AI Could Help Make MRIs More Widely Available
A study published Thursday showed that an MRI (magnetic resonance imaging) machine made from simple, commercially available parts and powered by artificial intelligence performed as well as a traditional MRI machine. This finding could help make this lifesaving but expensive device more accessible.
MRI is a medical imaging technique that provides detailed two- or three-dimensional images of the body’s internal organs in a non-invasive way. MRI plays a crucial role in locating tumors and treating diseases of the central nervous system (brain and spinal cord), muscles, or heart.
However, these sophisticated machines are limited in developing countries. Africa, for example, has less than one machine per million people, compared to about 40 per million in the United States and 55 in Japan. The cost of the latest generation of MRI machines exceeds $1 million.
To address this problem, a team at the University of Hong Kong, led by researcher Yuqiao Zhao, built a simplified, low-power MRI machine using off-the-shelf components for $22,000. They published their results in the prestigious journal “Science.”
