>>12623387>I have no idea.well, they probably don't expect you to develop a way to drive the machine, so data acq is prolly out.
image reconstruction is a physical inverse problem, so you prolly won't be doing that either.
that means image processing. and if that's the case, i've been personally shown by an MRI cardiac research doctor how they do their job. they open up the image data with essentially photoshop and use magic lassos. it's appalling. mechanical image seg on DICOMs is the right direction.
>focus on image measurement in multiple sclerosisyou may also want to brush up on some machine learning and machine vision.
