A new mosquito egg counting tool developed by Javed et al. shows the potential applications of AI in parasitology research.
AI (Artificial Intelligence) concept, 3D rendering, abstract image visual *** Local Caption *** © metamorworks / Getty Images / iStock
With the release of ChatGPT late last year, discussions of artificial intelligence moved from the realm of Big Tech and science fiction to headlines. Since then, debates about the potential uses and dangers of these tools have not left the public consciousness.
In an ironic episode, a major science fiction magazine had to close your submission portal last winter after being inundated with AI-generated short stories. More recently, just this week, US President Joe Biden issued a decree establishing new rules for AI.
But it’s not all bad. AI and deep learning methods can help simplify and innovate. For example, in science, it can make it easier to process large data sets and other information.
Which brings me to the main topic of today’s BugBitten blog: a recently published article in the journal Parasites and vectors, EggCountAI: software based on a convolutional neural network for counting eggs Aedes aegypti mosquito eggs by Javed et al. In this article, the authors discuss a free, artificial intelligence (AI)-based automatic tool they developed to count eggs from Aedes aegypti mosquitoes.
Why develop something like this?
Because, as Javed et al. report, “Aedes aegypti Mosquitoes are the primary vector of several medically important viruses, including dengue, Zika, yellow fever, and chikungunya. And while much research has been done on how to limit or even eliminate mosquito-borne pathogens, these diseases remain a major problem worldwide. What’s more, in the future, they may even become a greater concern, as climate change worsens and we become more interconnected.
But why eggs in particular?
Because researchers can actually glean a lot of information just from them. For example, the number of eggs can be used to estimate the mosquito population in an area. Additionally, some pathogens can actually change mosquito behavior, including their fecundity (i.e., the number of eggs they lay).
However, as you can imagine, manually counting small mosquito eggs can be quite difficult, especially since samples can contain high levels of eggs. This is where the software comes in.
Can you count how many eggs are in these figures? Based on Javed, N., López-Denman, AJ, Paradkar, PN et al. EggCountAI: a convolutional neural network-based software for counting Aedes aegypti mosquito eggs. Parasite Vectors 16, 341 (2023). https://doi.org/10.1186/s13071-023-05956-1
Javé et al. created EggCount AI and trained it on egg samples they had collected. They used two different datasets for training, one for “micro” images (with egg counts ranging from 13 to 167) and one for “macro” images (ranging from 133 to 624). Next, they tested the tool to see how it compared to similar software, validating the counts with a manual count (luckily aided by the ImageJ software and not a magnifying glass!).
Overall, EggCount AI performed remarkably well. For micro images, it had an accuracy of 98.88% and for macro images, 96.06%, outperforming similar tools. As Javed et al. According to one report, by producing an accurate egg count, it can lead researchers “to a deeper understanding of mosquito behavior and physical characteristics.” Additionally, for anyone curious about the tool, EggCount AI is free and available on the article page.
So, what is the future of AI for science? It’s hard to say for sure, but it’s clear that this will play an important role in the future of research. And that’s why Parasites and vectors recently launched a new collection of items, Artificial intelligence, parasites and parasitic diseases, welcoming articles reporting on the uses of AI and deep learning in parasitology research, such as EggCount AI. We encourage anyone interested in scientific applications of AI to check back periodically as more articles are added to the collection.
