Very low magnetic fields with permanent magnets, but deep learning to sort through the images. Not as sharp, but perhaps useful and way better than nothing.
The open access paper in Nature Communications.
A low-cost and shielding-free ultra-low-field brain MRI scanner
Yilong Liu 1,2,7, Alex T. L. Leong1,2,7, Yujiao Zhao1,2,7, Linfang Xiao1,2,7, Henry K. F. Mak 3, Anderson Chun On Tsang 4, Gary K. K. Lau5, Gilberto K. K. Leung4 & Ed X. Wu 1
Magnetic resonance imaging is a key diagnostic tool in modern healthcare, yet it can be cost- prohibitive given the high installation, maintenance and operation costs of the machinery. There are approximately seven scanners per million inhabitants and over 90% are con- centrated in high-income countries. We describe an ultra-low-field brain MRI scanner that operates using a standard AC power outlet and is low cost to build. Using a permanent 0.055 Tesla Samarium-cobalt magnet and deep learning for cancellation of electromagnetic inter- ference, it requires neither magnetic nor radiofrequency shielding cages. The scanner is compact, mobile, and acoustically quiet during scanning. We implement four standard clinical neuroimaging protocols (T1- and T2-weighted, fluid-attenuated inversion recovery like, and diffusion-weighted imaging) on this system, and demonstrate preliminary feasibility in diagnosing brain tumor and stroke. Such technology has the potential to meet clinical needs at point of care or in low and middle income countries
Comments