[1] https://www.caiso.com/TodaysOutlook/Pages/supply.aspx#sectio...
1,774 karma · joined January 2, 2014
[1] https://www.caiso.com/TodaysOutlook/Pages/supply.aspx#sectio...
this is the agency that brought you the central fucking subway, a $300M sewer project masquerading as some red paint on van ness, that picked the already-mostly-grade-separated M Ocean over the N Judah to subway-ify and that is incapable of flicking the traffic preemption switch on the rest of the T to the on position without a decades long pedestrian detection LIDAR project for the unique in the world needs of san francisco.
the gradient coils make the noise, and due to field homogeneity requirements, it is safe to assume the superconducting coil is not moved by the gradient coils
this has not been true since 1951
even in this nuclear free fantasy world, medical and industrial sources will still be around and far easier to steal than fission fuel ever was. we've had the tech to make (virtually) free unlimited energy for 70 years and there is no good reason why it hasn't become ubiquitous
unfortunately, the cat's out of the bag and what is currently in use in hospitals around the world is far scarier than misuse of diagnostics. GE has irresponsibly deployed a ML based reconstruction method [1], which freed from the onerous constraint of having to be correct, makes much crisper images than classical methods. classical compressed sensing reconstruction methods come with a mathematical guarantee on the fidelity of the reconstruction. GE's approach does not, it's just a supervised method. kid stuff. the FDA, for their part, is also illiterate and rubber-stamped the method after looking at their paper where 9/10 radiologists preferred the ML reconstructed images.
would be remiss to not point out that Ajil Jalal et al. are doing great work on reconstruction guarantees for compressed sensing with learned priors
[1] https://www.gehealthcare.com/products/magnetic-resonance-ima...