Infertility affects approximately 7% of the male population, and a potential solution may lie in the realm of artificial intelligence (AI). Dr. Steven Vasilescu, a biomedical engineer at the University of Technology Sydney (UTS) and founder of the medical company NeoGenix Biosciences, and his team have developed AI software called SpermSearch, which exhibits remarkable capabilities.
SpermSearch is designed to assist men who face a particularly challenging form of infertility called non-obstructive azoospermia (NOA), where there is no sperm present in the ejaculate, affecting about 10% of infertile men. Typically, in such cases, a small section of the testes is surgically removed and taken to a laboratory, where an embryologist manually searches for healthy sperm.
This process is laborious and time-consuming, taking six to seven hours and involving the risk of fatigue and potential inaccuracies. Dr. Vasilescu describes the microscopic view as a chaotic mixture of cells, including blood and tissue, making it akin to searching for a needle in a haystack.
In contrast, SpermSearch accomplishes the same task in mere seconds by instantly analyzing photographs of tissue samples uploaded to the computer. To achieve this efficiency, Dr. Vasilescu and his team trained the AI by exposing it to thousands of images of sperm within complex tissue samples. In a published scientific paper, the UTS biomedical engineering team demonstrated that SpermSearch is 1,000 times faster than an experienced embryologist in identifying viable sperm.
According to Dr. Sarah Martins da Silva, a clinical reader in reproductive medicine at the University of Dundee, speed in identifying sperm is crucial, especially given the narrow time window for fertilizing eggs during procedures like egg collection.
Male infertility is a growing problem, with factors such as pollution, smoking, poor diets, lack of exercise, and stress contributing to a reported 50% decline in sperm counts over the last four decades.
Other researchers are also exploring innovative approaches to address male infertility. Dr. Meurig Gallagher, an Assistant Professor at the University of Birmingham, uses imaging software to track the speed and behavior of sperm tails, providing insights into their health and responsiveness.
Meanwhile, Examen, a fertility firm based in Belfast, employs single-cell gel electrophoresis to identify DNA damage in individual sperm, a technique developed over two decades by Prof. Sheena Lewis and her team.
Although developments in AI for addressing male infertility are exciting, progress in the medical field can be slow. SpermSearch, currently in the proof-of-concept stage following a small trial with seven patients, still has a long journey ahead before potentially becoming a mainstream solution.
Despite the challenges, Dr. Vasilescu emphasizes that innovative treatments like SpermSearch can make a significant difference, potentially enabling men to father their own biological children. The UTS team is now preparing for clinical trials, with the ultimate goal of achieving a successful live pregnancy using their AI technology.
