What AI Can See in CT Scans That Humans Can't

If a picture is worth a thousand words, then a CT scan of the chest might as well be Atlas Shrugged. When you think of the sheer information content in one of those scans, it becomes immediately clear that our usual method of CT scan interpretation must be leaving a lot on the table. After all, we can go through all that information and come out with simply "normal" and call it a day.
Of course, radiologists can glean a lot from a CT scan, but they are trained to look for abnormalities. They can find pneumonia, emboli, fractures, and pneumothoraces, but the presence or absence of life-threatening abnormalities is still just a fraction of the data contained within a CT scan.
Pulling out more data from those images - data that may not indicate disease per se, but nevertheless tell us something important about a patient and their risks - might just fall to those entities that are primed to take a bunch of data and interpret it in new ways: artificial intelligence (AI).
Click here to subscribe: czcams.com/users/methodsmanm...
Get more medical news analysis at www.methodsman.com or www.medscape.com

[@sea6808]

I actually really appreciate what the scientists did in this study. While an AI "let loose" on a data set may do a better job at predicting, we wouldn't necessarily know WHY it thinks that. Something like this "middleman" AI allows humans to better stay in the loop. I'd imagine there are a decent chunk of ways to try to affect body composition!

[@commsky]

There was a similar study done (I forgot which paper) and the AI was picking up the model of the CT machine used and accurately predicting outcomes. The only reason the model of the CT was relevant was because certain hospitals using older models happened to be acute care facilities or something to that effect.

[@SmittyWerbenjagermanjensen]

Malpractice insurance reasons probably impacts it as well. And not to overwhelm doctors with information, I think letting it loose would be good, and then having it give an expert level suggestion while leaving out details, treating it exactly as it should be treated, a non-explanatory heuristic.

[@comandante9312]

all those expensive chips r going to calculate the weigh of patients?

[@phsopher]

Weird book choice