Surveillance of mosquitoes that spread malaria will get a shot in the arm from this development.

AI can differentiate and detect the Anopheles mosquito, which is responsible for malaria, from other species of mosquitoes with near-total accuracy, according to researchers reporting in PLOS Neglected Tropical Diseases. (Newsgram)

A research team from the University of Rhode Island in the US used an AI system known as a Convoluted Neural Network (CNN) on this project. The system could effectively identify and classify mosquitoes according to their sex, genus, species, and strain.

The menace of Anopheles and malaria

Eradication of malaria has proved stubbornly difficult because of the wide prevalence of the mosquitoes that spread the disease. In particular, the Anopheles variety.

During mosquito surveillance operations it sometimes becomes very difficult to identify and distinguish this strain from the many other mosquito species.

Malaria is a continuing public health crisis across the world and particularly in sub-Saharan Africa. Hence the need for rapid and accurate detection of the mosquitoes.

How AI worked

The scientists used a database of 1,709 two-dimensional images of adult mosquitoes to train a CNN in detection.

The images of the insects were drawn from 16 colonies in five geographic regions. The collection even had a particular species that even trained medical entomologists could not identify. These images were drawn from both frozen and dried mosquitoes.

After training, the CNN could identify Anopheles with 99.96% accuracy prediction for class and 98.48% accuracy for sex.

“These results demonstrate that image classification with deep learning can be a useful method for malaria mosquito identification, even among species with cryptic morphological variation,” the researchers said. “The development of an independent and accurate method of species identification can potentially improve mosquito surveillance practices.”

Related Story:   Cameras Powered By AI Help Save Elephants