Diseases transmitted through water, affect more than 2 billion people worldwide, causing economic difficulties: for the treatment of all these cases resources are needed. For example, in the US, diseases transmitted through water, costs more than $2 billion dollars a year annually 90 million cases. Traditional methods of bacteria detection in water takes too much time and the scientists decided to correct the situation. Details about their development publishes the journal Light: Science & Applications.
Among water-related pathogens one of the most common public health problems is the presence of coliform bacteria in drinking water.
Traditional methods of detecting bacteria, based on culture, often in 24-48 hours with subsequent visual inspection and counting of the colonies expert in accordance with the guidelines of the Agency for the protection of the United States environmental protection Agency (EPA).
Alternatively, the methods of molecular detection, for example based on amplification of nucleic acids, can reduce detection time to a few hours. However, they typically lack sensitivity to detect bacteria at very low concentrations. Also they are not able to distinguish between living and dead microorganisms. In addition, there is no EPA approved method based on nucleic acids for detection cryptonym bacteria in water samples.
Therefore there is an urgent need in automated method with high sensitivity, which can provide fast and high-performance detection of bacterial colonies. This will give an alternative to the currently available EPA approved methods, which take at least 24 hours and require an expert in counting colonies.
In the end, a group of scientists under the leadership of Professor Aydogan Ozkan from the Department of electrical and computer engineering, University of California, Los Angeles (UCLA), USA, and their colleagues have developed an intelligent imaging system on the basis of the AI for the early detection and classification of live bacteria in water samples.
Based on holography, the researchers developed a highly sensitive and high-performance visualization system. It captures microscopic images of the entire bowl with the culture of bacteria. It is necessary to quickly detect the growth of colonies by analyzing slow motion images through a neural network. After the detection of growth of each colony, the second neural network is used to classify the type of bacteria.
Clean water from undrinkable sources: scientists figured out how to purify
The effectiveness of this unique platform was demonstrated by the early detection and classification of three types of bacteria, namely E. coli , Klebsiella aerogenes and Klebsiella pneumoniae. Researchers at UCLA have reached the limit of detection of 1 colonialisme bacteria on 1 liter samples of water for 9 hours total test time. Thus, they demonstrated a saving of time for detection of bacteria for more than 12 hours compared to the standard method EPA.
These results underscore the potential of a new platform for holographic imaging on the basis of the AI, which not only provides highly sensitive, rapid and cost effective detection of live bacteria, but also provides a powerful and versatile tool for studies in Microbiology.