Scientists have developed an AI technology that can accurately assess the quality of live sperm within seconds. This invention eliminates the need for invasive procedures that compromise sperm viability in IVF treatments. Current clinical techniques require human analysis and chemical staining of sperm to assess sperm morphology. Those operations can harm the sperm.
The new AI-powered method, developed by Monash University's Department of Mechanical and Aerospace Engineering in collaboration with Monash IVF, works on live, unstained sperm, preserving viability.
AI technology with high accuracy
Research published in Advanced Intelligent System shows the new AI technology could analyze sperm imaging with more than 93% accuracy in just a few seconds. According to Dr. Reza Nosrati, this new technology could pave the way for standardized sperm selection through automation in clinical IVF settings.
“The consistency and reliability of our AI model provide unprecedented accuracy in the classification of live sperm morphology. By providing a clear and accurate analysis of sperm quality, it offers promising opportunities for improving clinical selection of sperm and reducing daily variability in clinics. With this tool, we hope to improve fertility treatment outcomes and offer new hope to couples struggling to conceive,” Nosrati said.
Better outcomes
PhD candidate and lead author of the study, Sahar Shahali, says the adaptability of the new AI technology ensures that it can become a versatile tool for (IVF) clinics worldwide. Tests have shown that the new AI technology performs effectively with images of different resolutions. As a result, the technology can be rolled out easily, and with reliable results, in different clinics, worldwide.
“Sometimes in IVF, embryologists need to inject one sperm directly into an egg to increase the chances of fertilization. Although they are experts at finding the best sperm for this process - sperm that are the right shape and size and move freely - it can sometimes take hours to sift through a sample to find the best sperm for injection,” says Professor Deirdre Zander-Fox, Chief Scientific Officer of Monash IVF.
Faster sperm selection
Scientists believe that AI technology makes the process of checking sperm quality faster and, by bypassing invasive testing procedures, leads to better results. They also note that embryologists can monitor the process at all times.
“As a follow-up to this research, Monash IVF hopes to develop an AI algorithm that can be used to drive a sperm selection device that can guide embryologists in selecting sperm at the time of microinjection to help improve IVF outcomes,” concludes Professor Zander-Fox.
Sperm robot
This development could be an important step in increasing the success rate of IVF treatments. Other areas are also working toward that goal. For example, in 2023 Barcelona already successfully tested a sperm robot for fertilizing eggs for IVF treatments. With the help of this robot, the IVF needle was able to place sperm cells even more precisely into eggs, increasing the chances of fertilization.