AI-assisted pregnancy: 8 million images in under an hour — how AI helped couple conceive after 18 years of struggle - Times of India

A couple has conceived after nearly two decades of unsuccessful attempts with the help of AI-based fertility breakthrough developed at the Columbia University Fertility Center in New York, reported NY Post. The STAR system -- short for Sperm Tracking and Recovery -- identified viable sperm in a man diagnosed with azoospermia, a condition previously believed to cause complete infertility.Columbia University announced the development in a press release, quoting Dr Zev Williams, director of the fertility center, who said, “A semen sample can appear totally normal, but when you look under the microscope, you discover just a sea of cellular debris, with no sperm visible.”Azoospermia affects up to 15% of infertile men, according to Columbia’s research. Until now, treatment options included painful surgical extraction or the use of donor sperm. “The options have typically been either to use donor sperm or to try undergoing a painful surgery where a portion of the testes is actually removed and they look in the testes to try to find sperm,” Williams told Today.com.

In response, Williams and his team adapted technology originally used by astrophysicists to detect distant planets and stars.

Over five years, they developed the STAR system, using artificial intelligence to scan high-powered images of semen samples.

According to Williams, the system was tested on samples previously examined manually by embryologists without success. STAR located 44 viable sperm within an hour in one such sample. “We’re using the same technologies that are used to search for life in the universe to help create new life right here on Earth,” Williams said.In March 2025, a 38-year-old woman identified only as Rosie became the first to get pregnant using the STAR method. Speaking to Time magazine, she said, “There really was nothing else out there. Especially because I am running quite a few years ahead of where we should be [for fertility]. I’m not that old, but in fertility years — egg-wise — I was reaching my end.”Her husband, diagnosed with azoospermia, provided a semen sample that STAR scanned, capturing over 8 million images in less than an hour. AI algorithms identified three viable sperm cells, which were extracted robotically to avoid damage from traditional methods like centrifugation.“Imagine searching for a single needle hidden among a thousand haystacks scattered across ten football fields — and finding it in under two hours,” Williams told The Bump. “That’s the level of precision and speed delivered by the STAR system.”The sperm were used to fertilise Rosie’s eggs within two hours of collection. After successful embryo transfer, she is now five months pregnant. “I still wake up in the morning and can’t believe if this is true or not,” she told Time. The baby is expected in December 2025.The STAR system is currently available only at Columbia University Fertility Center. Dr. Williams told CNN the cost of identifying, isolating, and freezing sperm through STAR is just under $3,000. According to GoodRx, a standard IVF cycle in the US typically ranges from $12,400 to $15,000, but total expenses can exceed $30,000 with medications and genetic testing.While promising, the innovation has prompted calls for further evaluation. Dr. Robert Brannigan, president-elect of the American Society for Reproductive Medicine, told The Washington Post, “At face value, this looks promising, but as with any new technology in medicine, especially in reproductive care, we need to follow the data and study it further.”The STAR breakthrough comes amid rising concerns over global male infertility. A study cited by Columbia found that sperm counts in Western men fell by 52.4% between 1973 and 2011. Researchers suspect environmental exposures, obesity, poor diets, and sedentary lifestyles as contributing factors.