Dengue fever, a mosquito-borne disease caused by dengue viruses, is a significant public health concern in many countries especially in the tropical and subtropical regions. In this paper, we introduce a deep learning-based model using Faster R-CNN with InceptionV2 accompanied by image processing techniques to identify the dengue mosquitoes. Performance of the proposed model is evaluated using a custom mosquito dataset built upon varying environments which are collected from the internet. The proposed Faster R-CNN with InceptionV2 model is compared with other two state-of-art models, R-FCN with ResNet 101 and SSD with MobilenetV2. The False positive (FP), False negative (FN), precision and recall are used as performance measurement tools to evaluate the detection accuracy of the proposed model. The experimental results demonstrate that as a classifier the Faster- RCNN model shows 95.19% of accuracy and outperforms other state-of-the-art models as R-FCN and SSD model show 94.20% and 92.55% detection accuracy, respectively for the test dataset.

Dengue is a major public health concern, affecting almost 400 million people worldwide, with about 70% of the global burden of disease in Asia. Despite revised clinical classifications of dengue infections by the World Health Organization, the wide spectrum of the manifestations of dengue illness continues to pose challenges in diagnosis and patient management for clinicians. When the Zika epidemic spread through the American continent and then later to Africa and Asia in 2015, researchers compared the characteristics of the Zika infection to Dengue, considering both these viruses were transmitted primarily through the same vector, the Aedes aegypti female mosquitoes. An important difference to note, however, was that the Zika epidemic diffused in a shorter time span compared to the persisting feature of Dengue infections, which is endemic in many Asian countries. As the pathogenesis of viral illnesses is affected by host immune responses, various immune modulators have been proposed as biomarkers to predict the risk of the disease progression to a severe form, at a much earlier stage of the illness. However, the findings for most biomarkers are highly discrepant between studies. Meanwhile, the cross-reactivity of CD8+ and CD4+ T cells response to Dengue and Zika viruses provide important clues for further development of potential treatments. This review discusses similarities between Dengue and Zika infections, comparing their disease transmissions and vectors involved, and both the innate and adaptive immune responses in these infections. Consideration of the genetic identity of both the Dengue and Zika flaviviruses as well as the cross-reactivity of relevant T cells along with the actions of CD4+ cytotoxic cells in these infections are also presented. Finally, a summary of the immune biomarkers that have been reported for dengue and Zika viral infections are discussed which may be useful indicators for future anti-viral targets or predictors for disease severity. Together, this information appraises the current understanding of both Zika and Dengue infections, providing insights for future vaccine design approaches against both viruses.

No abstract