New Delhi: Artificial intelligence (AI) has enabled a couple to conceive after 19 years of infertility by identifying two viable sperm cells from over 25 lakh microscopic images, according to a study published in The Lancet.

The couple — a 39-year-old man and a 37-year-old woman in the US — had previously undergone several failed in vitro fertilisation (IVF) attempts and two surgical sperm extraction procedures.

Led by Zev Williams, Director of the Columbia University Fertility Center, researchers developed a method called Sperm Tracking and Recovery (STAR), which uses AI to perform high-speed, real-time detection and isolation of rare sperm cells in samples previously classified as azoospermic — containing no visible sperm.

The STAR system employs advanced imaging to capture over eight million images in less than an hour. AI algorithms then locate viable sperm, which are extracted by a robotic tool for use in fertilisation or storage.

In this case, the system analysed 2.5 million images in about two hours and detected seven sperm cells — two motile and five non-motile. The two motile sperm were injected into mature eggs, forming embryos that were implanted into the woman.

Thirteen days later, she tested positive for pregnancy, and at eight weeks, ultrasound confirmed a healthy foetus with a heartbeat of 172 beats per minute.

Researchers said larger clinical trials are underway to assess STAR's potential in treating male infertility.