fidoptUltraCortex, cortex and white matter at 9.4 T
9.4 T T1 MR of the brain of one adult with the cerebral cortex and white matter of each hemisphere segmented by hand.
Read before comparing (2)
- Cases. The fixed images of UltraCortex's three test and three development pairs: a test pair's image is a test case, a development pair's a development case. The moving images are left out.
- Sequences. 9 of the 12 subjects were scanned with MP2RAGE and 3 with MP-RAGE (sub-37, sub-45, sub-57), at 0.6 mm except sub-29 (0.8 mm). Their contrast and scale differ, MP2RAGE values reaching about 10,000 and MP-RAGE staying under 1,000, and two of the three test pairs join the two. The gradient non-linearity was not corrected, as the dataset states.
| Accuracy | Cost | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| # | Method | Dice | Surface Dice | HD95 mm | Time s | RAM GB | GPU GB | Machine | Images |
| 11–2 | SynthSeg 1.0CPUapp | 0.848 ±0.013 | 0.907 ±0.009 | 2.49 ±0.21 | 47 | 8.0 | Laptop | ||
| 21–2 | FastSurferVINNGPUapp2 of 4 structures | 0.864 ±0.074 | 0.877 ±0.124 | 5.20 ±2.10 | 52 | 5.2 | 9.2 | Workstation | |
The order averages each method's ranks on Dice, Surface Dice, HD95 mm, so the first one is not always the best in every column. ± is the 95% interval of the mean over the 3 cases. Two neighbours are tied when a paired Wilcoxon test on the shared cases does not find the upper one better on Dice (5%): the places a method could hold are then shown under its own. The best value of each column is in colour. Click a row to see its images, a column title to sort by it.
1 result not ranked: an older run, cases still missing, or a failure on every case
| Accuracy | Cost | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| # | Method | Dice | Surface Dice | HD95 mm | Time s | RAM GB | GPU GB | Machine | Images |
| FastSurferVINNGPUapp2 of 4 structuresolder run | 0.864 ±0.074 | 0.877 ±0.124 | 5.19 ±2.17 | 66 | 4.0 | 8.8 | Laptop | ||
Dice: how much the organ contours overlap, 1 is perfect. Surface Dice: the share of the contours' surfaces within a tolerance of each other, 1 is perfect. HD95: distance between the contours' surfaces.
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
- Truth
- contours by experts the dataset's manual segmentation of the cerebral cortex and the cerebral white matter of each hemisphere (4 labels), corrected voxel by voxel from FreeSurfer's and validated by two neuroradiologists
- Source
- openneuro.org/datasets/ds005216
doi.org/10.18112/openneuro.ds005216.v1.1.0
doi.org/10.1038/s41597-025-04779-2
github.com/MPI-Neuroinformatics/UltraCortex - Licence
- CC0
3 cases for tuning, never tested
sub-29_sub-44/fixed, sub-20_sub-70/fixed, sub-3_sub-57/fixed