Datasets

 

Rat mesenchymal stem cells on a flat polyacrylamide substrate (2D)

Dr. F. Prósper. Cell Therapy laboratory.

Center for Applied Medical Research (CIMA) Pamplona. Spain


Microscope: PerkinElmer UltraVIEW ERS

Objective lens: Plan-Neofluar 10x/0.3 (Plan-Apo 20x/0.75)

Pixel size (microns): 0.3 x 0.3 (0.3977 x 0.3977)

Time step (min): 20 (30)


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-C2DL-MSC.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-C2DL-MSC.zip

--------------------

Chinese Hamster Ovarian (CHO) nuclei overexpressing GFP-PCNA (3D)

Dr. J. Essers. Dept. of Cell Biology

Erasmus Medical Center. Rotterdam. The Netherlands


Microscope: Zeiss LSM 510

Objective lens: Plan-Apochromat 63x/1.4 Oil

Voxel size (microns): 0.202 x 0.202 x 1

Time step (min): 9.5


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N3DH-CHO.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N3DH-CHO.zip

--------------------

GFP-GOWT1 mouse stem cells (2D)

Dr. E. Bártová. Institute of Biophysics

Academy of Sciences of the Czech Republic. Brno. Czech Republic


Microscope: Leica TCS SP5

Objective lens: Plan-Apochromat 63x/1.4 Oil

Pixel size (microns): 0.240 x 0.240

Time step (min): 5


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N2DH-GOWT1.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N2DH-GOWT1.zip

--------------------

GFP-transfected H157 Lung Cancer cells embedded in a matrigel matrix (3D)

Dr. A. Rouzaut. Cell Adhesion and Metastasis Laboratory

Center for Applied Medical Research (CIMA). Pamplona. Spain


Microscope: PerkinElmer UltraVIEW ERS

Objective lens: Plan-Apochromat 63x/1.2 Water

Voxel size (microns): 0.126 x 0.126 x 0.5

Time step (min): 2 (1)


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-C3DH-H157.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-C3DH-H157.zip

--------------------

MDA231 human breast carcinoma cells infected with a pMSCV vector including the GFP sequence, embedded in a collagen matrix (3D)

Dr. Roger Kamm. Dept. of Biological Engineering

Massachusetts Institute of Technology. Cambridge MA (USA)


Microscope: Olympus FluoView F1000

Objective lens: Plan 20x/0.7

Voxel size (microns): 1.242 x 1.242 x 6

Time step (min): 80


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-C3DL-MDA231.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-C3DL-MDA231.zip

--------------------

HeLa cells stably expressing H2b-GFP (2D)

Mitocheck Consortium


Microscope: Olympus IX81

Objective lens: Plan 10x/0.4

Pixel size (microns): 0.645 x 0.645

Time step (min): 30


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N2DL-HeLa.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N2DL-HeLa.zip

--------------------

Conditions of use of the images:


  1. 1)Please include a reference to this Bioinformatics paper in any publication resulting from the use of any of these datasets.


  1. 2)The fact that you have registered for the challenge does not oblige you in any way to submit results. Your registration is considered as an expression of interest to participate and allows you to download the datasets and submit results.


  1. 3)Ideally, we would like to encourage all participants to submit results for all datasets to get a complete picture of the strengths and weaknesses of all algorithms under different scenarios. However, given the varying nature of the datasets (nuclei or cells, different cell types, 2D or 3D, noise level and general image quality) and microscopy modalities (fluorescence, phase contrast, DIC) you can also submit results for only certain datasets, or submit more than one algorithm, each one targeting one or several specific datasets.


  1. 4)All participating teams wishing to be included in the challenge report and in any future publication, will be required to provide a working version of the algorithm used to produce the submitted results, either in the form of an executable or compilable source code. The challenge committee reserves the right to proceed to random tests to verify submitted results by rerunning the algorithms on the challenge datasets. The provided software will not be released publicly if participants do not agree with that. It will be used only for verification purposes.


  1. 5)To encourage the participation of groups that may be discouraged by the public display of potentially poor results, the rankings will display only the names of the top-three ranked participants for each dataset. The other lower ranked algorithms will not be listed, but the participants will be informed about the absolute performance of their algorithms.

C.elegans developing embryo (3D)

Waterston Lab

The George Washington University. Washington DC (USA)


Microscope: Zeiss LSM 510 Meta

Objective lens: Plan-Apochromat 63X/1.4 (oil)

Pixel size (microns): 0.09 x 0.09 x 1.0

Time step (min): 1 or 1.5


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N3DH-CE.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N3DH-CE.zip

--------------------

Glioblastoma-astrocytoma U373 cells on a polyacrylimide substrate  (2D)

Dr. Sanjay Kumar. Department of Bioengineering

University of California at Berkeley. Berkeley CA (USA)


Microscope: Nikon

Objective lens: Plan Fluor DLL 20X/0.5

Pixel size (microns): 0.65 x 0.65

Time step (min): 15


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/PhC-C2DH-U373.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/PhC-C2DH-U373.zip

--------------------

HeLa cells on a flat glass  (2D)

Dr. Gert van Cappellen

Erasmus Medical Center. Rotterdam. The Netherlands


Microscope: Zeiss LSM 510 Meta

Objective lens: Plan-Apochromat 63X/1.4 (oil)

Pixel size (microns): 0.19 x 0.19

Time step (min): 10


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/DIC-C2DH-HeLa.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/DIC-C2DH-HeLa.zip

--------------------

Pancreatic Stem Cells on a Polystyrene substrate  (2D)

Dr. Tim Becker

Fraunhofer Institution for Marine Biotechnology. Lübeck. Germany


Microscope: Olympus ix-81

Objective lens: UPLFLN 4XPH

Pixel size (microns): 1.6 x 1.6

Time step (min): 10


Download the training dataset at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/PhC-C2DL-PSC.zip

(Please note that only frames 150-250 have been used to generate the ground truth, although the evaluation of the challenge data will be based on the entire length -300 frames- of the videos)


Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/PhC-C2DL-PSC.zip

--------------------

Simulated nuclei of HL60 cells stained with Hoescht (2D & 3D)

Dr. V.Ulman & Dr. D. Svoboda. Centre for Biomedical Image Analysis (CBIA).

Masaryk University. Brno. Czech Republic

(Created using MitoGen, part of Cytopacq)


Microscope: Zeiss Axiovert 100S with a Micromax 1300-YHS camera

Objective lens: Plan-Apochromat 40X/1.3 (oil)

Pixel size (microns): 0.125 x 0.125 (x 0.200)

Time step (min): 29




Download the training datasets at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N2DH-SIM+.zip

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N3DH-SIM+.zip


Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N2DH-SIM+.zip

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N3DH-SIM+.zip


--------------------

The datasets consist of 2D and 3D time-lapse video sequences of fluorescent counterstained nuclei or cells moving on top or immersed in a substrate, along with 2D Phase Contrast and Differential Interference Contrast (DIC) microscopy videos of cells moving on a flat substrate. The videos cover a wide range of cell types and quality (spatial and temporal resolution, noise levels etc.) In addition, we provide 2D and 3D videos of synthetic fluorescent stained nuclei moving in a realistic way, displaying increasing cell density and noise levels.


All datasets are available for download to registered participants following the links bellow the sample videos. For download information or support, please contact Martin Maška (xmaska@fi.muni.cz).


The ground truth, consisting of manually annotated videos (segmentation) and acyclic graphs (tracking), was generated following the annotation guidelines described in the following document:


Annotation procedure.pdf


and both the original and ground truth files were named and created following the conventions described in:


Naming and file content conventions.pdf



The following video sequences contain sample renderings of examples of the type of data that was used in the challenge, along with a short description and links to the raw datasets (Please check the “Conditions of use of the images” at the end of this page before downloading these datasets).

Developing Drosophila Melanogaster embryo (3D)

Dr. Philipp Keller.

Howard Hughes Medical Institute

Janelia Farms Research Campus, Ashburn VA (USA)


Microscope: SIMView light-sheet microscope

Objective lens: 16X/0.8 (water)

Pixel size (microns): 0.406 x 0.406 (x 2.03)

Time step (sec): 30




Download the training datasets at:

http://ctc2015.gryf.fi.muni.cz/TrainingDatasets/Fluo-N3DL-DRO.zip

Download the challenge dataset at:

http://ctc2015.gryf.fi.muni.cz/ChallengeDatasets/Fluo-N3DL-DRO.zip


Important note: Only the cells that form the developing nervous system will be used for the evaluation of the segmentation and tracking accuracy. Those cells can be identified in the first frame of the provided tracking ground truth (TRA GT). Be aware that any other cells segmented and tracked will be considered as errors by the evaluation software.


--------------------