fidoptBaby Open Brains, 31 structures
Brain MR of one infant with the dataset's segmentation of 31 structures (Baby Open Brains).
Read before comparing (2)
- Cases. The fixed images of BOBs's pairs: a test pair's image is a test case, a development pair's a development case. The moving images are left out: their headers carry the pair's start, so they are not the images as delivered.
- Labels. The 31 structures the protocol has the markers edit, with the ventral diencephalon (28, the left ventral diencephalon, is missing from the dataset's dseg.tsv). prepare.py sets the other values to 0: vessels, choroid plexus, CSF, white matter hypointensities, optic chiasm, vermis and the cerebral and cerebellar exteriors, which are outside the protocol and come and go between visits.
| Accuracy | Cost | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| # | Method | Dice | Surface Dice | HD95 mm | Time s | RAM GB | GPU GB | Machine | Images |
| 1 | SynthSeg 1.0CPUapp | 0.626 ±0.146 | 0.701 ±0.156 | 5.06 ±1.83 | 43 | 7.8 | Laptop | ||
| 2 | FastSurferVINNGPUapp29 of 31 structures | 0.051 ±0.026 | 0.080 ±0.037 | 19.15 ±3.07 | 24 | 3.7 | 3.9 | 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 10 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 |
| FastSurferVINNGPUapp29 of 31 structuresolder run | 0.051 ±0.026 | 0.080 ±0.037 | 19.13 ±3.11 | 31 | 2.5 | 3.7 | 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 segmentation of each visit, 31 structures: cerebral white matter and cortex, ventricles, cerebellum, deep grey nuclei, hippocampus, amygdala, ventral diencephalon and brainstem
- Source
- registry.opendata.aws/bobsrepository
doi.org/10.1038/s41597-025-05404-y
doi.org/10.17605/OSF.IO/WDR78
openneuro.org/datasets/ds005450
bobsrepository.readthedocs.io - Licence
- CC BY 4.0
7 cases for tuning, never tested
sub-116845_ses-3mo_ses-6mo/fixed, sub-198202_ses-5mo_ses-8mo/fixed, sub-198549_ses-1mo_ses-7mo/fixed, sub-470437_ses-1mo_ses-7mo/fixed, sub-272097_ses-5mo_ses-8mo/fixed, sub-710922_ses-4mo_ses-7mo/fixed, sub-381606_ses-2mo_ses-8mo/fixed