Copyright Interesting Engineering
An AI-guided method developed by US researchers has led to the first successful pregnancy, marking a major advance in fertility treatment. The Columbia University Fertility Center developed the STAR (Sperm Tracking and Recovery) method, which is a new, non-invasive technique. The method is an aid for treating male-factor infertility in men with azoospermia (little or no sperm), a condition that affects 10-15% of infertile men. The STAR method achieved its first success with a patient who had struggled with infertility for nearly 20 years, undergoing multiple failed IVF cycles, manual sperm searches, and two surgical extractions. Challenge of identifying sperm cells Current methods for recovering sperm in men with azoospermia face significant drawbacks. Procedures to surgically retrieve sperm from the testes are often unsuccessful. It often carries risks like vascular problems, inflammation, or reduced testosterone. Manual inspection of samples is lengthy, costly, and can damage sperm via pre-processing with agents or centrifuges. Therefore, the medical field has been challenged to develop a more effective and gentle method for retrieving these rare sperm cells. “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,” said Zev Williams, senior author of the paper and Director of the Columbia University Fertility Center. “Many couples with male-factor infertility are told they have little chance of having a biological child,” Williams added. The STAR method was developed to address the challenge of identifying these rare sperm cells. The team included experts in advanced imaging, microfluidics, and robotics. Quick scanning of millions of images The STAR uses high-powered imaging technology, AI detection, and gentle retrieval using a robot. The system scans the semen sample, capturing over 8 million images in just an hour. Artificial Intelligence quickly analyzes these images to identify viable sperm cells within the debris. Moreover, a microfluidic chip in the STAR method uses tiny, hair-like channels to isolate the exact portion of the semen sample containing the sperm cell identified by the AI. This isolation is immediately followed by a robot, which gently removes the sperm cell within milliseconds, preserving it for use in creating an embryo or for future storage (freezing). In its first test with a couple who had struggled with infertility for nearly 20 years, the STAR system successfully identified and retrieved rare sperm. The patient provided a 3.5 mL semen sample, which STAR scanned through 2.5 million images in about two hours. The process successfully located and isolated two viable sperm cells. These two cells were then used to create two embryos, which ultimately resulted in the patient achieving a successful pregnancy. Although based on a single case, the successful pregnancy using STAR demonstrates the feasibility of this AI-guided technology to overcome the significant, long-standing barriers in treating male-factor infertility due to azoospermia. The potential impact is high, as the researchers emphasize that “You only need one healthy sperm to create an embryo.”
