IMO the best way is to just pick a project and work on it. Using application notes and datasheets lets you piece together circuits, and you pick up design patterns along the way.
It's new but not as new as the article tries to make it sound. Has been known for a while and is in use. Further, it's not going to "revolutinize" anything, it's another incremental med that has shown improvement in outcomes. Just like beta blockers and aldactone, it buys you some small clinical benefit.
This shows clear ignorance of what radiologists do, it's like a fish telling someone how to improve land transportation.
For some reason CS people fixate on radiology for automation just because it is imaging, but there's a lot of context behind it. There's a reason a radiologist/pathologist is called a doctor's doctor, and no one in the field is worried about automation.
For perspective: Training to be a radiologist is 5+1 years, your family doc trains for 3.