Skip to content

Artificial Intelligence scientists in Hong Kong create high-precision model for identifying fertile sperm, achieving accuracy rates of 96%.

Researchers at HKU scrutinized over 40,000 pictures of sperm from 117 infertile men, employing these images to educate a model.

Researchers in Hong Kong have created an artificial intelligence model capable of identifying...
Researchers in Hong Kong have created an artificial intelligence model capable of identifying fertile sperm with a precision rate of 96%.

Artificial Intelligence scientists in Hong Kong create high-precision model for identifying fertile sperm, achieving accuracy rates of 96%.

The University of Hong Kong (HKU) has made a significant breakthrough in the field of infertility diagnosis with the development of an artificial intelligence (AI) model designed to analyse sperm images. This innovative AI model could potentially revolutionise the way fertile sperm is identified, leading to more effective treatments for infertility.

Professor William Yeung Shu-biu, from HKU's clinical medicine school, spoke about the development of the AI model. The model is designed to replace traditional microscope-based methods for identifying fertile sperm, which are heavily reliant on the subjective judgment of laboratory technicians, increasing the likelihood of human error.

The AI model was used to examine over 40,000 sperm images from 117 men, both those diagnosed with infertility and those without a clear cause. The model was developed to improve the consistency and accuracy of identifying fertile sperm, address the inconsistencies and inaccuracies in the diagnosis of infertility, and potentially help to resolve the issue of subtle abnormalities in sperm that traditional methods often fail to identify.

Male factors contribute to 20 to 70 per cent of infertility cases, making this development particularly significant. According to the World Health Organization (WHO), infertility will become the third most common disease after cancer and cardiovascular disease in the 21st century. The potential impact of the AI model on the diagnosis and treatment of infertility could therefore be substantial.

The traditional methods for identifying fertile sperm are not standardized, leading to varying results in different laboratories. This lack of consistency is a concern, especially when it comes to diagnosing and treating infertility. The development of the AI model could potentially help reduce the number of infertility cases attributed to male factors.

The AI model's development comes at a time when infertility is projected to become one of the most common diseases in the 21st century. With this innovative technology, HKU is taking a leading role in addressing this growing health issue. Further research is needed to establish the accuracy of the model and its potential impact on infertility diagnosis and treatment. However, the initial results are promising, and this development could pave the way for a brighter future for those struggling with infertility.

Read also: