A new artificial intelligence (AI) tool may be capable of identifying sperm in infertile men in just seconds, a study has suggested.
The research was conducted to test if AI could speed up the treatment process for men, who do not have sperm in their semen.
Currently, some patients go through a treatment called Intracytoplasmic Sperm Injection (ICSI) – where a portion of their testes is removed and embryologists extract sperm manually from the biopsy sample in order to fertilise their partner’s eggs.
This treatment can take up to six hours to find and isolate sperm in the human tissue – but a team of scientists from the University of Technology Sydney have been looking at ways to speed up that process.
How was the study conducted?
The team carried out its research at an IVF clinic in Sydney in two phases over five months using AI software installed on a computer.
Researchers decided to coach the AI tool called SpermSearch, showing it thousands of still microscope photographs.
The images featured sperm and high levels of other cells and debris, but only the sperm was highlighted.
Teaching the AI tool enabled it to learn through image analysis what a sperm looked like using its own evaluation system that checks and adjusts its performance.
Lead author Dale Goss and his team used healthy sperm and then samples of testicular tissue from seven patients aged between 36 and 55.
Some of the participants had been diagnosed with non‐obstructive azoospermia (NOA) and had already undergone surgical sperm retrieval at the clinic.
The men donated tissue left-over after treatment that had been prepared for sperm retrieval but was not needed.
The AI tool takes the lead
The AI tool was then put head-to-head with an embryologist whose precision was considered to be at 100%.
To find the best results, the researchers compared the time both took to identify sperm and their degree of accuracy.
Scientists were able to establish that the AI found more sperm overall.
The AI tool managed to find 611 sperm compared with the embryologist, who found 560.
The study authors said the algorithm identified sperm for each area of the droplet that it viewed in less than a 1,000th of the time taken by the embryologist.
Read more from Sky News:
Decades of research destroyed after cleaner turns off beeping lab freezer, lawsuit claims
Intermittent fasting as effective as calorie counting for weight loss, study finds
The team, therefore, concluded that the AI was more accurate and precise in identifying sperm.
In a conference presentation at the European Society of Human Reproduction and Embryology, the authors said the study was based on a proof-of-concept test and that a clinical trial was required to understand things further.
The team also said such research should be carried out among men with other forms of severe infertility and who are undergoing other surgical approaches, such as sperm collection from different parts of the testes.
Mr Goss said the tool had the ability to give people the “chance of fathering their own biological children an increased chance”.
He added: “The algorithm improves antiquated approaches that have not been updated in decades.
“It will ensure the rapid identification of sperm in samples, which will not only increase the chance of a couple conceiving their own biological children, but also reduce stress on sperm and increase efficiency in the laboratory.”
