Microscope enhanced with AI may guide in identifying bacteria rapidly and accurately, this could enable clinical microbiologists to diagnose potentially dangerous blood infections and improve patients chances of survival. The bacteria that most often cause bloodstream attacks include the rod-shaped bacterias E. coli, the cocci clusters of Staphylococcus, and the pairs or chains of Streptococcus kinds.
Rapid identification and delivery of antibiotic medications are vital to treating bloodstream attacks, which can kill up to 40 percent of patients who develop them.
Researchers from the Beth Israel Deaconess Medical Center (BIDMC) in the US demonstrated that an AI-enhanced microscope system is “highly adept” at discovering images of bacteria rapidly and accurately.
“This marks the first demonstration of machine learning in the diagnostic area,” said James Kirby from BIDMC.“With further development, we believe this technology could form the basis of a future diagnostic platform that augments the capabilities of clinical laboratories, ultimately speeding the delivery of patient care,” Dr.Kirby said.
According to the study published in the Journal of Clinical Microbiology, the researchers used a Microscope enhanced with AI may guide in identifying bacteria rapidly and accurately to accumulate high-resolution image data from microscopic slides. They trained a convolutional neural network (CNN) – a class of Artificial intelligence to analyse the visual data and then categorise the bacteria structured on their condition and distribution. To train the AI system, the scientists fed the neural network more than 100,000 images from blood samples.
Automated classification can also ameliorate the shortage of human technologists by helping them work more efficiently, “conceivably reducing technologist read time from minutes to seconds”, Kirby suggested.
The machine intellect sorted the images into three types of bacteria (rod-shaped, round clusters, and circle chains or pairs), with practically 95 percent precision.
Automated classification can “conceivably reduce technologist read time from minutes to seconds,” added Dr.Kirby.
Furthermore, the new tool may possibly also have applications in microbiology training and research.
Source- The Hindu