That is, until the model encounters something it hasn't quite seen before. Hence the need to keep humans in the loop...
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
In my thesis I worked on segmenting both liver & hepatic tumor using NN. It took me weeks to learn how to recognize liver in a CT. On the other hand, a FCN model learned to recognize liver using 30 training images in few seconds
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
The humans reading them currently seem to focus purely on the things they are asked to look for
- End of conversation
New conversation -
-
-
What ground truth do you use to surpass human performance for this specific task?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I have been reading CT scans for 20 years, wrote several textbooks, and am a professor at a little Boston hospital. I see something I have never seen before *every day*. Replacement is a massive engineering challenge that lacks commercial logic for the foreseeable future.
-
Do you see potential for "assistive" intelligence in your work? Tech that would highlight interesting spots in a CT scan and let you annotate scans or otherwise "teach" it to recognize things you would want to be sure to notice?
- Show replies
New conversation -
-
-
Yes. Or preferably, to give a strong recommendation that can be overruled only with cause.
-
That to me is antithetical to good medical practice. We function in a complex environment with lots of nuance. The quickest way to alienate a referrer is to make hard recommendations based on imaging alone.
End of conversation
New conversation -
-
-
Agree with the first sentence. A good report answers a clinical question and recommends further management - integrating available multi-modality imaging/clinical information. ML may well have a role but not in the simplistic way you suggest. Join me for a reporting list anytime!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.