After 18 years of trying to conceive, one couple is pregnant with their first child thanks to the power of artificial intelligence.
The couple visited birth centers around the world, visiting several in vitro fertilizations, or IVF, in the hopes of giving birth to a baby.
In the IVF process, female eggs are removed and embryos are combined with sperm in the laboratory to create them and implanted into the uterus.
However, for this couple, the IVF attempt was a rare condition in which measurable sperm was not present in the male partner’s semen, which could lead to male infertility. A typical semen sample contains hundreds of millions of sperm, but men in the azosus plant have such low counts that they cannot find sperm cells, even after a few hours of meticulous search under a microscope.
So, the couple, who remained anonymous to protect their privacy, went to Columbia University’s Fertility Center to try a new approach.
It is called The Star Method and uses AI to help identify and recover hidden sperm from men who once thought they had no sperm. All my husband had to do was leave a semen sample with the medical team.
“We maintained hope to a minimum after so many disappointments,” my wife said in an emailed statement.
Fertility Center researchers analyzed semen samples using an AI system. Three hidden sperm was discovered, recovered and used to fertilize the wife’s eggs via IVF, and she successfully completed the first pregnancy enabled by the STAR method.
The baby is scheduled for December.
“It took me two days to believe I was actually pregnant,” she said. “I’m still up in the morning and can’t believe this is true or not. I don’t believe I’m pregnant until I see the scan.”
Artificial intelligence is working towards the US fertility treatment field. More healthcare facilities are using AI to assess egg quality when patients are undergoing IVF and to assess screening of healthy embryos. More research and testing is needed, However, AI may now be progressing towards male infertility.
Dr. Zev Williams, director of the Fertility Center at Columbia University, and his colleagues developed the Star Method for five years to help with detection and recovery Sperm in semen samples of people with azospermia.
They were hit by the results of the system.
“The patient provided the sample and a highly skilled technician searched for two days to try and find sperm through the sample. They didn’t find it. We brought it to an AI-based star system. We found 44 sperm in an hour.
Once semen samples are placed on a specially designed tip under a microscope, the star system representing sperm tracking and recovery is trained to connect to the microscope via high-speed cameras and high-power imaging techniques to scan the sample, taking over 8 million images within an hour to identify them as sperm cells.
This system instantly separates sperm cells into small droplets of media, allowing embryologists to recover cells that they may never have been able to. Find and identify with your own eyes.
“It’s like searching for needles scattered across a thousand haystacks, completing a search within an hour and doing it very gently without any harmful lasers or stains, so you can still use sperm to fertilize the egg,” Williams said.
“What’s surprising is that in a typical sample, instead of the usual (200 million) to 300 million sperm, these patients may have only two or three. “However, the accuracy of the stellar system and the expertise of embryologists allows them to successfully fertilize eggs using a small number of them.”
“A shocking and unexpected diagnosis”
Male partners account for up to 40% of all infertility cases in the United States, and it is estimated that up to 10% of infertility men are azos ospermic.
“This is often a truly heartbreaking, shocking and unexpected diagnosis,” Williams said. “Most men in the Azos plant feel completely healthy and normal. They have no sexual impairment and their semen looks normal. The difference is, if you look under a microscope, you see fragments and fragments of cells, rather than literally seeing hundreds of millions of people sperm swim, but no sperm.”
Treatment options for azosmia traditionally included unpleasant surgery to retrieve sperm directly from a patient’s testes.
“Part of the testis is removed and broken into small pieces where it tries to find the sperm,” Williams said. “It’s invasive. You can only do it a few times. It can damage permanent scars and tests and is painful.”
Other treatment options may include prescription hormone medications, but they are only effective if the person has a hormonal imbalance. If other treatment options are not successful, the couple can have children using donor sperm.
Williams said the Star Method could be a new option.
“It’s really the effort of the team to develop this and it’s the fact that it really drives everyone and motivates them, and can help couples who otherwise wouldn’t have the opportunity,” he said.
Although this method is currently only available at Columbia University’s Fertility Center, Williams and his colleagues want to publish their work and share it with other fertility centers. Using the STAR method, he said, finding, separating and freezing sperm for a patient would cost just under $3,000 in total.
“Infertility is unique in that it is a very old part of the human experience. It is literally the Bible. It is something we had to contest throughout all of human history,” he said. “It’s amazing to think that the most advanced technology we have right now is being used to solve this really old problem.”
It’s not the first time a doctor has turned to AI to help a man with AZOSOSPERMIA.
Another Canadian research team has built an AI model that can automate and accelerate the process of searching for rare sperm in samples from men with a condition.
“The reason AI is so good for this is that it really depends on learning. You can use that learning algorithm to show you what sperm looks like, what shapes are, what properties it should have, and to identify the specific image you are looking for,” in Canada.
“It’s very exciting,” she said. “In general, at least in the medical world, it’s a whole new landscape and I think it really revolutionizes the way we see so many problems in medicine.”
The STAR method is a new approach to identifying sperm, but AI is also used in many other ways in fertility medicine, said Dr. Aimee Eyvazzadeh, a San Francisco-based reproductive endocrinologist and host of the podcast “The Egg Whisperer Show.”
“AI helps us see what our eyes can’t,” wrote Eyvazzadeh, who was not involved in the development of the star, in an email.
AI algorithms, such as what is called Stork-A, are used to analyze early stage embryos and predict them with “amazing accuracy” that are likely to be healthy. Another AI tool, Chloe, can assess the quality of female eggs before freezing them for future use.
“AI is used to personalize IVF drug protocols, making cycles more efficient and less guessing games. It also helps with sperm selection and identifies healthy sperm even in difficult samples. Also, AI can predict IVF success rates more accurately than ever before. “A typical thread? A better decision, more confidence, and a more compassionate experience for the patient.”
The new star system is a “game changer,” she said.
“AI is not producing sperm. It helps us find something unusual and viable already there but almost invisible,” she said. “It’s not because it replaces human expertise, but because it’s amplifying it, but because it’s the future of fertility treatment.”
However, concerns are also growing that the hastily application of AI in reproductive medicine could give patients false hope, says Dr. Giampiero Palermo, director of Androgy, a professor of embryology, who has supported Weil Cornell medicine in fertilization.
“AI has recently gained a lot of traction to provide an unbiased assessment of embryos by examining embryo morphology,” Palermo said in an email. “However, the current available models are still somewhat inconsistent and require additional validation.”
Palermo said the STAR approach needs to be validated, but still, it is necessary to pick up sperm into human developmental scientists and inject them into the eggs to create embryos for patients undergoing IVF.
“The addition of AI was not involved in star development, but Palermo, who first described how to inject sperm directly into the egg, states: Since he pioneered that method, it has become the most utilized supportive reproductive technology in the world.
“In my opinion, this approach is flawed because it inevitably does not have sperm,” Palermo said, “It doesn’t matter how the specimen is screened, whether it’s human or machine.”
