When teams submit their segmentation results, the evaluation results will be sent to the team contact person by e-mail and will be listed below.

RankTeam nameSubmission nameSubmission dateScoreSequences usedDuration
1XMU_SmartDSP23D Spatial Weighted U-Net for Multi-modality Brain MRI Segmentation29-08-1849T1; T1_IR; FLAIR10 min
2lrhsBrain Tissue Segmentation based on Transfer Learning24-03-2153T1; T1_IR; FLAIR34 sec
3Smartdsp37133D weighted U-shape fully convolutional network26-07-1959T1; T1_IR; FLAIR2 min
4TailHotMulti-modality aggregation network313-04-1881T1; T1_IR; FLAIR13 sec
5WTA23D Cascade convolutional architecture - Method 2223-05-18101T1; T1_IR; FLAIR2 min
6XMU SmartDSP3D CNN with a Cross-modality Channel Attention Scheme317-08-18106T1; T1_IR; FLAIR10 min
73DAPCNet3D Anisotropic Pyramidal Convolution Network24-01-21122T1; T1_IR; FLAIR45 sec
8XLab3D Fully CNN with Multi-Modality Feature Fusion310-08-18122T1; T1_IR; FLAIR2 min
9LIVIA_ETSHyperDenseNet206-02-18123T1; T1_IR; FLAIR4 min
10CU_DL2"3D Deep Learning; voxnet2"28-06-16140T1; T1_IR; FLAIR2 min
11CU_DL"3D Deep Learning; voxnet13"16-06-16149T1; T1_IR; FLAIR2 min
12muyaFusion Weighted Network304-07-19153T1; T1_IR; FLAIR10 min
13LRDEFully Convolutional Network20-12-16160T12 sec
14CVSSCNN with Attention Mechanism312-03-19163T1; T1_IR; FLAIR1 min
15MSL-SKKUDeep Convolutional Neural Network19-06-17168T1; T1-IR; FLAIR1.5 min
16QL111111Multi-modality Aggregation Network with Self-attention and Deep Feature Reconstruction218-03-19192T1; T1_IR; FLAIR10 sec
17HUST-CBIB3D Reversible Spatial Attention Network304-01-21204T1; T1_IR; FLAIR20 sec
18MDGRUMulti-Dimensional Gated Recurrent Units327-07-16205T1; T1_IR; FLAIR2 min
19FBI/LMB FreiburgU-Net (3D)01-05-16207T1-1mm; T1-IR; FLAIR2 min
20ASTRI_DLU-Net inspired CNN model with 3D context information225-07-18210T1; T1_IR; FLAIR7 min
21PyraMiD-LSTM2NOCC with rounds323-05-16213T1; T1-IR; FLAIR2 min
22THUityModified U-Net315-08-18217T140 sec
23NISTFully CNN for Multi-Modality Brain Tissue Segmentation14-08-18225T1; T1_IR; FLAIR2 min
24AOCAtlas of Classifiers24-12-17244T16 sec
25IDSIAPyraMiD-LSTM05-06-15249T1; T1_IR; FLAIR2 min
26UDSC_DLMulti-UDense-Net214-09-19254T1; T1_IR; FLAIR4 min
27STHHybrid ANN-based Auto-context method203-06-16267T1; T1-IR; FLAIR5 min
28nanand2DeepLab-v3+ with pre-training on FreeSurfer automated labels316-08-18268T115 sec
29holloww2D Rotation-Driven Convolutions30-07-20276T1; T1_IR; FLAIR13 sec
30ISI-NeonatologyMulti-stage voxel classification31-05-14278T11.5 hours
31UNC-IDEALINKS:Learning-based multi-source integration09-02-15280T1; T1_IR; FLAIR3 min
32CNK3D-Unet-deep supervision05-01-21302T1; T1_IR; FLAIR2 min
33ASTRI_MSARevised VoxResNet27-08-18304T1; T1_IR; FLAIR1 min
34BCH_CRL_IMAGINE3D patch-wise DenseNet and Patch Fusion224-05-18308T1; T1-IR; FLAIR2 min
35LfBMulti-modality Mix Network17-01-19315T1; T1_IR; FLAIR40 sec
36medical_imaging_nitdgpU-Net Inception and Morphological Gradient Channel24-01-20318T1; FLAIR30 sec
37KSOM GHMFASeTs: MAP-Based with Manifold learning13-05-14320T1; T1_IR; FLAIR23 min
38WTA3D Cascade convolutional architecture - Method 1315-05-18321T1; T1_IR; FLAIR5 min
39MNAB2Random Forests21-02-14325T1; T1_IR; FLAIR25 min
40vicorob UdG T1_FMSSEG using T1 + FLAIR (T1-IR skull)14-01-16328T1; IR; FLAIR2 min
41VBM12VBM12_r738 with WMHC=207-10-15331T16 min
42BIGR2Multi-Feature SVM Classification26-09-13345T1; T1_IR; FLAIR35 min
43vicorob UdG T1MSSEG using only T1 (T1-IR skull)21-01-16349T1; IR2 min
44UofL BioImagingMAP-Based Framework26-09-13394T16 sec
45mehran007Tsallis-Entropy Segmentation through MRF04-04-19396T16.5 min
46NarsilSegmentation using Ensemble Trees26-09-13404T1; FLAIR< 2 min
47UB VPML MedMulti-Atlas with Multiway Cut26-09-13409T1; T1_IR; FLAIR30 min
48CMIVModel-guided Level Sets and Skeletons26-09-13413T1; FLAIR3 min
49draiVGG based Fully Convolutional Neural Network20-01-17419T12 sec
50bigr_neuroAutomatically Trained kNN Classifier26-09-13430T1; FLAIR2 hours
51VIBOT10 M-T1+FConvolutional Neural Network27-02-17436T1; FLAIR3 min
52SPM12_T1_F*SPM12 with T1 and FLAIR sequence31-08-15442T1; FLAIR3 min
53S2_QM2Atlas-based segmentation and AdaBoost28-07-14445T1; T1-IR; FLAIR45 min
54SJCEFuzzy Clustering12-04-17449T1<1 min
55RobartsMulti-Atlas with Hierarchical Max-Flow26-09-13451T1-1mm; T1-IR16 min
56KM-MRF-MASMAP on Intensity, and Local and Multi-atlas Priors28-10-16452T110 min
57CSIM-lab_Mqe-MMRFHybrid Modified Entropy-Based Segmentation with Modified MRF25-06-18454T16 min
58SPM12_T1_IR*SPM12 with T1 and IR sequence31-08-15464T1; IR3 min
59SPM12_T1*SPM12 with T1 sequence31-08-15473T13 min
60MNABRandom Decision Forests26-09-13492T1; T1-IR; FLAIR15 min
61SPM12_T1_IR_F*"SPM12 with T1; IR and FLAIR sequence"31-08-15528T1; IR; FLAIR4 min
62FSL-Seg*FSL (v5.0) seg file31-08-15532T110 min
63FreeSurfer*FreeSurfer (v5.3.0)31-08-15539T1-1mm1 hour
64LUH-TNTLevel-sets with dictionary learning27-10-14540T1< 1 min
65FSL-PVSeg*FSL (v5.0) PVSeg file31-08-15544T110 min
66Jedi Mind MeldAutomated Walks using Machine Learning26-09-13559T1; T1-IR; FLAIR27 sec
67mlmi2014ssAdaBoostM228-07-14562T1; T1-IR; FLAIR5 min
68S2_QMBayesian-based Adaptive Mean-Shift26-09-13576T1; T1-IR; FLAIR1.5 hours
69CSIM-LabMultiple Logistic Classification24-10-17590T1
70ISTB UniBeDecision Forests with spatial regularization04-06-14604T1; T1-IR; FLAIR3 min
71LNMBrainsGaussian Intensity Model26-09-13604T1; T1-IR; FLAIR5 min
72ECOESHModified Expectation Maximization06-01-14647T15 min
* These methods (SPM, FSL and FreeSurfer) were applied by the MRBrainS organizers as described in the MRBrainS journal paper.
2, 3 At the end of the submission name indicates that this is the 2nd or 3rd submission (max 3 resubmissions allowed).

Note: As described below, when teams have equal scores, the standard deviations of the three tissue types and the three evaluation measures over all patients are taken into account.

How is the ranking determined?

Ranking is based on the evaluation results of all 15 test datasets and determined as follows: For each evaluation measure (Dice Coefficient (DC), Modified Hausdorff Distance (HD) and Absolute Volume Difference(AVD)), the mean value over all 15 datasets is determined for white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). Each team receives a rank (1=best) for each tissue type (GM, WM, CSF) and each evaluation measure (DC, HD-95, AVD) based on the mean value of the evaluation measures over all 15 datasets. The final score is determined by adding the ranks of all tissue types and evaluation measures for each team. The team with the lowest score is ranked number 1. In case two teams would have an equal score, the team with the lowest standard deviation over the tissue types will be ranked first.