AI could become a powerful tool in treating male infertility – BBC News

Infertility affects 7% of the male population. Now artificial intelligence (AI) may be about to help solve the problem.

Dr. Steven Vasilescu says that AI software developed by him and his team can detect sperm in samples taken from men with severe infertility 1,000 times faster than a trained eye. copy.

“It could highlight a sperm that’s likely to survive before humans can process what they’re looking at,” he said.

Dr Vasilescu is a biomedical engineer at the University of Technology Sydney (UTS), Australia, and the founder of the medical company NeoGenix Biosciences.

The system he and his colleagues developed is called SpermSearch.

It is designed to help men who do not have sperm when they ejaculate, 10% of men have infertility, a condition called nonobstructive azoospermia (NOA).

Usually in these cases, a small portion of the testicle is surgically removed and taken to a lab, where an embryologist can manually search for healthy sperm.

The tissues are separated and examined under a microscope. If any live sperm are found, they can be extracted and injected into the egg.

Dr Vasilescu said the process can take many employees six or seven hours and risks fatigue and inaccuracies.

“When an embryologist looks down a microscope, what they see is just a complete mess – a star shape of cells,” he said.

“There’s blood and tissue,” Dr. Vasilescu said. “There may be only 10 sperm in total, but there could be millions of other cells. It’s a needle in a haystack.”

In contrast, he says, SpermSearch can find any healthy sperm in seconds, as snapshots of samples are instantly loaded into a computer.

To get to this speed, Dr Vasilescu and his colleagues trained the AI ​​to identify sperm in these complex tissue samples by showing it thousands of such images.

In a published scientific paper, UTS’s biomedical engineering team said in one test, “Searching for sperm was 1,000 times faster than an experienced embryologist.”

However, SpermSearch is not designed to replace embryologists but to act as an aid.

Dr Sarah Martins da Silva says the speed at which sperm are found is very important. “Time is crucial,” says clinical reader in reproductive medicine at the University of Dundee.

“If you have someone who has already collected eggs and you have eggs that need to be fertilized, there’s only a small amount of time for us to be able to do that. Speeding up the process would be hugely beneficial.”

With sperm counts widely reported to have halved in the past four decades, infertility remains a growing problem.

Dr. Meurig Gallagher is another scholar working to help men with infertility problems.

An assistant professor in the Center for Quantitative Biomedical and Systems Modeling at the University of Birmingham, his new technique uses imaging software to monitor sperm tail speed and activity.

He said: “Observing the tail helps to better understand the condition of the specimen. “Small changes can tell us whether sperm is under environmental stress, dying, or responding to biological cues.”

Meanwhile, Belfast-based fertility company Examen uses a technique called single-cell gel electrophoresis to identify DNA damage in individual sperm.

Professor Sheena Lewis and her team have been developing this technique for more than 20 years.

However, Professor Lewis, professor emeritus of reproductive medicine at Queens University Belfast and chief executive officer of Examen, says that while developments in the use of AI are exciting, medicine is progressing. very slow.

For example, SpermSearch is currently in the proof-of-concept stage, after a very small trial involving only seven patients.

Professor Lewis said: “It doesn’t make any sense yet. “The time between when something is in beta to it’s on the market is probably two to five years.

“There’s a long way to go. It also targets a very small group of men with NOA. Anything you can do is great – but it’s never going to go mainstream.”

Back in Sydney, Dr Vasilescu said treatment like theirs was the “last stop”.

“It could be the difference between fertilizing an egg – or just stopping the treatment,” he said.

“If we can make embryologists more efficient, more precise, they can find sperm that they can’t find. That gives a man the opportunity to father his biological child. me.”

The UTS team is now ready to put their AI into clinical trials. “A truly live pregnancy – that’s the next step,” says Dr. Vasilescu.