Infertility affects approximately 7% of the male population, posing a significant challenge to couples trying to conceive. However, a breakthrough in medical technology brought about by AI might offer hope to those affected by this issue.
Dr. Steven Vasilescu, a biomedical engineer at the University of Technology Sydney (UTS) and the founder of NeoGenix Biosciences, has developed an artificial intelligence (AI) tool that could revolutionize the treatment of infertility and remedy low sperm count in males faster.
The AI tool called SpermSearch is a cutting-edge AI system designed to aid in the identification of viable sperm in semen samples, specifically focusing on men with a condition known as non-obstructive azoospermia (NOA), where they have no sperm in their ejaculate. Traditionally, embryologists would manually search for healthy sperm by surgically removing a portion of the testes, a time-consuming and potentially inaccurate process that could take several hours.
SpermSearch, however, can analyse and identify healthy sperm within seconds by processing images of the samples immediately uploaded to the computer. To achieve this remarkable speed, Dr. Vasilescu and his team trained the AI by exposing it to thousands of images of sperm within complex tissue samples.
“It can highlight a potentially viable sperm before a human can even process what they’re looking at,” he says.
Read also: Google to introduce digital watermark to detect AI images, launches Duet AI for Workspace
What SpermSearch offers
The AI tool, SpermSearch, has been designed to help men who have no sperm in their semen at all, 10% of infertile men suffer from this condition called non-obstructive azoospermia (NOA).
Usually, in these cases, a small portion of the testes is surgically removed, and taken to a lab, where an embryologist can manually search for healthy sperm. The tissue is teased apart and examined under a microscope. If any viable sperm are found, they can be extracted and injected into an egg.
This process, says Dr Vasilescu, can take multiple staff six or seven hours, and there is the danger of fatigue and inaccuracy.
“When an embryologist looks down the microscope, what they see is just this complete mess – a starscape of cells,” he says. There’s blood and tissue. There might be only 10 sperm in the whole thing, but there can be millions of other cells. It’s a needle in a haystack,” says Dr Vasilescu.
Dr. Sarah Martins da Silva, a clinical reader in reproductive medicine at the University of Dundee, emphasised the critical importance of speed in identifying viable sperm. Given the limited time window for fertilisation, accelerating the process through AI assistance could provide a significant advantage.
“Time is critical, If you’ve got somebody that’s had an egg collection, and you’ve got eggs that need to be fertilised, there’s only a small time window for us to be able to do that. Speeding up the process would be hugely advantageous.”
Dr. Sarah Martins da Silva, a clinical reader in reproductive medicine at the University of Dundee
However, it’s worth noting that SpermSearch is not intended to replace embryologists but to act as an assistive tool. The human eye and expertise of embryologists remain indispensable in this field. Dr. Vasilescu stressed that the microscope view of complex tissue samples can be overwhelming, with blood, tissue, and numerous other cells obscuring the search for viable sperm. SpermSearch streamlines and accelerates this process, making it more efficient and accurate.
The growing issue of low sperm count in male
Male infertility has become a growing concern, with studies reporting a 50% decline in sperm counts over the past four decades. Various factors contribute to this decline, including pollution, smoking, poor diets, a lack of exercise, and excessive stress.
Other researchers are also exploring innovative approaches to address the problem. Dr. Meurig Gallagher, an Assistant Professor at the University of Birmingham, is using imaging software to track the speed and activity of sperm tails. This technique provides insights into the health of sperm samples, helping identify stress, impending death, or biological responses.
Additionally, Belfast-based fertility firm Examen employs single-cell gel electrophoresis to detect DNA damage in individual sperm. These developments, although exciting, highlight the gradual pace at which medical innovations typically progress.
Read also: Meta to launch AI model that will write computer codes in English
What next for SpermSearch, the AI solution
While SpermSearch has shown immense promise, it is currently in the proof-of-concept stage following a small trial involving just seven patients. The path from proof-of-concept to commercial availability typically spans two to five years, according to Prof. Sheena Lewis, emeritus professor in reproductive medicine at Queen’s University Belfast and chief executive of Examen.
She thinks that while AI development is interesting, it might be limited to specialised treatments for particular ailments like NOA.
Dr. Vasilescu and his UTS team are now preparing for clinical trials, with the ultimate goal of achieving live pregnancies using their AI-assisted technology. Dr. Vasilescu firmly believes that this innovation could make a significant difference in the journey towards parenthood for many couples, offering newfound hope for those facing male infertility issues.
“It can be the difference between fertilising an egg – or just stopping treatment,” he says. If we can make the embryologist more efficient, more accurate, they might find sperm they wouldn’t otherwise find. That gives a man the chance of fathering his own biological children.”
In the realm of reproductive medicine, the fusion of artificial intelligence and human expertise continues to pave the way for innovative solutions, raising the possibility of brighter prospects for those struggling with infertility.