AI system to find and collect very rare sperm

Rare sperm screening and retrieval with a domain-adaptive deep learning-enabled microwell system.

NIH-funded research Brigham and Women's Hospital · NIH-11322720

An AI-powered lab tool that looks for and helps retrieve tiny numbers of sperm to help men with very low sperm counts or azoospermia try for biological children.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionBrigham and Women's Hospital NIH-funded
Lab location1 site (Boston, United States)
Project IDNIH-11322720 on NIH RePORTER

What this research studies

This project builds a tiny-well (microwell) lab device combined with domain-adaptive deep learning to spot sperm that are extremely rare in semen or testicular samples. The device isolates small volumes so the AI can rapidly scan and flag candidate sperm that would be very time-consuming to find by eye. Flagged sperm can then be retrieved for use with assisted reproductive technologies, potentially avoiding or reducing the need for invasive testicular surgery. The team is addressing past limits of microfluidic and machine-learning methods by adapting the AI to work reliably across different sample types and lab conditions.

Who could benefit from this research

Good fit: Men with non-obstructive azoospermia or very low sperm counts (severe oligospermia) who are pursuing assisted reproductive help are the most likely candidates for this approach.

Not a fit: Men whose testes produce no sperm at all (for example certain complete testicular failure or some severe genetic conditions) are unlikely to benefit from this technology.

Why it matters

Potential benefit: If successful, the system could let some men avoid invasive sperm-retrieval surgery by finding usable sperm in ejaculates or small lab samples, improving chances of having biological children.

How similar studies have performed: Previous microfluidic and machine-learning approaches showed promise but have not replaced manual microscope searches, so combining microwells with domain-adaptive AI is a newer, relatively untested clinical approach.

Where this research is happening

Boston, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.