Johns Hopkins researchers found that algorithms trained on manufactured data can be even better than the real thing for important surgical tasks like X-ray image analysis
The new JHU + Amazon Initiative for Interactive AI will advance machine learning, computer vision, natural language understanding, and speech processing while increasing access to these technologies
Credit: Johns Hopkins Medicine
Media Contact: Michael E. Newman, mnewma25@jhmi.edu
In the movie Mary Poppins, the title character sings that a spoonful of sugar helps the medicine go down. Now, Johns Hopkins Medicine researchers have shown how a radioactive sugar combined with a widely used imaging technology could soon help physicians make the medicine work better by enabling them to rapidly detect and monitor infections from the largest group of bacterial pathogens threatening humans.
The new imaging tool uses positron emission tomography commonly known as a PET scan to noninvasively find and track dangerous infections from the microbial family Enterobacterales, a group that includes the Escherichia coli strains that cause food poisoning; Klebsiella pneumoniae, a cause of pneumonia and a severe threat to patients weakened from COVID-19; and Yersinia pestis, the scourge behind the Black Death pandemic of plague in the 14th century that wiped out 75% of the world s pop