search

YazhouZhu19 / RPT

[MICCAI 2023] Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
34 stars 5 forks source link

Experimental precision issues. #6

Closed 1islist closed 3 months ago

1islist commented 6 months ago

I reproduced your code and found that the experimental accuracy is far from the paper, I would like to know how did you calculate the final accuracy? Even the experimental results I got in the 50% fold cross validation and using the best supported image are 3 points off from the article results.

meetbbh223 commented 3 months ago

May I ask which datasets you take to train? MRI or CT? When I use CT , the scores hit merely 6-14%.

YazhouZhu19 commented 3 months ago

Hi, Sorry for the delay in replying and thank you for attention. I have updated the files: models/fewshot.py train.py test.py and uploaded the trained models for three datasets under setting 1 and setting 2. You can run and check the results. Thanks again for attention.