Difference between revisions of "MSChallenge"

From IACL
Jump to navigation Jump to search
 
(60 intermediate revisions by 2 users not shown)
Line 1: Line 1:
−
<meta name="title" content="MS Challenge" />  
+
<!-- <meta name="title" content="The 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge" /> -->
−
{{h1|The 2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge}}
+
{{h2|The 2015 Longitudinal MS Lesion Segmentation Challenge}}
 +
{{MSChallengeNav}}
 +
__NOTOC__
 +
{{h3|I. Introduction}}
 +
[[Image:2015_lesions_orig.png|right|thumb|400px|2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge]]
 +
The Longitudinal MS Lesion Segmentation Challenge was conducted at the [http://biomedicalimaging.org/2015 2015 International Symposium on Biomedical Imaging] in New York, NY, April 16-19. Competing teams applied their automatic lesion segmentation algorithms to MR neuroimaging data acquired at multiple time points from MS patients. Algorithms were evaluated against manual segmentations from two raters in terms of their segmentation accuracy and ability to track lesion evolution.
  
−
{{TOCright}}
+
34 Teams initially registered for the Challenge coming from 15 different countries, representing 27 different institutions/universities. '''Congratulations to Team IIT Madras (First Prize), Team PVG_1 (Second Prize), and Team IMI (Third Prize and Efficiency Prize)'''!
  
−
{{h3|I. Introduction}}
+
Information about the data is available [[MSChallenge/data|here]], and the evaluation software from [[MSChallenge/evaluation|here]].
  
−
The Longitudinal MS Lesion Segmentation Challenge will be conducted at the [http://biomedicalimaging.org/2015 2015 International Symposium on Biomedical Imaging] in New York, NY, April 16-19. Competing teams will apply their automatic lesion segmentation algorithms to MR neuroimaging data acquired at multiple time points from MS patients. Algorithms will be evaluated against manual segmentations from multiple raters in terms of their segmentation accuracy and ability to track lesion evolution. This website is undergoing construction so please check back for new information.
 
  
−
{{h3| II. Data}}  
+
{{h3|Leaderboard & Paper}}
 +
'''A live leaderboard is maintained on the [https://smart-stats-tools.org/lesion-challenge Smart Stats Website].''' The main Challenge article has appeared in {{iacl-pub ni}}: {{iacl-pub|author=A. Carass, S. Roy, A. Jog, J.L. Cuzzocreo, E. Magrath, A. Gherman, J. Button, J. Nguyen, F. Prados, C.H. Sudre, M.J. Cardoso, N. Cawley, O. Ciccarelli, C.A.M. Wheeler-Kingshott, S. Ourselin, L. Catanese, H. Deshpande, P. Maurel, O. Commowick, C. Barillot, X. Tomas-Fernandez, S.K. Warfield, S. Vaidya, A. Chunduru, R. Muthuganapathy, G. Krishnamurthi, A. Jesson, T. Arbel, O. Maier, H. Handels, L.O. Iheme, D. Unay, S. Jain, D.M. Sima, D. Smeets, M. Ghafoorian, B. Platel, A. Birenbaum, H. Greenspan, P.-L. Bazin, P.A. Calabresi, C.M. Crainiceanu, L.M. Ellingsen, D.S. Reich, J.L. Prince, and D.L. Pham|title=Longitudinal Multiple Sclerosis Lesion Segmentation: Resource and Challenge|jrnl=ni|number=148(C):77-102|when=2017|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490}}<br />
 +
and a companion paper has appeared in ''Data in Brief'':
 +
{{iacl-pub|author=A. Carass, S. Roy, A. Jog, J.L. Cuzzocreo, E. Magrath, A. Gherman, J. Button, J. Nguyen, P.-L. Bazin, P.A. Calabresi, C.M. Crainiceanu, L.M. Ellingsen, D.S. Reich, J.L. Prince, and D.L. Pham|title=Longitudinal multiple sclerosis lesion segmentation data resource|journal=Data in Brief|number=12:346-350|when=2017|doi=10.1016/j.dib.2017.04.004|pubmed=28491937}}
  
−
The overall data will be composed of three parts: 1) Training data consisting of longitudinal images from 5 patients; 2) Test data 1 consisting of longitudinal images from 10 patients; and 3) Test data 2 consisting of longitudinal images from 5 patients. Only the training data will include manual delineations when it is released to teams. These delineations will be performed by at least 2 trained raters. Test data 1 will be released in advance of the challenge day and test data 2 will be released on or shortly before the challenge day to discourage patient-specific tuning of the algorithms and computationally inefficient approaches.
 
  
−
Each longitudinal dataset will include T1-weighted, T2-weighted, PD-weighted, and T2-weighted FLAIR MRI with 3-5 time points acquired on a 3T MR scanner. T1-weighted images will have approximately a 1mm cubic voxel resolution, while the other scans will be 1mm in plane with 3mm sections. Accounting for the multiple time points, this constitutes approximately 80 individual data sets. To minimize the dependency of the results on registration performance and brain extraction, all images will be provided already rigidly co-registered to the baseline T1-weighted image with automatically computed skull stripping masks that may optionally be used by the teams.  
+
<!--
−
 
+
{| align="center" style="width:80%; border:2px #87cefa solid; background:#f0ffff; text-align:left;"
−
The training and test data will continue to be made publicly available following the challenge, similar to the [http://www.ia.unc.edu/MSseg/ |MICCAI 2008 Lesion Challenge] data. Manual delineations on the test data will not be made available to the public but the organizers will provide evaluation results for any submitted segmentations.
+
|-
−
 
+
| colspan="4" style="border-top:1px solid #87cefa;"|
−
{{h3| III. Key dates}}
+
|-
−
| class="wikitable"
+
| colspan="4" align="center" style="background:#87cefa; text-align:center;" | '''''Leaderboard'''''
−
|+Key dates
+
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| '''Ranking'''&nbsp;&nbsp;
 +
| style="width:80%" | '''Method Name'''<br />'''Authors'''<br />'''Paper Title'''<br />'''Paper Link(s)'''
 +
|
 +
| '''Website'''<br />'''Score'''
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 1
 +
| ''MV-CNN''<br />A. Birenbaum & H. Greenspan<br />'''Multi-View Convolutional Neural Networks'''<br />
 +
|
 +
| 91.267
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 2
 +
| ''MIAC''<br />S. Andermatt, J. Würfel, & P.C. Cattin<br />''' '''<br />
 +
|
 +
| 91.011
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 3
 +
| ''Team PVG One''<br />A. Jesson & T. Arbel<br />'''Hierarchical MRF and Random Forest Segmentation of MS Lesions and Healthy Tissues in Brain MRI'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 90.698
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 4
 +
| ''Team IMI''<br />O. Maier & H. Handels<br />'''MS-Lesion Segmentation in MRI with Random Forests'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 90.283
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 5
 +
| ''ATMS''<br />O. Ghribi<br /><br />
 +
|
 +
| 90.170
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 6
 +
| ''MV-CNN''<br />A. Birenbaum & H. Greenspan<br />'''Multi-View Convolutional Neural Networks'''<br />{{pub|doi=10.1007/978-3-319-46976-8_7|period=}}
 +
|
 +
| 90.070
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 7
 +
| ''Team VISAGES GCEM''<br />L. Catanese, O. Commowick, & C. Barillot<br />'''Automatic Graph Cut Segmentation of Multiple Sclerosis Lesions'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 89.807
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 8
 +
| ''Team IIT Madras''<br />S. Vaidya, A. Chunduru, R. Muthuganapathy, & G. Krishnamurthi<br />'''Longitudinal Multiple Sclerosis Lesion Segmentation using 3D Convolutional Neural Networks'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 89.159
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 9
 +
| ''Team MS*metrix*''<br />S. Jain, D.M. Sima, & D. Smeets<br />'''Automatic Longitudinal Multiple Sclerosis Lesion Segmentation'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 88.744
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 10
 +
| ''Lesion-TOADS''<br />N. Shiee, P.-L. Bazin, A. Ozturk, D. S. Reich, P. A. Calabresi, & D. L. Pham<br />'''A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions'''<br />{{pub|doi=10.1016/j.neuroimage.2009.09.005|pubmed=19766196|pmcid=2806481|period=}}
 +
|
 +
| 88.465
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 11
 +
| ''Team CMIC''<br />F. Prados, M.J. Cardoso, N. Cawley, O. Ciccarelli, C.A.M. Wheeler-Kingshott, & S. Ourselin<br />'''Multi-Contrast PatchMatch Algorithm for Multiple Sclerosis Lesion Detection'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 88.009
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 12
 +
| ''MORF''<br />A. Jog, A. Carass, D.L. Pham, & J.L. Prince<br />'''Multi-Output Random Forests for Lesion Segmentation in Multiple Sclerosis'''<br />{{pub|doi=10.1117/12.2082157|pubmed=27695155|pmcid=5041594|period=}}
 +
|
 +
| 87.917
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 13
 +
| ''Team TIG-BF''<br />C.H. Sudre, M.J. Cardoso, & S. Ourselin<br />'''Model Selection Propagation for Application on Longitudinal MS Lesion Segmentation'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 87.376
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 14
 +
| ''Team CRL''<br />X. Tomas-Fernandez & S.K. Warfield<br />'''Model of Population and Subject (MOPS) Segmentation'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 87.017
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 15
 +
| ''Team DIAG''<br />M. Ghafoorian & B. Platel<br />'''Convolution Neural Networks for MS Lesion Segmentation'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 86.916
 +
|-
 +
| colspan="4" style="border-top:1px solid #87cefa;"|
 +
|-
 +
| 16
 +
| ''Team TIG''<br />C.H. Sudre, M.J. Cardoso, & S. Ourselin<br />'''Model Selection Propagation for Application on Longitudinal MS Lesion Segmentation'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 86.436
 
|-
 
|-
−
|Release of training data
+
| colspan="4" style="border-top:1px solid #87cefa;"|
−
|February 1, 2015
 
 
|-
 
|-
−
|Release of test data 1
+
| 17
−
|March 15, 2015
+
| ''Team VISAGES DL''<br />H. Deshpande, P. Maurel, & C. Barillot<br />'''Sparse Representations and Dictionary Learning Based Longitudinal Segmentation of Multiple Sclerosis Lesions'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 86.068
 
|-
 
|-
−
|Submisssion of manuscript
+
| colspan="4" style="border-top:1px solid #87cefa;"|
−
|April 1, 2015
 
 
|-
 
|-
−
|Submisssion of test data 1 results
+
| 18
−
|April 6, 2015
+
| ''Team BAUMIP''<br />L.O. Iheme & D. Unay<br />'''Automatic White Matter Hyperintensity Segmentation using FLAIR MRI'''<br />{{pub|doi=10.1016/j.neuroimage.2016.12.064|pubmed=28087490|period=}}
 +
|
 +
| 84.140
 
|-
 
|-
−
|Release and submission of test data 2
+
| colspan="4" style="border-top:1px solid #87cefa;"|
−
|April 16, 2015
 
 
|-
 
|-
−
|Challenge Day
 
−
|April 16, 2015
 
 
|}
 
|}
 +
-->
 +
 +
 +
{{h3|VII. Organizers}}
 +
'''Primary Organizer:'''  <br />
 +
[mailto:dzung.pham@nih.gov Dzung Pham], Center for Neuroscience and Regenerative Medicine, Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD
 +
 +
'''Organizing committee members:'''<br />
 +
[http://www.cbs.mpg.de/staff/bazin-11500 Pierre-Louis Bazin], Department of Neurophysics, Max Planck Institute, Leipzig, Germany<br>
 +
{{iacl|~aaron/|Aaron Carass}}, Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD<br>
 +
[http://www.hopkinsmedicine.org/profiles/results/directory/profile/0018579/peter-calabresi Peter Calabresi], Department of Neurology, Johns Hopkins University, Baltimore, MD<br>
 +
[http://www.biostat.jhsph.edu/~ccrainic/ Ciprian Crainiceanu], Department of Biostatistics, Johns Hopkins University, Baltimore, MD<br>
 +
{{iacl|~lotta/|Lotta Ellingsen}}, Department of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland<br>
 +
Qing He, Center for Neuroscience and Regenerative Medicine, Henry Jackson Foundation, Bethesda, MD<br>
 +
[[Prince|Jerry Prince]], Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD<br>
 +
[http://www.cc.nih.gov/drd/staff/daniel_reich.html Daniel Reich], Translational Neuroradiology Unit, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD<br>
 +
{{iacl|~roy/|Snehashis Roy}}, Center for Neuroscience and Regenerative Medicine, Henry Jackson Foundation, Bethesda, MD<br>
 +
 +
 +
{{h3|VIII. Funding support}}
 +
This challenge was supported in part by a grant from the [http://www.ninds.nih.gov/ National Institute of Neurological Disorders and Stroke] (NINDS R01 NS070906).  Funding for prizes was provided by the [http://www.nationalmssociety.org/ National Multiple Sclerosis Society].

Latest revision as of 00:59, 3 July 2022

The 2015 Longitudinal MS Lesion Segmentation Challenge

2015 Longitudinal MS Lesion Segmentation Challenge
MS Challenge Overview MS Challenge Data MS Challenge Evaluation

I. Introduction

2015 Longitudinal Multiple Sclerosis Lesion Segmentation Challenge

The Longitudinal MS Lesion Segmentation Challenge was conducted at the 2015 International Symposium on Biomedical Imaging in New York, NY, April 16-19. Competing teams applied their automatic lesion segmentation algorithms to MR neuroimaging data acquired at multiple time points from MS patients. Algorithms were evaluated against manual segmentations from two raters in terms of their segmentation accuracy and ability to track lesion evolution.

34 Teams initially registered for the Challenge coming from 15 different countries, representing 27 different institutions/universities. Congratulations to Team IIT Madras (First Prize), Team PVG_1 (Second Prize), and Team IMI (Third Prize and Efficiency Prize)!

Information about the data is available here, and the evaluation software from here.


Leaderboard & Paper

A live leaderboard is maintained on the Smart Stats Website. The main Challenge article has appeared in NeuroImage:

  • A. Carass, S. Roy, A. Jog, J.L. Cuzzocreo, E. Magrath, A. Gherman, J. Button, J. Nguyen, F. Prados, C.H. Sudre, M.J. Cardoso, N. Cawley, O. Ciccarelli, C.A.M. Wheeler-Kingshott, S. Ourselin, L. Catanese, H. Deshpande, P. Maurel, O. Commowick, C. Barillot, X. Tomas-Fernandez, S.K. Warfield, S. Vaidya, A. Chunduru, R. Muthuganapathy, G. Krishnamurthi, A. Jesson, T. Arbel, O. Maier, H. Handels, L.O. Iheme, D. Unay, S. Jain, D.M. Sima, D. Smeets, M. Ghafoorian, B. Platel, A. Birenbaum, H. Greenspan, P.-L. Bazin, P.A. Calabresi, C.M. Crainiceanu, L.M. Ellingsen, D.S. Reich, J.L. Prince, and D.L. Pham, "Longitudinal Multiple Sclerosis Lesion Segmentation: Resource and Challenge", NeuroImage, 148(C):77-102, 2017. (doi) (PubMed)

and a companion paper has appeared in Data in Brief:

  • A. Carass, S. Roy, A. Jog, J.L. Cuzzocreo, E. Magrath, A. Gherman, J. Button, J. Nguyen, P.-L. Bazin, P.A. Calabresi, C.M. Crainiceanu, L.M. Ellingsen, D.S. Reich, J.L. Prince, and D.L. Pham, "Longitudinal multiple sclerosis lesion segmentation data resource", Data in Brief, 12:346-350, 2017. (doi) (PubMed)



VII. Organizers

Primary Organizer:
Dzung Pham, Center for Neuroscience and Regenerative Medicine, Henry M. Jackson Foundation for the Advancement of Military Medicine, Bethesda, MD

Organizing committee members:
Pierre-Louis Bazin, Department of Neurophysics, Max Planck Institute, Leipzig, Germany
Aaron Carass, Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD
Peter Calabresi, Department of Neurology, Johns Hopkins University, Baltimore, MD
Ciprian Crainiceanu, Department of Biostatistics, Johns Hopkins University, Baltimore, MD
Lotta Ellingsen, Department of Electrical and Computer Engineering, University of Iceland, Reykjavik, Iceland
Qing He, Center for Neuroscience and Regenerative Medicine, Henry Jackson Foundation, Bethesda, MD
Jerry Prince, Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD
Daniel Reich, Translational Neuroradiology Unit, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD
Snehashis Roy, Center for Neuroscience and Regenerative Medicine, Henry Jackson Foundation, Bethesda, MD


VIII. Funding support

This challenge was supported in part by a grant from the National Institute of Neurological Disorders and Stroke (NINDS R01 NS070906). Funding for prizes was provided by the National Multiple Sclerosis Society.

Retrieved from "https://iacl.ece.jhu.edu/index.php?title=MSChallenge&oldid=17846"