The real problem is liability. Radiologist, if they make a mistake can be sued. Who are you going to sue when the program misdiagnoses you?
NB. In all claims I've seen so far about outperforming radiologist, the common denominator was that people creating these models have mostly never even seen a real radiologist and had no idea how to read the images. Subsequently, the models "worked" due to some kind of luck, where they accidentally (or deliberately) were fed data that made them look good.
NB. In all claims I've seen so far about outperforming radiologist, the common denominator was that people creating these models have mostly never even seen a real radiologist and had no idea how to read the images. Subsequently, the models "worked" due to some kind of luck, where they accidentally (or deliberately) were fed data that made them look good.