georgeaccnt-gh / azurechestxraynoaml Goto Github PK

Hello @georgeAccnt-GH, and thank you very much for your implementation of the study! Our team has also tried to replicate your results, and while we have better results than the original poster, we still didn't reach your AUC (we have a mean of 0,81).

What happens is that around epoch 30-35, the algorithms starts overfitting, so training becomes useless as performance on the valid/test sets just drops. We have followed the exact same steps that you have implemented yourself.

Do you think the data splits have an impact and the difference might come from there? Or is there anything else you did specifically to make the network not overfit so fast (we have also tried random crops along with the augmentation techniques used in your implementation, but that didn't help much either)?

Where is the source of blacklist.csv? Is it created by you folks? Or is it created by the people at NIH?

Thanks,