Code for paper: Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks By: Davood Karimi and Ali Gholipour
Submitted to IEEE TMI
If you have any questions about the code, please email Davood.Karimi@childrens.harvard.edu.
files included:
data_prep.py read and prepare datasets train_model.py train CNNs ood_detection.py for detecting out-of-distribution data on the trained model
dk_aux.py, dk_model.py, and dk_seg.py include functions that are used by the other codes.