Male Fertility Rescue: AI can identify healthy sperm in infertile men in seconds

Copenhagen, Denmark – Tracking down the problems that contribute to male infertility could get a lot easier soon. Researchers have unveiled a new artificial intelligence (AI) tool that can find viable sperm inside severely infertile men in seconds. The application of the AI ​​algorithm could give hope to men who want a biological child but cannot conceive naturally.

The current process normally takes six hours to find and isolate sperm from human tissue. It involves undergoing a procedure in which part of their testicles is removed. Embryologists then manually extract sperm from this sample to fertilize their partners’ eggs through intracytoplasmic sperm injection (ICSI) treatment.

The long hours required to extract sperm can play a role in successfully identifying viable samples as embryologists may experience mental and physical fatigue. Embryologists have to mince tissue samples and separate them with fine needles. Any available sperm is then placed in a special liquid in a Petri dish. Using a microscope, the doctor looks through the droplets of the liquid to examine the semen. However, contamination from other particles and cells can allow an embryologist to lose a sperm. Also, the longer the process takes, the greater the chance that the sperm will no longer be usable.

In the current study, the researchers used artificial intelligence to see if it could speed up the process. The tool is called SpermSearch and was installed on a computer at an IVF clinic over a period of five months. First they trained the algorithm to identify sperm by showing thousands of microscopic photographs. Each image contained sperm and large amounts of cells and debris, but only the sperm was highlighted.

Sperm flow
(Tatiana Shepeleva –

The AI ​​would eventually learn through images what a sperm looks like in different contexts. The team used healthy sperm and testicular tissue samples from seven patients aged 36 to 55. All have been diagnosed with non-obstructive azoospermia where there is no sperm in their semen. About one percent of men have this more severe form of infertility, and the condition is seen in about five percent of couples who seek fertility treatments.

The AI ​​tool and an embryologist – whose accuracy in examining sperm was believed to be 100% – ran the test simultaneously. The results showed that the algorithm was more accurate than an experienced doctor. Although there have been some cases where the sperm was only detected by the embryologist and vice versa.

The AI ​​tool found 60 more sperm and was five times more accurate at identifying the sperm in the special liquid. Data from this study shows that artificial intelligence can spare healthcare workers from this laborious process. This gives the embryologist more time to evaluate whether the sperm is a good sample for ICSI treatment.

This tool has the ability to give patients who have very little chance of fathering their own biological children a better chance, says lead author Dale Goss, a researcher at the Sydney University of Technology, in a news release. The algorithm improves on antiquated approaches that haven’t been updated in decades. It will ensure rapid identification of the sperm in the samples, which will not only increase the chance of a couple conceiving their own biological children, but will also reduce the stress on the sperm and increase laboratory efficiency.

While it’s an extraordinary feat, the authors caution that this was a trial run and that more clinical trials are needed to show that the technique is useful in a real-life setting. Furthermore, the algorithm should be tested on other forms of infertility or on people undergoing other surgical approaches.

“Finding microscopically healthy sperm in testicular biopsy fragments can be an arduous process. The prospect of using artificial intelligence to make the process faster and more accurate is very attractive. We need to see more research to build on these findings, says Carlos Calhaz-Jorge, a professor at the Northern Lisbon Hospital Center and Hospital de Santa Maria in Lisbon, Portugal, who was not involved in the research.

The study was presented at the 39th annual meeting of the European Society of Human Reproduction and Embryology.

Youtube videos

#Male #Fertility #Rescue #identify #healthy #sperm #infertile #men #seconds
Image Source :

Leave a Comment