AI can spot sperm 1,000 times faster than trained eyes.
Infertility affects 7% of men worldwide, and artificial intelligence (AI) could help to solve the problem.
Researchers at the University of Technology Sydney (UTS) in Australia have developed an AI system that can spot sperm in samples taken from severely infertile men faster than a trained pair of eyes.
The system called SpermSearch, works by analysing photographs of sperm samples and identifying any healthy sperm cells.
It does this in seconds, compared to the six or seven hours it can take for an embryologist to manually search for viable sperm.
‘It can highlight a potentially viable sperm before a human can even process what they’re looking at,’ said Dr Steven Vasilescu, who developed the software.
It has been designed to help men who have no sperm in their ejaculate at all, a condition called non-obstructive azoospermia (NOA), that affects 10% of infertile men.
In these cases, a small portion of the testes is surgically removed and an embryologist manually searches for healthy sperm in a lab.
This consists of a painstaking process of teasing the tissue apart and examining it under a microscope. If any viable sperm are found, they can be extracted and injected into an egg.
‘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,’ said Dr Vasilescu, speaking to the BBC.
SpermSearch has been trained to quickly identify sperm in these complex tissue samples by showing it thousands of such images.
In a published scientific paper, the UTS biomedical engineering team said that in a test SpermSearch was 1,000 times faster than an experienced embryologist.
The AI is not designed to replace embryologists, but to assist them, thereby improving the chances of success by reducing fatigue and inaccuracy.
While the AI system is still in the early stages of development, it has the potential to revolutionise the treatment of infertility by reducing the time and cost of treatment.
Still, SpermSearch is currently at the proof-of-concept stage, following a very small trial involving just seven patients.
There are a number of other AI-based fertility treatments in development. For example, Dr Meurig Gallagher at the University of Birmingham is developing a technique that uses imaging software to track the speed and action of sperm tails.
This could help to assess the health of sperm cells and identify those that are more likely to fertilise an egg.
Meanwhile, Belfast-based fertility firm Examen uses a technique known as single cell gel electrophoresis to identify DNA damage in individual sperm.
MORE : Man told cancer treatment left him infertile expecting ‘miracle’ baby he may never meet
MORE : Scientists grow human embryo in a lab without sperm, egg or womb
