Abstract
The fruit fly Drosophila melanogaster is a classic research object in genetics and systems biology. In the genetic analysis of flies, a routine task is to determine the offspring size and gender ratio in their populations. Currently, these estimates are made manually, which is a very time-consuming process. The counting and gender determination of flies can be automated by using image analysis with deep learning neural networks on mobile devices. We proposed an algorithm based on the YOLOv4-tiny network to identify Drosophila flies and determine their gender based on the protocol of taking pictures of insects on a white sheet of paper with a cell phone camera. Three strategies with different types of augmentation were used to train the network. The best performance (F1 = 0.838) was achieved using synthetic images with mosaic generation. Females gender determination is worse than that one of males. Among the factors that most strongly influencing the accuracy of fly gender recognition, the fly’s position on the paper was the most important. Increased light intensity and higher quality of the device cameras have a positive effect on the recognition accuracy. We implement our method in the FlyCounter Android app for mobile devices, which performs all the image processing steps using the device processors only. The time that the YOLOv4-tiny algorithm takes to process one image is less than 4 s.
Highlights
We have shown that using a learning strategy with synthetic image generation can significantly improve the accuracy of gender recognition in flies
The dependencies of the Loss and mean average precision (mAP) values on the iteration number for the YOLOv4tiny-synt + mosaic strategy and validation dataset are shown in Figure S5
We proposed an algorithm based on the YOLOv4-tiny network to identify and determine the gender of Drosophila flies located on a white sheet of paper using a mobile app
Summary
One of the traditional ecological indicators in such D. melanogaster tests is the offspring size and gender ratio: the genetic effects of drugs are evaluated by the frequency of recessive lethal mutations linked with gender, leading to the selective death of males having only one X-chromosome. This work usually involves counting a large number of offspring in the fly population to assess their fertility and simultaneously determine their gender to estimate their ratio. This task is performed manually and is extremely time-consuming because genetic experiments require estimating the size of dozens of fly populations, comprising up to several hundred insects [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
