite the documented continual decline of the species and related sub‐species and the recent
IUCN reassessment. This commentary presents a review of the factors that have contributed to the dramatic decline of this keystone species and makes a case for raising the level of protection they receive.
... Researchers continue to explore and characterize spill-over infections of Plasmodium knowlesi in areas with long-tailed macaque populations and mosquito vectors that can and do feed on humans if macaques are not available (Lee et al., 2022;Stark et al., 2019). Between 2010 and 2020 the detection of P. knowlesi, the malaria parasite associated with long-tailed and pig-tailed macaques in Malaysian Borneo, surged among humans living and working near towns, while the prevalence of infections caused by the "human" malaria parasites P. vivax, P. falciparum, P. malariae, and P. ovale plummeted (Yunos et al., 2022). ...
In 2022, long-tailed macaques (Macaca fascicularis), a once ubiquitous primate species, was elevated to Endangered on the International Union for Conservation of Nature (IUCN) Red List of Threatened Species. In 2023, recognizing that the long-tailed macaque is threatened by multiple factors: (1) declining native habitats across Southeast Asia; (2) overutilization for scientific, commercial, and recreational purposes; (3) inadequate regulatory mechanisms; and (4) culling due to human–macaque conflicts, a petition for rulemaking was submitted to the United States Fish and Wildlife Service to add the species to the US Endangered Species Act, the nation's most effective law to protect at risk species. The long-tailed macaque remains unprotected across much of its geographical range despite the documented continual decline of the species and related sub-species and the recent IUCN reassessment. This commentary presents a review of the factors that have contributed to the dramatic decline of this keystone species and makes a case for raising the level of protection they receive.
... The images were acquired from the publicly available dataset MP-IDB (https://github.com/andrealoddo/MP-IDB-The-Malaria-Parasite-Image-Database-for-Image-Processing-and-Analysis). Besides that, archived thin blood films of malaria infections from Kapit Hospital, Sarawak was obtained from previous studies (Daneshvar et al., 2010;Divis et al., 2015Divis et al., , 2018Hu et al., 2021;Yunos et al., 2022). These blood films were fixed with absolute ethanol (BDH, England) for 10 seconds and stained with 10% Giemsa (BDH, England) in Gurrâ buffered water, pH 7.2 (BDH, England). ...
Timely and rapid diagnosis is crucial for faster and proper malaria treatment planning. Microscopic examination is the gold standard for malaria diagnosis, where hundreds of millions of blood films are examined annually. However, this method's effectiveness depends on the trained microscopist's skills. With the increasing interest in applying deep learning in malaria diagnosis, this study aims to determine the most suitable deep-learning object detection architecture and their applicability to detect and distinguish red blood cells as either malaria-infected or non-infected cells. The object detectors Yolov4, Faster R-CNN, and SSD 300 are trained with images infected by all five malaria parasites and from four stages of infection with 80/20 train and test data partition. The performance of object detectors is evaluated, and hyperparameters are optimized to select the best-performing model. The best-performing model was also assessed with an independent dataset to verify the models' ability to generalize in different domains. The results show that upon training, the Yolov4 model achieves a precision of 83%, recall of 95%, F1-score of 89%, and mean average precision of 93.87% at a threshold of 0.5. Conclusively, Yolov4 can act as an alternative in detecting the infected cells from whole thin blood smear images. Object detectors can complement a deep learning classification model in detecting infected cells since they eliminate the need to train on single-cell images and have been demonstrated to be more feasible for a different target domain.
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.
Graphical Abstract
Malaysia has maintained zero cases of indigenous human malaria since 2018. However, zoonotic malaria is still prevalent in underdeveloped areas and hard-to-reach populations. This study aimed to determine the prevalence of malaria among remote indigenous communities in Peninsular Malaysia. A cross-sectional survey was conducted in six settlements in Kelantan state, from June to October 2019. Blood samples were tested for malaria using microscopy and nested polymerase chain reaction (nPCR) targeting the Plasmodium cytochrome c oxidase subunit III ( cox3 ) gene. Of the 1,954 individuals who appeared healthy, no malaria parasites were found using microscopy. However, nPCR revealed seven cases of Plasmodium knowlesi mono-infection (0.4%), and six out of seven infections were in the group of 19 to 40 years old ( P = 0.026). No human malaria species were detected by nPCR. Analysis of the DNA sequences also showed high similarity that reflects common ancestry to other P. knowlesi isolates. These findings indicate low submicroscopic P. knowlesi infections among indigenous communities in Malaysia, requiring PCR-based surveillance to support malaria control activities in the country.
