Current results of CHAOS

In this page, results of the online submissions are presented for each task. The leaderboard is being updated after each online submission.

Task 1: Liver Segmentation (CT-MRI)
Team Name                  Date        SCORE      Dice     Dice_Scr    RAVD    RAVD_scr   ASSD    ASSD_scr    MSSD    MSSD_scr
FightHCC2D 07/06/19 72.765 0.904 87.569 3.542 50.566 4.996 83.466 31.626 56.094
FightHCC3D 07/06/19 70.557 0.899 86.882 3.279 47.339 4.801 82.737 31.225 55.932
12Sigma 10/06/19 68.026 0.931 91.805 5.34 37.302 2.479 83.473 30.444 51.629
PKDIAv2 07/05/19 50.661 0.854 84.146 6.654 21.657 9.767 75.839 46.561 42.277
MILab2 14/06/19 49.289 0.899 86.832 11.725 12.252 3.927 73.821 80.101 20.29
METU_MMLAB_v102 22/04/19 42.542 0.863 75.942 18.008 14.117 8.506 60.364 62.613 24.943
Task 2: Liver Segmentation (CT only)
Team Name                  Date        SCORE      Dice     Dice_Scr    RAVD    RAVD_scr   ASSD    ASSD_scr    MSSD    MSSD_scr
AbdomenNet V2.1 03/07/19 85.749 0.980 97.977 1.436 71.284 0.679 95.471 13.043 78.262
AbdomenNet V2 03/07/19 85.459 0.979 97.923 1.421 71.586 0.697 95.353 13.815 76.974
FightHCC3D 07/06/19 84.644 0.979 97.947 1.547 69.053 0.692 95.387 14.287 76.188
PKDIAv2 07/05/19 82.457 0.978 97.789 1.32 73.597 0.891 94.059 21.892 64.383
FightHCC2D 07/06/19 82.167 0.977 97.667 1.488 70.235 0.957 93.623 19.713 67.144
DLIPLab 14/06/19 80.963 0.963 96.315 1.611 67.772 1.231 91.796 19.218 67.97
AbdomenNet 23/05/19 80.752 0.964 96.387 1.726 65.578 1.214 91.908 18.52 69.133
Dawn v3 17/07/19 78.965 0.967 96.656 2.028 59.787 1.25 91.663 19.348 67.754
Dawn v2 26/05/19 77.177 0.965 96.489 2.239 58.537 1.422 90.521 22.103 63.162
Dawn 05/05/19 75.998 0.965 96.526 2.268 54.645 1.387 90.753 23.006 62.069
12Sigma 10/06/19 74.429 0.957 95.719 2.326 61.034 1.718 88.55 28.553 52.412
OncoRadiomics 24/05/19 74.347 0.972 97.234 1.618 67.643 2.143 85.711 42.807 46.8
Dense V-Networks(Post) 23/05/19 73.784 0.953 95.263 2.887 50.15 1.568 89.547 23.894 60.176
DeepMedic(Post) 23/05/19 73.317 0.967 96.685 3.179 51.348 1.24 91.732 27.898 53.503
Segreg2 08/07/19 73.292 0.975 97.529 1.385 72.306 1.263 91.58 59.582 31.753
DLIPLab2 25/06/19 72.995 0.964 96.372 3.08 38.809 1.223 91.85 21.03 64.95
AIExplore 19/06/19 71.555 0.948 94.799 3.569 40.832 1.788 88.082 22.497 62.505
Segreg 05/07/19 71.335 0.975 97.476 1.475 70.498 1.622 89.19 66.332 28.176
NEHUSGGSv2 14/05/19 65.18 0.939 93.9 4.597 32.49 2.382 84.117 30.007 50.212
MILab4 28/06/19 62.907 0.966 96.587 4.251 30.115 2.21 85.265 53.497 39.66
V-Net(Post) 23/05/19 60.01 0.896 86.853 6.783 31.581 4.873 76.542 42.524 45.062
Dense V-Networks 23/05/19 59.365 0.951 95.15 2.92 50.131 2.451 83.657 119.508 8.522
OncoRadiomicsV2 14/06/19 58.374 0.936 93.627 11.59 0 2.256 84.962 27.056 54.907
BITLab 24/05/19 56.82 0.953 91.933 4.561 53.327 11.394 78.268 158.676 3.751
DeepMedic 23/05/19 54.428 0.954 95.368 2.341 56.076 7.92 61.87 142.704 4.399
UniSegm 28/05/19 53.76 0.919 91.851 7.825 18.057 3.728 75.148 44.082 29.985
MILab5 08/07/19 53.126 0.961 96.105 6.321 14.486 2.824 82.643 69.772 19.272
NEHUSGGS 09/05/19 52.701 0.935 93.517 4.48 37.187 4.345 71.767 111.218 8.332
V-Net 23/05/19 52.604 0.894 86.786 6.794 31.872 5.535 74.869 80.646 16.888
MILab3 22/06/19 50.421 0.957 95.727 7.311 9.732 3.946 75.374 84.15 20.851
KCliver 17/05/19 49.548 0.756 75.55 24.22 15.291 148.847 66.084 178.089 41.265
MILab2 14/06/19 48.834 0.935 93.521 6.737 15.366 4.847 67.995 85.815 18.452
MILab 14/06/19 46.352 0.935 93.469 6.843 13.451 5.135 66.294 92.223 12.194
Liver_AI_Team2 28/04/19 25.304 0.479 33.909 2.809 50.205 30.513 15.447 123.71 1.654
Liver_AI_Team 22/04/19 14.518 0.496 37.849 14.423 0 27.123 18.28 121.411 1.943

Task 3: Liver Segmentation (MRI only)
Team Name                  Date        SCORE      Dice     Dice_Scr    RAVD    RAVD_scr   ASSD    ASSD_scr    MSSD    MSSD_scr
PKDIAv2 07/05/19 70.712 0.945 94.474 3.529 41.803 1.563 89.58 26.062 56.992
12Sigma5 22/06/19 66.025 0.928 92.802 4.301 35.223 2.397 84.022 30.12 52.052
12SigmaShanghai 02/07/19 65.431 0.934 93.44 4.358 28.673 2.032 86.453 28.594 53.159
FightHCC2D 07/06/19 62.378 0.867 82.725 4.538 39.592 7.06 77.783 38.763 49.411
12Sigma3 07/06/19 61.325 0.919 91.88 6.045 22.425 2.771 81.528 32.135 49.466
FightHCC3D 07/06/19 60.837 0.867 82.281 4.771 33.948 6.74 77.238 38.969 49.88
12Sigma6 22/06/19 60.704 0.899 88.396 5.338 34.856 3.482 77.129 36.199 42.436
12Sigma2 07/06/19 59.861 0.89 89.034 8.804 26.866 12.062 77.581 42.306 45.963
IG5 12/07/19 59.347 0.905 86.365 9.26 23.355 3.86 79.66 35.779 48.01
IG4 04/07/19 59.181 0.909 88.495 7.895 25.453 3.752 80.049 39.662 42.727
Segreg 05/07/19 55.23 0.909 89.728 7.167 30.404 3.903 75.514 59.437 25.274
IG3 04/07/19 54.358 0.892 85.606 9.282 27.146 4.685 74.515 62.255 30.167
MILab4 28/06/19 54.017 0.875 84.067 10.115 21.034 4.029 76.754 50.492 34.215
IG 01/07/19 53.263 0.9 87.629 8.383 26.915 4.462 75.296 67.186 23.212
METU_MMLAB_v102 22/04/19 53.152 0.888 81.057 12.642 10.943 3.476 77.032 35.743 43.574
MILab 14/06/19 50.553 0.863 83.123 10.714 23.806 4.625 72.528 79.723 22.754
MILab5 08/07/19 49.347 0.887 85.089 15.002 4.375 3.5 76.67 53.829 31.253
MILab2 14/06/19 42.185 0.875 84.732 18.368 4.701 4.801 68.071 99.039 11.236
BITLab 24/05/19 31.852 0.704 51.437 459.377 0 9.654 53.127 95.236 22.843
Task 4: Segmentation of abdominal organs (CT+MRI)
Team Name                  Date        SCORE      Dice     Dice_Scr    RAVD    RAVD_scr   ASSD    ASSD_scr    MSSD    MSSD_scr
FightHCC3D 07/06/19 71.284 0.879 84.726 5.552 37.651 4.654 83.119 25.455 63.97
FightHCC2D 07/06/19 71.216 0.878 84.907 6.55 37.435 5.242 82.484 27.501 62.336
12Sigma4 12/06/19 68.15 0.914 88.839 8.035 29.157 2.163 85.632 23.755 62.045
PKDIAv2 07/05/19 49.634 0.878 85.464 8.428 18.97 6.373 82.087 33.171 56.642

Task 5: Segmentation of abdominal organs (MRI only)
Team Name                  Date        SCORE      Dice     Dice_Scr    RAVD    RAVD_scr   ASSD    ASSD_scr    MSSD    MSSD_scr
12SigmaShanghai 02/07/19 68.818 0.928 92.773 6.528 26.854 1.58 89.465 20.53 66.192
12Sigma7 17/07/19 68.1 0.921 91.104 6.517 33.164 1.701 88.657 19.558 68.604
PKDIAv2 07/05/19 66.463 0.93 92.972 6.914 28.652 1.434 90.441 20.101 66.713
12Sigma5 22/06/19 64.63 0.912 89.205 7.219 29.74 1.976 86.828 21.488 65.155
12Sigma4 12/06/19 63.522 0.907 87.853 8.348 23.847 2.107 85.955 22.982 63.114
FightHCC3D 07/06/19 63.437 0.857 81.941 6.192 30.821 5.592 80.596 28.413 62.244
FightHCC2D 07/06/19 61.6 0.849 79.542 7.95 29.58 5.798 79.366 30.109 59.24
AbdomenNet 23/05/19 61.467 0.897 84.389 12.17 18.43 2.592 83.908 24.682 61.87
12Sigma6 22/06/19 60.528 0.885 81.67 10.068 21.508 2.853 81.017 26.032 58.504
METU_MMLAB_v102 22/04/19 56.012 0.886 80.218 12.442 15.626 3.206 79.192 32.7 49.295

(Post)=Post-processing. Tiny artifacts and incorrectly segmented small areas were cleaned by 3D connected component analysis.

Dice=Sørensen–Dice coefficient, Dice_scr=Score of Dice metric
RAVD=Relative absolute volume difference, RAVD_scr=Score of RAVD metric
ASSD=Average symmetric surface distance (millimeter), ASSD_scr=Score of ASSD metric
MSSD=Maximum symmetric surface distance (millimeter), MSSD_scr=Score of MSSD metric

Team Information

PKDIA:
-Pierre-Henri Conze : IMT Atlantique | UMR 1101, Inserm, Brest, France
-Emilie Cornec-Le Gall : UMR 1078, Inserm | Department of Nephrology, University Hospital | UBO, Brest, France
-François Rousseau : IMT Atlantique | UMR 1101, Inserm, Brest, France
-Yannick Le Meur : Department of Nephrology, University Hospital, Brest, France

METU_MMLAB: Bora Baydar, Savaş Özkan, Gözde Bozdağı Akar, Dept. of Electrical and Electronics Eng., Middle East Technical University, Ankara, Turkey

NEHUSGGS: Gajendra Kumar Mourya et al. - Department of Biomedical Engineering, SOT, North Eastern Hill University, Shillong, Meghalaya, India

Dawn: South China University of Technology

Liver_AI_Team: D.Sabarinathan(Couger Inc, Japan), Dr. Parisa Beham, Dr. Priya Kansal (Sethu Institute of Technology, India)

KCliver: Chen Kun, Fudan University Shanghai, China

AbdomenNet: Mandel Chen et al. IFLYTEK South China AI Research Institute, China

DeepMedic [Applied by organizers]: https://biomedia.doc.ic.ac.uk/software/deepmedic/ Biomedical Image Analysis Group, Department of Computing, Imperial College London, London SW7 2AZ, UK

  1. Konstantinos Kamnitsas, Christian Ledig, Virginia F.J. Newcombe, Joanna P. Simpson, Andrew D. Kane, David K. Menon, Daniel Rueckert, and Ben Glocker, “Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation”, Medical Image Analysis, 2016.
  2. Konstantinos Kamnitsas, Liang Chen, Christian Ledig, Daniel Rueckert, and Ben Glocker, “Multi-Scale 3D CNNs for segmentation of brain Lesions in multi-modal MRI”, in proceeding of ISLES challenge, MICCAI 2015.

Dense V-Networks [Applied by organizers via NiftyNet]:

  1. E. Gibson et al., "Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks," in IEEE Transactions on Medical Imaging, vol. 37, no. 8, pp. 1822-1834, Aug. 2018. https://doi.org/10.1109/TMI.2018.2806309
  2. E. Gibson, W. Li, C. Sudre, L. Fidon, D. Shakir, G. Wang, Z. Eaton-Rosen, R. Gray, T. Doel, Y. Hu, T. Whyntie, P. Nachev, M. Modat, D. C. Barratt, S. Ourselin, M. J. Cardoso and T. Vercauteren (2018) NiftyNet: a deep-learning platform for medical imaging, Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2018.01.025

V-Net [Applied by organizers via NiftyNet]:

  1. F. Milletari, N. Navab and S. Ahmadi, "V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation," 2016 Fourth International Conference on 3D Vision (3DV), Stanford, CA, 2016, pp. 565-571. https://doi.org/10.1109/3DV.2016.79
  2. E. Gibson, W. Li, C. Sudre, L. Fidon, D. Shakir, G. Wang, Z. Eaton-Rosen, R. Gray, T. Doel, Y. Hu, T. Whyntie, P. Nachev, M. Modat, D. C. Barratt, S. Ourselin, M. J. Cardoso and T. Vercauteren (2018) NiftyNet: a deep-learning platform for medical imaging, Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2018.01.025

OncoRadiomics:
-Akshayaa Vaidyanathan, Artificial Intelligence Scientist, OncoRadiomics, Liège, Belgium
-Dr. Sean Walsh, Chief Science Officer, OncoRadiomics, Liège, Belgium
-Prof. Dr. Philippe Lambin, Chief Scientific Advisor, OncoRadiomics, Liège, Belgium

BITLab: Lei Chen, Beijing Institute of Technology, Beijing , China.

FightHCC: Jun Ma, University of Toronto, Nanjing University of Science and Technology.
UniSegm: Catalina Gómez et al. Biomedical Computer Vision group at Universidad de los Andes, Colombia

12Sigma: Jie Cai, University of South Carolina U.S. Shizhong Han and Yunqiang Chen, 12Sigma Technologies

12SigmaShanghai: Yuxiang Ye, Yinan chen, Yajing Zhu, 12Sigma Technologies

AIExplore: Smart Healthcare, Manufacturing, and City, Taiwan.

MILab:
SiChuan University, China.

DLIPLab:
Minyoung Chung, Computer Graphics & Image Processing Laboratory, Department of Computer Science & Engineering, Seoul National University, Korea.

IG: Jiejian Luo, Lixin Wang, Jin Qin, Mingkun Yang from Sinovation Ventures

Segreg:  Panlong Xu, SJTU(Shanghai Jiao Tong University), China.