University of Warwick research warns that popular deep learning systems trained for cancer pathology may be relying on hidden shortcuts rather than genuine biological signals.
There was something similar with a cancer-detecting model somewhat recently. It was trained on a bunch of scans both positive and negative. However, positive scans had to be signed off on by a doctor. So the model just ended up looking for signatures.
There was something similar with a cancer-detecting model somewhat recently. It was trained on a bunch of scans both positive and negative. However, positive scans had to be signed off on by a doctor. So the model just ended up looking for signatures.