UZ Brussel uses AI to detect sperm cells efficiently in men with reduced fertility

The UZ Brussel hospital has developed a method to make fertility treatments more effective. The hospital uses artificial intelligence to detect sperm cells more quickly and accurately in men with reduced fertility.
The new AI tool was developed by researchers at Brussels IVF, the reproductive medicine centre at UZ Brussel, and the company Robovision’s healthcare division. The technology, called T'easy, could be a major step forward in improving the effectiveness of fertility treatments.
In men who have no sperm cells in their ejaculate, a TESE procedure, or testicular sperm extraction, can be performed.
"TESE offers men with reduced fertility a chance to have their own biological children"
“This involves the doctor removing a small piece of tissue from the testicles to isolate sperm cells,” says UZ Brussel. “These can then be used for ICSI, a form of IVF in which a single sperm cell is injected directly into an egg cell. TESE thus offers men with reduced fertility a chance to have their own biological children.”
The method, which has been in use since 1995, has now become a routine treatment for infertile men, but results vary as it’s not always easy to detect sperm cells. T'easy combines an app, a customised microscope and AI to detect sperm cells in testicular tissue automatically and quickly. Using an AI model, T'easy can detect an average of 98 per cent of the sperm cells in just 10 minutes.
Time savings
“Thanks to T'easy, we can detect sperm cells faster and more accurately, which gives prospective parents faster clarity about the chances of success of their fertility treatment,” the hospital said. “It furthermore reduces the risk of missing usable sperm cells.”
T'easy means considerable time savings for healthcare providers. Manually detecting sperm cells in testicular tissue is labour-intensive and time-consuming and requires specialised staff, as sperm cells are often scarce and difficult to find in this tissue.
The application was developed with support from Vlaio and Innoviris. T'easy is currently only being used for research purposes.
#FlandersNewsService | Illustration © PHOTO PHOTOPQR / VOIX DU NORD / JULIE SEBADELHA / MAXPPP
Related news