brain_segmentation icon indicating copy to clipboard operation
brain_segmentation copied to clipboard

can't download the ground truth of testing dataset in Brats2015

Open dudu114 opened this issue 6 years ago • 2 comments

As far as I know, using Dice, PPV and Sensitivity to evaluate the segmentation image must have the ground truth of the testing dataset. I cannot get the 'more' that the type of it is .nii of the testing in brats2015 from , although I can download the other files that the type of them is .mha successfully. So i don't know how to evaluate the results.I find the paper 'Brain tumor segmentation with Deep Neural Networks' of Havaei suggest that there is no ground truth provided for the test and leaderboard datasets of brats2013 image,but I'm very curious how does he evaluate the segmentations?Is there anyone who can solve this problem for me?Thanks

dudu114 avatar May 06 '18 12:05 dudu114

The results of those datasets are evaluated online. The online portal evaluates your results.

Delta-Sigma avatar May 18 '18 07:05 Delta-Sigma

I have the testing dataset of BRATS 2013 without ground truth. I want to use the online platform https://www.smir.ch/Home/Browse to evaluate the segmentations, which requires the filetype of input is .mha, but the filetype of segmentations that i get is .png,I don't know how to convert the .png to .mha. I would like to know what online platform you use for evaluation, and if it is same as me. If the answer is yes,how do you convert the .png to the .mha? I sincerely wish you can help me to solve the problem or you can give me some advice of evaluating segmentations?Many thanks! @Delta-Sigma

tiantian-li avatar Jul 10 '18 09:07 tiantian-li