fidoptBrainWeb, 20 simulated brains, tissue classes
A simulated T1-weighted head MR of one of BrainWeb's 20 digital brain phantoms, with the eleven tissue classes it was simulated from.
20 test casesbrainimage MRresearch only
Read before comparing (4)
- Cases. Both images of BrainWeb20's test pairs, one a phantom, named <pair>/<side>. A method gets the simulated T1 alone.
- Truth. Graded synthetic: the eleven classes the image was simulated from (BrainWeb20's), exact by construction up to the class filling most of each 1 mm voxel; thin classes (vessels, dura, the connective tissue around fat) are a few voxels wide.
- Start. Labelling the whole image as each class scores a mean Dice of 0.056 over the eleven at the median of the 20 cases, an Otsu mask 0.148 (grey matter 0.481, white matter 0.330). TotalSegmentator has no tissue class of the brain or the scalp on MR: not run.
- Licence. None stated; the pages ask that their references be cited.
No method has a result on every case of this dataset yet.
Case by case
Click a score to look at that result: the image, the truth in green and the method's map in red. Underlined scores have their image; for the others you see the case without the result.
About the data
- Test cases
- Both images of BrainWeb20's ten test pairs: 20 test cases, one a phantom, and no development case, as in BrainWeb20.
- Truth
- contours a known deformation the phantom's discrete anatomical model brought to the T1's 1 mm grid by the class filling most of each voxel (BrainWeb20's labels); the image is simulated from the phantom, so the classes are exact by construction
- Source
- brainweb.bic.mni.mcgill.ca/brainweb/anatomic_normal_20.html
brainweb.bic.mni.mcgill.ca/brainweb
doi.org/10.1109/TMI.2006.883453 - Licence
- none stated: the BrainWeb pages ask only that their references be cited