Login | Register

CREMI

MICCAI Challenge on
Circuit Reconstruction from Electron Microscopy Images

Leaderboard Neuron Segmentation

Results for the neuron segmentation category, averaged over all samples.

Change the view to:
Group Submission CREMI score VOI split VOI merge ARAND
JRC MALAMCv3 0.300 0.584 0.062 0.140
IAL HCAvgSP 0.262 0.448 0.063 0.135
IAL HCCAvgSP 0.257 0.438 0.063 0.132
PNI RS-UNet1 0.258 0.435 0.076 0.130
PCH ori_x4 0.839 1.700 0.078 0.398
PNI JRC-UNet 0.239 0.386 0.081 0.123
IAL HCAvgPx 0.224 0.364 0.083 0.114
IAL HCCAvgPx 0.224 0.361 0.085 0.113
JRC MALAMCv2 0.276 0.490 0.089 0.132
IAL spUNet1 0.504 0.873 0.091 0.266
PNI RS-UNet0 0.248 0.376 0.092 0.134
IAL AvgAggLR 0.244 0.372 0.096 0.130
IAL GASP_avg 0.241 0.365 0.096 0.129
IAL MWS 0.392 0.718 0.100 0.187
PNI PNIUNet0 0.229 0.350 0.101 0.117
PNI PNIUNet5 0.228 0.345 0.106 0.116
PNI PNIUNet7 0.228 0.345 0.106 0.116
IAL CMskMWS2 0.246 0.383 0.107 0.125
PNI PNIUNet4 0.237 0.350 0.110 0.122
PCH UNet_mis 0.272 0.453 0.113 0.131
PCH interp_a 0.274 0.472 0.113 0.129
PCH interp 0.275 0.473 0.114 0.129
PNI PNIUNet6 0.237 0.349 0.114 0.122
PNI PNIUNet8 0.237 0.349 0.114 0.122
IAL UnetLMC2 0.221 0.339 0.115 0.108
  • Page 1 of 7
  • 25 of 162 items

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.

Change the view to:
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
VCG FgSm0805 54.23 111486.0 4917.0 0.142 84.04 24.43
DIVE CleftC5 65.75 125395.7 11906.7 0.181 84.10 47.41
SDG PyTC20-1 67.97 131489.3 8699.0 0.167 84.22 51.73
SDG Unet1 75.28 185988.3 16897.3 0.230 84.34 66.22
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 CleftC1 66.50 149148.3 12971.0 0.187 86.56 46.43
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
CleftKing CleABC3 59.10 106917.7 10746.3 0.165 87.22 30.99
I2I SparSep 66.76 151781.7 11350.3 0.188 87.35 46.17
CleftKing CleABC2 59.47 110518.3 10494.7 0.170 88.88 30.05
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
SDG PyTC20 65.68 167107.0 6190.0 0.196 90.36 41.00
3DEM BesA225 59.34 120053.7 7534.0 0.177 90.88 27.80
I2I CleftB1 64.97 80004.7 19895.0 0.158 90.98 38.97
VCG FgUPlus 57.90 137412.7 4763.3 0.160 90.99 24.81
SDG Unet0 171.88 33308.3 108288.7 0.262 91.45 252.31
I2I CleftB 74.31 65334.0 21669.0 0.142 92.36 56.26
3DEM BesA0.20 60.04 121311.3 7529.0 0.182 92.91 27.17
DIVE cleft_hi 107.24 44844.3 52063.7 0.158 94.14 120.33
DIVE MixUNet2 65.19 106260.3 13962.0 0.188 95.28 35.09
SDG PyTC20-P 64.59 215905.3 4962.0 0.227 96.14 33.05

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.

Change the view to:
Group Submission CREMI score FP FN
PNI asyn_mod 0.423 367.667 262.333
NO2 lr_balan 0.447 175.333 314.000
HCBS Tr66_80K 0.449 223.000 286.667
HCBS Tr66comb 0.451 219.000 292.333
DIVE PTR_V2 0.453 162.667 333.667
IAL PSP_unar 0.461 266.667 281.000
IAL PSP_full 0.464 187.333 310.000
HCBS PrnTrn66 0.465 178.667 322.333
PNI asyn_at0 0.468 293.333 297.000
HCBS Tr66t-01 0.469 182.667 318.667
PNI asyn_at1 0.490 274.333 314.667
PNI asyn_ori 0.493 310.000 302.333
NO2 lr_affin 0.567 118.333 450.000
AnonumoysGroup PrTrn66 0.620 238.000 451.667
  • 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.