EggCountAI: A Convolutional Neural Network Based Software for Counting of Aedes Aegypti Mosquito Eggs

Abstract

Abstract 1. Mosquito-borne diseases exert a huge impact on both animal and human populations, posing substantial health risks. Established practices, such as long-lasting insecticidal nets (LLINs) and indoor residual spraying (IRS), are proving inadequate for controlling mosquito-borne diseases. The behavioural fitness traits of mosquitoes, such as locomotion and fecundity, are crucial factors that influence the spread of diseases. Technological advancements, including Artificial Intelligence (AI), have provided various methods that can be used to monitor these traits effectively. 2. This study presents EggCountAI, a Mask RCNN (Region-based Convolutional Neural Network) based free automatic egg counting tool for Aedes aegypti mosquitoes, the primary vector of several life-threatening diseases, including dengue fever. EggCountAI takes a folder containing egg strip images as input and counts eggs in all the images without any supervision. EggCountAI also provides flexible filtration, considering the possibility of unwanted impurities of different sizes on images. The performance of the EggCountAI was tested using microscopic and macroscopic images of eggs laid on a paper strip. To validate EggCountAI's capability, the results were also compared with two commonly employed tools, ICount and MECVision, confirmed by manually counting all eggs on strips. 3. The results obtained from EggCountAI highlight its remarkable performance, achieving an overall percentage accuracy of 98.88% for micro images and 96.06% for macro images. EggCountAI also significantly outperformed two currently available tools, ICount and MECVision, in performance. The overall accuracy of ICount was 81.71% for micro images and 82.22% for macro images, while the overall accuracy of MECVision was 68.01% for micro images and 51.71% for macro images. The superior performance of the EggCountAI was most evident when handling overlapping or clustered eggs. 4. The use of such tools can benefit in establishing the role of mosquito fitness changes to improve epidemiological models and implement new mosquito management strategies. Introducing such tools can also help to reduce transmission by vectors quicker, by finding the mosquitoes' preferred sites to lay their eggs. Though the focus of this AI-based tool is to count the number of eggs, this tool can be modified to track other mosquito fitness parameters such as egg sizes.