A new algorithm can determine male fertility faster and more accurately than was previously possible, according to research by a British startup Bayezian.
The breakthrough comes amid growing problems for couples trying to conceive.
A recent report from the World Health Organization estimated that one in six people worldwide now suffers from infertility. Despite perceptions that it is ‘women’s business’, men now contribute approximately 50% of fertility problems.
Indeed, the male factor has become a growing concern. Recent research discovered that sperm counts have dropped by more than 50% in the last 45 years, with a double drop since 2000. Until 7% of people are now affected by infertility but get a diagnosesis could be slow, expensive and unclear.
These issues have led to calls for better fertility testing. About 18 months ago, Bayezian was asked to help. The company, which provides data science and machine learning incubation services, applied AI to the problem.
Crystals, beams and magnets – is this how to make cooling greener?
“We see accurate diagnosis as a crucial tool to address male fertility.
Bayezian sought a solution the MHSMA dataseta collection of semen images from 235 patients with male factor infertility. Each image has been labeled by experts for normal or abnormal sperm acrosome, head, vacuole and tail, making it an attractive dataset for machine learning studies.
Using the data setthe research group built deep learning frameworks that can see a sperm’s morphology.
According to Bayezian, their algorithm detects differences that the human eye cannot detect. The company says it can identify sperm fertility with an accuracy rate of 96% – 2% higher than existing scientific data approaches.
“This project is the perfect example of the team’s tech for good approach,” said Ed Dixon, founder and CEO of Bayezian. “We see accurate diagnosis as a critical tool in helping address male fertility.”