Leaderboard Neuron Segmentation
Results for the neuron segmentation category, averaged over all samples.
Group | Submission | CREMI score | VOI split | VOI merge | ARAND |
---|---|---|---|---|---|
IAL | CMaskSP2 | 0.327 | 0.339 | 0.205 | 0.201 |
JRC | MALA v1 | 0.327 | 0.524 | 0.165 | 0.156 |
IAL | MutexWS4 | 0.342 | 0.364 | 0.288 | 0.182 |
JRC | LSDLR | 0.344 | 0.336 | 0.256 | 0.203 |
VCG | mala-seg | 0.349 | 0.452 | 0.245 | 0.179 |
JRC | MALALMC | 0.352 | 0.640 | 0.116 | 0.165 |
IAL | MutexWS3 | 0.362 | 0.362 | 0.312 | 0.199 |
IAL | CMaskSP3 | 0.378 | 0.349 | 0.323 | 0.220 |
IAL | MWS | 0.392 | 0.718 | 0.100 | 0.187 |
IAL | LMC V5 | 0.398 | 0.597 | 0.272 | 0.184 |
IAL | LMC V1 | 0.399 | 0.646 | 0.211 | 0.187 |
IAL | UnetLRMC | 0.410 | 0.442 | 0.374 | 0.208 |
IAL | LMC V3 | 0.445 | 0.655 | 0.308 | 0.208 |
IAL | LMC V2 | 0.446 | 0.629 | 0.285 | 0.219 |
IAL | LMC V4 | 0.447 | 0.622 | 0.295 | 0.219 |
IAL | MutexWS2 | 0.469 | 0.427 | 0.551 | 0.228 |
IAL | spUNet1 | 0.504 | 0.873 | 0.091 | 0.266 |
DIVE | CRNNGate | 0.514 | 1.191 | 0.196 | 0.194 |
IAL | MutexWS1 | 0.514 | 0.423 | 0.626 | 0.255 |
IAL | LMC V6 | 0.516 | 0.672 | 0.415 | 0.245 |
VIDAR | unet3d | 0.534 | 0.833 | 0.282 | 0.256 |
DIVE | MSTW | 0.537 | 0.915 | 0.168 | 0.268 |
IAL | spUNetHC | 0.540 | 0.755 | 0.325 | 0.271 |
VIDAR | mala_py3 | 0.543 | 0.724 | 0.374 | 0.270 |
DIVE | ag35-42 | 0.553 | 0.999 | 0.150 | 0.267 |
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 |
---|---|---|---|---|---|---|---|
DIVE | CleftC2 | 66.19 | 117135.0 | 19904.7 | 0.181 | 83.30 | 49.08 |
3DEM | BesA0.20 | 60.04 | 121311.3 | 7529.0 | 0.182 | 92.91 | 27.17 |
DIVE | CleftC1 | 66.50 | 149148.3 | 12971.0 | 0.187 | 86.56 | 46.43 |
I2I | SparSep | 66.76 | 151781.7 | 11350.3 | 0.188 | 87.35 | 46.17 |
DIVE | MixUNet2 | 65.19 | 106260.3 | 13962.0 | 0.188 | 95.28 | 35.09 |
lbdl | lb_thicc | 59.04 | 107211.3 | 234.0 | 0.190 | 109.17 | 8.91 |
SDG | PyTC20 | 65.68 | 167107.0 | 6190.0 | 0.196 | 90.36 | 41.00 |
DIVE | Mix_ABC2 | 75.02 | 131499.0 | 13795.7 | 0.200 | 78.36 | 71.67 |
DIVE | ex19t2 | 283.68 | 173078.7 | 0.0 | 0.201 | 551.77 | 15.60 |
DIVE | BesUNet | 82.46 | 131090.7 | 15589.0 | 0.206 | 109.52 | 55.40 |
lbdl | lb_lst | 64.22 | 118160.0 | 0.0 | 0.209 | 121.50 | 6.93 |
DIVE | clefitlo | 151.12 | 105664.7 | 32928.0 | 0.220 | 190.20 | 112.05 |
SDG | PyTC20-P | 64.59 | 215905.3 | 4962.0 | 0.227 | 96.14 | 33.05 |
SDG | Unet1 | 75.28 | 185988.3 | 16897.3 | 0.230 | 84.34 | 66.22 |
VCG | FgSemi05 | 57.63 | 221731.7 | 975.7 | 0.232 | 107.73 | 7.52 |
DIVE | cleftloh | 194.25 | 22502.0 | 67513.7 | 0.236 | 102.22 | 286.27 |
SDG | Unet2 | 63.92 | 202177.7 | 13156.0 | 0.256 | 97.64 | 30.19 |
3DEM | All_A | 76.12 | 157692.7 | 6808.7 | 0.256 | 130.59 | 21.66 |
SDG | Unet0 | 171.88 | 33308.3 | 108288.7 | 0.262 | 91.45 | 252.31 |
lbdl | Cleft_lb | 97.85 | 227868.0 | 0.0 | 0.262 | 181.08 | 14.61 |
SDG | Synap0.0 | 118.10 | 193580.0 | 12504.0 | 0.270 | 185.62 | 50.58 |
SDG | SynapX.0 | 118.10 | 193580.0 | 12504.0 | 0.270 | 185.62 | 50.58 |
Kreshuk | MG | 152.52 | 129494.3 | 63958.0 | 0.278 | 157.83 | 147.21 |
DIVE | 3class8t | 198.78 | 262876.7 | 0.0 | 0.282 | 393.81 | 3.76 |
SDG | SynapX.X | 121.40 | 204301.0 | 16302.7 | 0.286 | 194.74 | 48.06 |
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 |
---|---|---|---|---|
NO2 | lr_affin | 0.567 | 118.333 | 450.000 |
DIVE | PTR_V2 | 0.453 | 162.667 | 333.667 |
NO2 | lr_balan | 0.447 | 175.333 | 314.000 |
HCBS | PrnTrn66 | 0.465 | 178.667 | 322.333 |
HCBS | Tr66t-01 | 0.469 | 182.667 | 318.667 |
IAL | PSP_full | 0.464 | 187.333 | 310.000 |
HCBS | Tr66comb | 0.451 | 219.000 | 292.333 |
HCBS | Tr66_80K | 0.449 | 223.000 | 286.667 |
AnonumoysGroup | PrTrn66 | 0.620 | 238.000 | 451.667 |
IAL | PSP_unar | 0.461 | 266.667 | 281.000 |
PNI | asyn_at1 | 0.490 | 274.333 | 314.667 |
PNI | asyn_at0 | 0.468 | 293.333 | 297.000 |
PNI | asyn_ori | 0.493 | 310.000 | 302.333 |
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.