use 1.5 or 3tesla fields). The main
tradeoff is that the signals are
weaker, so signaltonoise ratio is
worse, and as a consequence, image
resolution is lower.
To maintain portability, the ULF
design eschews physical RF shield
ing. Instead the researchers used a
“deep learning” algorithm trained to
recognize and predict interferencesignals, which are then subtracted
from the measured signals. “That’s
one very useful innovation here,”
says biomedical engineer Sairam
Geethanath of Columbia University,who was not involved in the study.
“It’s similar to noisecancellation
headphones, where you’re trying to
learn the noise pattern in realtime
and suppress it.”
The team demonstrated the
device by scanning 25 patients and
comparing the images with those
from a standard MRI machine. The
researchers could identify most
of the same pathologies, including
stroke and tumors. “The images
appear of sufficient quality to be
clinically useful in a number of
scenarios,” says neuroscientist Tom
Johnstone of Swinburne University
of Technology in Melbourne, Austra
lia, who was not involved in the
study. “Rapid assessment of stroke,
which has a large impact on success
of interventions, could be facilitated
by ULF MRI being located in more
towns or even mobile units.”
The new design joins a growing
list of other ULF MRI scanners being
developed. A company called
Hyperfine, based in Guilford, Conn.,
received fda approval last year for yumiyum/Getty ImagesNEWS
Fine details in standard MRI images such as
these currently elude ultralow field scanners,
which instead may be useful in urgent cases
where patients cannot be moved.