Classifying stages in the gonotrophic cycle of mosquitoes from images using computer vision techniques.

The ability to distinguish between the abdominal conditions of adult female mosquitoes has important utility for the surveillance and control of mosquito-borne diseases. However, doing so requires entomological training and time-consuming manual effort. Here, we design computer vision techniques to determine stages in the gonotrophic cycle of female mosquitoes from images. Our dataset was collected from 139 adult female mosquitoes across three medically important species-Aedes aegypti, Anopheles stephensi, and Culex quinquefasciatus-and all four gonotrophic stages of the cycle (unfed, fully fed, semi-gravid, and gravid). From these mosquitoes and stages, a total of 1959 images were captured on a plain background via multiple smartphones. Subsequently, we trained four distinct AI model architectures (ResNet50, MobileNetV2, EfficientNet-B0, and ConvNeXtTiny), validated them using unseen data, and compared their overall classification accuracies. Additionally, we analyzed t-SNE plots to visualize the formation of decision boundaries in a lower-dimensional space. Notably, ResNet50 and EfficientNet-B0 demonstrated outstanding performance with an overall accuracy of 97.44% and 93.59%, respectively. EfficientNet-B0 demonstrated the best overall performance considering computational efficiency, model size, training speed, and t-SNE decision boundaries. We also assessed the explainability of this EfficientNet-B0 model, by implementing Grad-CAMs-a technique that highlights pixels in an image that were prioritized for classification. We observed that the highest weight was for those pixels representing the mosquito abdomen, demonstrating that our AI model has indeed learned correctly. Our work has significant practical impact. First, image datasets for gonotrophic stages of mosquitoes are not yet available. Second, our algorithms can be integrated with existing citizen science platforms that enable the public to record and upload biological observations. With such integration, our algorithms will enable the public to contribute to mosquito surveillance and gonotrophic stage identification. Finally, we are aware of work today that uses computer vision techniques for automated mosquito species identification, and our algorithms in this paper can augment these efforts by enabling the automated detection of gonotrophic stages of mosquitoes as well.

Analysis of entomological indices for transmission of Japanese encephalitis in Malkangiri district, Odisha State, east central India during 2015-2019.

There have been repeated episodes of the outbreak of Japanese encephalitis (JE) in Malkangiri district of Odisha State in the recent past. In the current study, we aimed to assess the entomological parameters of JE vectors in the district. Prevalence of JE vector species, their per man hour density (PMHD), dusk index (DI), human blood index (HBI), infection status and other factors responsible for transmission of JE were assessed over 5 years (2015-2019). Culex vishnui was the predominant JE vector species (32.0%) collected, followed by Cx. whitmorei (27.1%) and Cx. tritaeniorhynchus (18.0%). The PMHD was higher in cattle shed (CS) than human dwelling (HD) and outdoor resting collection (ODRC) sites for all the JE vector species, except An. barbirostris. In particular, the PMHD of Cx. vishnui (8.02), Cx. whitmorei (5.71) and Cx. tritaeniorhynchus (5.01) were significantly higher in CS than HD and ODRC. The DI of Cx. vishnui (2.47), Cx. whitmorei (1.66) and Cx. tritaeniorhynchus (1.59) was significantly higher in CS compared to HD and ODRC. The HBI of Cx. vishnui was 0.015, whereas the HBI of Cx. tritaeniorhynchus was 0.009 in the study area. Among the 829 pools of JE vector species subjected to PCR, JE virus was isolated from one pool of Cx. vishnui. Based on the abundance of JE vectors and JE virus isolation from Cx. vishnui, it is requisite to implement systematic and long-term control measures for effective control of JE vector species in Malkangiri district, Odisha State.

Response to insecticides and underlying mechanisms of resistance in the field populations of Aedes aegypti Linnaeus (Diptera: Culicidae) in Puducherry, India.

Background & objectives: Mosquito-borne diseases are major threats to human health worldwide. Successful control of vector mosquitoes requires periodic updates on their response to the insecticides that are in use. Different classes of neurotoxic insecticides have been used in vector control programs. Ae. aegypti and Ae. albopictus are the primary vectors of dengue and have developed resistance to organophosphates and synthetic pyrethroids that are used in vector control programs. Monitoring insecticide pressure and studying the underlying mechanisms of resistance in the field populations of Aedes aegypti are important to formulate resistant management strategies for their control programs. Methods: Aedes aegypti were collected from study sites Lawspet and Abishegapakkam and F1 progeny was subject to biochemical assays to determine the enzyme activity. Insecticide susceptibility tests were conducted to determine vector susceptibility/resistance to malathion and deltamethrin. Adult dried mosquitoes were subjected to multiplex PCR to detect point mutation in the VGSC gene. Results: Insecticide susceptibility test results revealed that Aedes aegypti is resistant to malathion and incipient resistance to deltamethrin has emerged. It was observed that ß-esterase and monoxygense activity were significantly higher in Lawspet sample than the laboratory strain, whereas it was comparatively lower in Abishegapakkam sample than laboratory strain. Multiplex PCR assays showed no kdr mutation in all Ae. aegypti strains. Interpretation & conclusion: Monitoring insecticide resistance in Ae. aegypti would help the local health authorities to implement a rationalized approach for insecticide use in vector control.