Leaderboard Neuron Segmentation
Results for the neuron segmentation category, averaged over all samples.
Group | Submission | CREMI score | VOI split | VOI merge | ARAND |
---|---|---|---|---|---|
DIVE | pi-net | 0.728 | 1.480 | 0.270 | 0.305 |
DIVE | seg5 | 0.730 | 1.423 | 0.243 | 0.328 |
DIVE | seg2 | 0.735 | 1.438 | 0.239 | 0.330 |
DIVE | seg1 | 0.745 | 1.461 | 0.242 | 0.333 |
DIVE | CRunet22 | 0.746 | 1.522 | 0.438 | 0.298 |
DIVE | newSeg | 0.752 | 1.471 | 0.252 | 0.335 |
DIVE | ag35-4 | 0.759 | 0.899 | 0.510 | 0.416 |
DIVE | M2uD_CSR | 0.766 | 1.030 | 0.770 | 0.329 |
DIVE | segBW4 | 0.772 | 1.113 | 0.645 | 0.344 |
DIVE | seg0316 | 0.775 | 1.536 | 0.327 | 0.331 |
DIVE | segBW5 | 0.775 | 1.112 | 0.651 | 0.345 |
DIVE | segBW2 | 0.776 | 1.111 | 0.651 | 0.346 |
DIVE | segBW3 | 0.776 | 1.110 | 0.653 | 0.346 |
DIVE | ag35-3 | 0.784 | 0.829 | 0.612 | 0.433 |
DIVE | seg018 | 0.787 | 1.567 | 0.325 | 0.336 |
DIVE | seg4 | 0.791 | 1.565 | 0.347 | 0.340 |
DIVE | ag35-5 | 0.793 | 1.491 | 0.296 | 0.358 |
DIVE | seg030 | 0.793 | 1.584 | 0.328 | 0.337 |
DIVE | seg3 | 0.798 | 1.587 | 0.351 | 0.341 |
DIVE | ag35 | 0.804 | 0.853 | 0.647 | 0.438 |
DIVE | unet2 | 0.972 | 1.481 | 0.803 | 0.419 |
DIVE | unet-2 | 0.972 | 1.481 | 0.803 | 0.419 |
DIVE | unet4 | 0.987 | 1.523 | 0.775 | 0.429 |
DIVE | unet-4 | 0.987 | 1.523 | 0.775 | 0.429 |
DIVE | unet3 | 0.994 | 1.451 | 0.831 | 0.441 |
Legend
- CREMI score
- The geometric mean of (VOI split + VOI merge) and ARAND.
- VOI split and merge
- The Variation of Information between a segmentation X and ground truth Y. The split and merge parts correspond to the conditional entropies H(X|Y) and H(Y|X), respectively.
- ARAND
- The Adapted Rand Error, i.e., 1.0 - Rand F-Score.
For each value, lower is better.
Leaderboard Synaptic Cleft Detection
Results for the synaptic cleft detection category, averaged over all samples.
Group | Submission | CREMI score | FP | FN | 1 - F-score | ADGT | ADF |
---|---|---|---|---|---|---|---|
I2I | SparSep | 66.76 | 151781.7 | 11350.3 | 0.188 | 87.35 | 46.17 |
SDG | SnapX.O | 124.59 | 182577.0 | 17000.7 | 0.306 | 205.18 | 44.01 |
SDG | SnapF.V | 124.59 | 182577.0 | 17000.7 | 0.306 | 205.18 | 44.01 |
VCG | FgSm0808 | 57.34 | 75120.7 | 9109.7 | 0.107 | 72.74 | 41.94 |
CMM | UNet50 | 69.31 | 65762.0 | 12634.7 | 0.139 | 97.45 | 41.17 |
SDG | PyTC20 | 65.68 | 167107.0 | 6190.0 | 0.196 | 90.36 | 41.00 |
I2I | CleftB1 | 64.97 | 80004.7 | 19895.0 | 0.158 | 90.98 | 38.97 |
JRC | DTU-1 | 72.21 | 85169.0 | 13607.3 | 0.131 | 106.31 | 38.11 |
DIVE | cleft | 88.46 | 97220.7 | 21239.3 | 0.172 | 139.74 | 37.18 |
DIVE | MixUNet2 | 65.19 | 106260.3 | 13962.0 | 0.188 | 95.28 | 35.09 |
3DEM | Part_A | 65.43 | 112964.7 | 10645.0 | 0.174 | 96.87 | 34.00 |
SDG | PyTC20-P | 64.59 | 215905.3 | 4962.0 | 0.227 | 96.14 | 33.05 |
DIVE | SegCleft | 77.03 | 80978.3 | 20639.3 | 0.162 | 121.03 | 33.03 |
DIVE | celft_1 | 77.03 | 80978.3 | 20639.3 | 0.162 | 121.03 | 33.03 |
DIVE | ex19t5 | 315.97 | 64192.0 | 1757.3 | 0.112 | 600.79 | 31.15 |
CleftKing | CleABC3 | 59.10 | 106917.7 | 10746.3 | 0.165 | 87.22 | 30.99 |
SDG | Unet2 | 63.92 | 202177.7 | 13156.0 | 0.256 | 97.64 | 30.19 |
CleftKing | CleABC2 | 59.47 | 110518.3 | 10494.7 | 0.170 | 88.88 | 30.05 |
DIVE | CleftNet | 57.73 | 116095.3 | 8004.3 | 0.169 | 85.60 | 29.87 |
DIVE | Aug-UNet | 57.89 | 123985.7 | 7992.0 | 0.177 | 86.45 | 29.32 |
DIVE | MixUNet | 57.91 | 125220.0 | 7920.0 | 0.178 | 86.57 | 29.25 |
CleftKing | CleABC1 | 58.02 | 130521.0 | 7637.3 | 0.179 | 87.11 | 28.94 |
DIVE | MixUNet4 | 59.03 | 122122.0 | 7761.3 | 0.177 | 89.35 | 28.71 |
DIVE | MixUNet3 | 59.11 | 125333.0 | 7696.0 | 0.180 | 89.68 | 28.54 |
3DEM | BesA225 | 59.34 | 120053.7 | 7534.0 | 0.177 | 90.88 | 27.80 |
Legend
- CREMI score
- The mean of ADGT and ADF. We are not including the F-Score for now, as our current way of computing it can lead to unfair comparison. We are working on a more robust measure and will update the results accordingly.
- FP, FN, and F-Score
- The False Positives, False Negatives, and the resulting F-Score in the clefts detection volume. See metrics for details.
- ADGT
- The average distance of any found cleft voxel to the closest ground truth cleft voxel.
- ADF
- The average distance of any ground truth cleft voxel to the closest found cleft voxel.
For each value, lower is better (F-Score shown as 1 - F-Score).
Leaderboard Synaptic Partner Identification
Results for the synaptic partner identification category, averaged over all samples.
Group | Submission | CREMI score | FP | FN |
---|---|---|---|---|
AnonumoysGroup | PrTrn66 | 0.620 | 238.000 | 451.667 |
NO2 | lr_affin | 0.567 | 118.333 | 450.000 |
DIVE | PTR_V2 | 0.453 | 162.667 | 333.667 |
HCBS | PrnTrn66 | 0.465 | 178.667 | 322.333 |
HCBS | Tr66t-01 | 0.469 | 182.667 | 318.667 |
PNI | asyn_at1 | 0.490 | 274.333 | 314.667 |
NO2 | lr_balan | 0.447 | 175.333 | 314.000 |
IAL | PSP_full | 0.464 | 187.333 | 310.000 |
PNI | asyn_ori | 0.493 | 310.000 | 302.333 |
PNI | asyn_at0 | 0.468 | 293.333 | 297.000 |
HCBS | Tr66comb | 0.451 | 219.000 | 292.333 |
HCBS | Tr66_80K | 0.449 | 223.000 | 286.667 |
IAL | PSP_unar | 0.461 | 266.667 | 281.000 |
PNI | asyn_mod | 0.423 | 367.667 | 262.333 |
- 14 items
Legend
- CREMI score
- 1 - F-Score of the FP and FN.
- FP, FN
- The False Positives and False Negatives synaptic partner pairs. See metrics for details.
For each value, lower is better.