Overview

We use seven public data sets and one private data set for evaluation. Below we outline how to obtain each of the public data sets and how our evaluation system expects the files to be laid out on the file system. We have taken great care into ensuring that we use the original file layout from extracted zip files. See the Rules for details on evaluations. See Getting Started for more information on how to run your own method locally on these data sets.

 

The POPI data set consists 4D CT series made up of ten 3D volumes representing ten different phases of one breathing cycle. Images were acquired on a 16 Slice Brilliance CT Big Bore Oncology™ configuration (Philips). Each slice has a resolution of 0.976562mm x 0.976562mm and a thickness of 2mm. The resulting volume size of one 3D volume is 512 x 512 x 141. For the challenge, we use the preprocessed meta images at extreme phases of the breathing cycle and the lung masks included in the data set.

The data set is presented in Vandemeulebroucke, J., Sarrut, D. and Clarysse, P. The POPI-model, a point-validated pixel-based breathing thorax model, XVth International Conference on the Use of Computers in Radiation Therapy (ICCR), Toronto, Canada. 2007 and can be downloaded from https://www.creatis.insa-lyon.fr/rio/dir_validation_data (quick method: run `$ wget --recursive --accept 00.mhd,00.raw,50.mhd,50.raw,*.pts --no-parent https://www.creatis.insa-lyon.fr/~srit/POPI/MedPhys11`).

The file layout expected by the Python scripts to run registration locally is:

 

POPI
|-- bh
|   |-- mhd
|   |   |-- 00.mhd
|   |   |-- 00.raw
|   |   |-- 50.mhd
|   |   |-- 50.raw
|   `-- pts
|       |-- 00.pts
|       |-- 00.vtk
|       `-- 50.pts
|-- bl
|   |-- mhd
|   |   |-- 00.mhd
|   |   |-- 00.raw
|   |   |-- 50.mhd
|   |   |-- 50.raw
|   `-- pts
|       |-- 00.pts
|       `-- 50.pts
|-- dx
|   |-- mhd
|   |   |-- 00.mhd
|   |   |-- 00.raw
|   |   |-- 50.mhd
|   |   `-- 50.raw
|   `-- pts
|       |-- 00.pts
|       |-- 50.pts
|-- gt
|   |-- mhd
|   |   |-- 00.mhd
|   |   |-- 00.raw
|   |   |-- 50.mhd
|   |   |-- 50.raw
|   `-- pts
|       |-- 00.pts
|       `-- 50.pts
|-- mm2
|   |-- mhd
|   |   |-- 00.mhd
|   |   |-- 00.raw
|   |   |-- 50.mhd
|   |   |-- 50.raw
|   `-- pts
|       |-- 00.pts
|       |-- 00.vtk
|       `-- 50.pts
`-- ng
    |-- mhd
    |   |-- 00.mhd
    |   |-- 00.raw
    |   |-- 50.mhd
    |   |-- 50.raw
    `-- pts
        |-- 00.pts
        `-- 50.pts
 

The data set consists of 10 thoracic 4DCT images acquired at The University of Texas M. D. Anderson Cancer Center in Houston, TX. For this challenge, we use images in the extreme phases have been annotated with 300 anatomical landmarks by an expert in thoracic imaging. 

Image details are given at https://www.dir-lab.com/ReferenceData.html. The data used for this challenge is presented in Castillo R, Castillo E, Guerra R, Johnson VE, McPhail T, Garg AK, Guerrero T. 2009. A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets. Phys Med Biol 54 1849-1870 and Castillo E, Castillo R, Martinez J, Shenoy M, Guerrero T. 2009. Four-dimensional deformable image registration using trajectory modeling. Phys Med Biol 55 305-327 and can be downloaded from https://www.dir-lab.com/. Masks used for this challenge can be downloaded here.

The file layout expected by the Python scripts to run registration locally is:

DIR-LAB
|-- Case10Pack
|   |-- ExtremePhases
|   |   |-- case10_dirLab300_T00_xyz.txt
|   |   `-- case10_dirLab300_T50_xyz.txt
|   `-- Images
|       |-- case10_T00.img
|       `-- case10_T50.img
|-- Case1Pack
|   |-- ExtremePhases
|   |   |-- Case1_300_T00_xyz.txt
|   |   `-- Case1_300_T50_xyz.txt
|   `-- Images
|       |-- case1_T00_s.img
|       `-- case1_T50_s.img
|-- Case2Pack
|   |-- ExtremePhases
|   |   |-- Case2_300_T00_xyz.txt
|   |   `-- Case2_300_T50_xyz.txt
|   `-- Images
|       |-- case2_T00-ssm.img
|       `-- case2_T50-ssm.img
|-- Case3Pack
|   |-- ExtremePhases
|   |   |-- Case3_300_T00_xyz.txt
|   |   `-- Case3_300_T50_xyz.txt
|   `-- Images
|       |-- case3_T00-ssm.img
|       `-- case3_T50-ssm.img
|-- Case4Pack
|   |-- ExtremePhases
|   |   |-- Case4_300_T00_xyz.txt
|   |   `-- Case4_300_T50_xyz.txt
|   `-- Images
|       |-- case4_T00-ssm.img
|       `-- case4_T50-ssm.img
|-- Case5Pack
|   |-- ExtremePhases
|   |   |-- Case5_300_T00_xyz.txt
|   |   `-- Case5_300_T50_xyz.txt
|   `-- Images
|       |-- case5_T00-ssm.img
|       `-- case5_T50-ssm.img
|-- Case6Pack
|   |-- ExtremePhases
|   |   |-- case6_dirLab300_T00_xyz.txt
|   |   `-- case6_dirLab300_T50_xyz.txt
|   `-- Images
|       |-- case6_T00.img
|       `-- case6_T50.img
|-- Case7Pack
|   |-- ExtremePhases
|   |   |-- case7_dirLab300_T00_xyz.txt
|   |   `-- case7_dirLab300_T50_xyz.txt
|   `-- Images
|       |-- case7_T00.img
|       `-- case7_T50.img
|-- Case8Deploy
|   |-- ExtremePhases
|   |   |-- case8_dirLab300_T00_xyz.txt
|   |   `-- case8_dirLab300_T50_xyz.txt
|   `-- Images
|       |-- case8_T00.img
|       `-- case8_T50.img
`-- Case9Pack
    |-- ExtremePhases
    |   |-- case9_dirLab300_T00_xyz.txt
    |   `-- case9_dirLab300_T50_xyz.txt
    `-- Images
        |-- case9_T00.img
        `-- case9_T50.img

40 directories, 200 files
 

The EMPIRE10 challenge was launched in early 2010 with an initial set of 20 scan pairs to be registered by participants in their own facility. This was followed in September by a workshop at the MICCAI 2010 conference where participants registered a further 10 scan pairs. We use the full data set for this challenge and automatically submit results from our cluster to the official EMPIRE evaluation scripts. The challenge and results  described in detail in Murphy et al., "Evaluation of registration methods on thoracic CT: the EMPIRE10 challenge.", IEEE Trans Med Imaging. 2011 Nov;30(11):1901-20. and the EMPIRE lung data set can be downloaded from http://empire10.isi.uu.nl/.

To run registration locally with these Python scripts, You have to manually merge the extracted zip files into one folder with a layout like this:

EMPIRE
`-- scans
    |-- 01_Fixed.mhd
    |-- 01_Fixed.raw
    |-- 01_Moving.mhd
    |-- 01_Moving.raw
    |-- 02_Fixed.mhd
    |-- 02_Fixed.raw
    |-- 02_Moving.mhd
    |-- 02_Moving.raw
    |-- 03_Fixed.mhd
    |-- 03_Fixed.raw
    |-- 03_Moving.mhd
    |-- 03_Moving.raw
    |-- 04_Fixed.mhd
    |-- 04_Fixed.raw
    |-- 04_Moving.mhd
    |-- 04_Moving.raw
    |-- 05_Fixed.mhd
    |-- 05_Fixed.raw
    |-- 05_Moving.mhd
    |-- 05_Moving.raw
    |-- 06_Fixed.mhd
    |-- 06_Fixed.raw
    |-- 06_Moving.mhd
    |-- 06_Moving.raw
    |-- 07_Fixed.mhd
    |-- 07_Fixed.raw
    |-- 07_Moving.mhd
    |-- 07_Moving.raw
    |-- 08_Fixed.mhd
    |-- 08_Fixed.raw
    |-- 08_Moving.mhd
    |-- 08_Moving.raw
    |-- 09_Fixed.mhd
    |-- 09_Fixed.raw
    |-- 09_Moving.mhd
    |-- 09_Moving.raw
    |-- 10_Fixed.mhd
    |-- 10_Fixed.raw
    |-- 10_Moving.mhd
    |-- 10_Moving.raw
    |-- 11_Fixed.mhd
    |-- 11_Fixed.raw
    |-- 11_Moving.mhd
    |-- 11_Moving.raw
    |-- 12_Fixed.mhd
    |-- 12_Fixed.raw
    |-- 12_Moving.mhd
    |-- 12_Moving.raw
    |-- 13_Fixed.mhd
    |-- 13_Fixed.raw
    |-- 13_Moving.mhd
    |-- 13_Moving.raw
    |-- 14_Fixed.mhd
    |-- 14_Fixed.raw
    |-- 14_Moving.mhd
    |-- 14_Moving.raw
    |-- 15_Fixed.mhd
    |-- 15_Fixed.raw
    |-- 15_Moving.mhd
    |-- 15_Moving.raw
    |-- 16_Fixed.mhd
    |-- 16_Fixed.raw
    |-- 16_Moving.mhd
    |-- 16_Moving.raw
    |-- 17_Fixed.mhd
    |-- 17_Fixed.raw
    |-- 17_Moving.mhd
    |-- 17_Moving.raw
    |-- 18_Fixed.mhd
    |-- 18_Fixed.raw
    |-- 18_Moving.mhd
    |-- 18_Moving.raw
    |-- 19_Fixed.mhd
    |-- 19_Fixed.raw
    |-- 19_Moving.mhd
    |-- 19_Moving.raw
    |-- 20_Fixed.mhd
    |-- 20_Fixed.raw
    |-- 20_Moving.mhd
    |-- 20_Moving.raw
    |-- 21_Fixed.mhd
    |-- 21_Fixed.raw
    |-- 21_Moving.mhd
    |-- 21_Moving.raw
    |-- 22_Fixed.mhd
    |-- 22_Fixed.raw
    |-- 22_Moving.mhd
    |-- 22_Moving.raw
    |-- 23_Fixed.mhd
    |-- 23_Fixed.raw
    |-- 23_Moving.mhd
    |-- 23_Moving.raw
    |-- 24_Fixed.mhd
    |-- 24_Fixed.raw
    |-- 24_Moving.mhd
    |-- 24_Moving.raw
    |-- 25_Fixed.mhd
    |-- 25_Fixed.raw
    |-- 25_Moving.mhd
    |-- 25_Moving.raw
    |-- 26_Fixed.mhd
    |-- 26_Fixed.raw
    |-- 26_Moving.mhd
    |-- 26_Moving.raw
    |-- 27_Fixed.mhd
    |-- 27_Fixed.raw
    |-- 27_Moving.mhd
    |-- 27_Moving.raw
    |-- 28_Fixed.mhd
    |-- 28_Fixed.raw
    |-- 28_Moving.mhd
    |-- 28_Moving.raw
    |-- 29_Fixed.mhd
    |-- 29_Fixed.raw
    |-- 29_Moving.mhd
    |-- 29_Moving.raw
    |-- 30_Fixed.mhd
    |-- 30_Fixed.raw
    |-- 30_Moving.mhd
    `-- 30_Moving.raw

1 directory, 120 files
 

The LONI Probabilistic Brain Atlas (LPBA40) consists of whole-head MRI of 40 human volunteers and manually delineations of 56 structures in the brain, most of which are within the cortex. The data is presented in Shattuck DW, Mirza M, Adisetiyo V, Hojatkashani C, Salamon G, Narr KL, Poldrack RA, Bilder RM, Toga AW, Construction of a 3D Probabilistic Atlas of Human Cortical Structures, NeuroImage (2007), doi: 10.1016/j.neuroimage.2007.09.031 and can be downloaded from http://www.loni.usc.edu/atlases/Atlas_Detail.php?atlas_id=12.

 

The file layout expected by the Python scripts to run registration locally is:

LPBA40
|-- Atlas_Distribution_Agreement_v2.pdf
|-- LPBA40_subject_data.pdf
|-- delineation_space
|   |-- S01
|   |   |-- S01.delineation.skullstripped.hdr
|   |   |-- S01.delineation.skullstripped.img.gz
|   |   |-- S01.delineation.structure.label.hdr
|   |   `-- S01.delineation.structure.label.img.gz
|   |-- S02
|   |   |-- S02.delineation.skullstripped.hdr
|   |   |-- S02.delineation.skullstripped.img.gz
|   |   |-- S02.delineation.structure.label.hdr
|   |   `-- S02.delineation.structure.label.img.gz
|   |-- S03
|   |   |-- S03.delineation.skullstripped.hdr
|   |   |-- S03.delineation.skullstripped.img.gz
|   |   |-- S03.delineation.structure.label.hdr
|   |   `-- S03.delineation.structure.label.img.gz
|   |-- S04
|   |   |-- S04.delineation.skullstripped.hdr
|   |   |-- S04.delineation.skullstripped.img.gz
|   |   |-- S04.delineation.structure.label.hdr
|   |   `-- S04.delineation.structure.label.img.gz
|   |-- S05
|   |   |-- S05.delineation.skullstripped.hdr
|   |   |-- S05.delineation.skullstripped.img.gz
|   |   |-- S05.delineation.structure.label.hdr
|   |   `-- S05.delineation.structure.label.img.gz
|   |-- S06
|   |   |-- S06.delineation.skullstripped.hdr
|   |   |-- S06.delineation.skullstripped.img.gz
|   |   |-- S06.delineation.structure.label.hdr
|   |   `-- S06.delineation.structure.label.img.gz
|   |-- S07
|   |   |-- S07.delineation.skullstripped.hdr
|   |   |-- S07.delineation.skullstripped.img.gz
|   |   |-- S07.delineation.structure.label.hdr
|   |   `-- S07.delineation.structure.label.img.gz
|   |-- S08
|   |   |-- S08.delineation.skullstripped.hdr
|   |   |-- S08.delineation.skullstripped.img.gz
|   |   |-- S08.delineation.structure.label.hdr
|   |   `-- S08.delineation.structure.label.img.gz
|   |-- S09
|   |   |-- S09.delineation.skullstripped.hdr
|   |   |-- S09.delineation.skullstripped.img.gz
|   |   |-- S09.delineation.structure.label.hdr
|   |   `-- S09.delineation.structure.label.img.gz
|   |-- S10
|   |   |-- S10.delineation.skullstripped.hdr
|   |   |-- S10.delineation.skullstripped.img.gz
|   |   |-- S10.delineation.structure.label.hdr
|   |   `-- S10.delineation.structure.label.img.gz
|   |-- S11
|   |   |-- S11.delineation.skullstripped.hdr
|   |   |-- S11.delineation.skullstripped.img.gz
|   |   |-- S11.delineation.structure.label.hdr
|   |   `-- S11.delineation.structure.label.img.gz
|   |-- S12
|   |   |-- S12.delineation.skullstripped.hdr
|   |   |-- S12.delineation.skullstripped.img.gz
|   |   |-- S12.delineation.structure.label.hdr
|   |   `-- S12.delineation.structure.label.img.gz
|   |-- S13
|   |   |-- S13.delineation.skullstripped.hdr
|   |   |-- S13.delineation.skullstripped.img.gz
|   |   |-- S13.delineation.structure.label.hdr
|   |   `-- S13.delineation.structure.label.img.gz
|   |-- S14
|   |   |-- S14.delineation.skullstripped.hdr
|   |   |-- S14.delineation.skullstripped.img.gz
|   |   |-- S14.delineation.structure.label.hdr
|   |   `-- S14.delineation.structure.label.img.gz
|   |-- S15
|   |   |-- S15.delineation.skullstripped.hdr
|   |   |-- S15.delineation.skullstripped.img.gz
|   |   |-- S15.delineation.structure.label.hdr
|   |   `-- S15.delineation.structure.label.img.gz
|   |-- S16
|   |   |-- S16.delineation.skullstripped.hdr
|   |   |-- S16.delineation.skullstripped.img.gz
|   |   |-- S16.delineation.structure.label.hdr
|   |   `-- S16.delineation.structure.label.img.gz
|   |-- S17
|   |   |-- S17.delineation.skullstripped.hdr
|   |   |-- S17.delineation.skullstripped.img.gz
|   |   |-- S17.delineation.structure.label.hdr
|   |   `-- S17.delineation.structure.label.img.gz
|   |-- S18
|   |   |-- S18.delineation.skullstripped.hdr
|   |   |-- S18.delineation.skullstripped.img.gz
|   |   |-- S18.delineation.structure.label.hdr
|   |   `-- S18.delineation.structure.label.img.gz
|   |-- S19
|   |   |-- S19.delineation.skullstripped.hdr
|   |   |-- S19.delineation.skullstripped.img.gz
|   |   |-- S19.delineation.structure.label.hdr
|   |   `-- S19.delineation.structure.label.img.gz
|   |-- S20
|   |   |-- S20.delineation.skullstripped.hdr
|   |   |-- S20.delineation.skullstripped.img.gz
|   |   |-- S20.delineation.structure.label.hdr
|   |   `-- S20.delineation.structure.label.img.gz
|   |-- S21
|   |   |-- S21.delineation.skullstripped.hdr
|   |   |-- S21.delineation.skullstripped.img.gz
|   |   |-- S21.delineation.structure.label.hdr
|   |   `-- S21.delineation.structure.label.img.gz
|   |-- S22
|   |   |-- S22.delineation.skullstripped.hdr
|   |   |-- S22.delineation.skullstripped.img.gz
|   |   |-- S22.delineation.structure.label.hdr
|   |   `-- S22.delineation.structure.label.img.gz
|   |-- S23
|   |   |-- S23.delineation.skullstripped.hdr
|   |   |-- S23.delineation.skullstripped.img.gz
|   |   |-- S23.delineation.structure.label.hdr
|   |   `-- S23.delineation.structure.label.img.gz
|   |-- S24
|   |   |-- S24.delineation.skullstripped.hdr
|   |   |-- S24.delineation.skullstripped.img.gz
|   |   |-- S24.delineation.structure.label.hdr
|   |   `-- S24.delineation.structure.label.img.gz
|   |-- S25
|   |   |-- S25.delineation.skullstripped.hdr
|   |   |-- S25.delineation.skullstripped.img.gz
|   |   |-- S25.delineation.structure.label.hdr
|   |   `-- S25.delineation.structure.label.img.gz
|   |-- S26
|   |   |-- S26.delineation.skullstripped.hdr
|   |   |-- S26.delineation.skullstripped.img.gz
|   |   |-- S26.delineation.structure.label.hdr
|   |   `-- S26.delineation.structure.label.img.gz
|   |-- S27
|   |   |-- S27.delineation.skullstripped.hdr
|   |   |-- S27.delineation.skullstripped.img.gz
|   |   |-- S27.delineation.structure.label.hdr
|   |   `-- S27.delineation.structure.label.img.gz
|   |-- S28
|   |   |-- S28.delineation.skullstripped.hdr
|   |   |-- S28.delineation.skullstripped.img.gz
|   |   |-- S28.delineation.structure.label.hdr
|   |   `-- S28.delineation.structure.label.img.gz
|   |-- S29
|   |   |-- S29.delineation.skullstripped.hdr
|   |   |-- S29.delineation.skullstripped.img.gz
|   |   |-- S29.delineation.structure.label.hdr
|   |   `-- S29.delineation.structure.label.img.gz
|   |-- S30
|   |   |-- S30.delineation.skullstripped.hdr
|   |   |-- S30.delineation.skullstripped.img.gz
|   |   |-- S30.delineation.structure.label.hdr
|   |   `-- S30.delineation.structure.label.img.gz
|   |-- S31
|   |   |-- S31.delineation.skullstripped.hdr
|   |   |-- S31.delineation.skullstripped.img.gz
|   |   |-- S31.delineation.structure.label.hdr
|   |   `-- S31.delineation.structure.label.img.gz
|   |-- S32
|   |   |-- S32.delineation.skullstripped.hdr
|   |   |-- S32.delineation.skullstripped.img.gz
|   |   |-- S32.delineation.structure.label.hdr
|   |   `-- S32.delineation.structure.label.img.gz
|   |-- S33
|   |   |-- S33.delineation.skullstripped.hdr
|   |   |-- S33.delineation.skullstripped.img.gz
|   |   |-- S33.delineation.structure.label.hdr
|   |   `-- S33.delineation.structure.label.img.gz
|   |-- S34
|   |   |-- S34.delineation.skullstripped.hdr
|   |   |-- S34.delineation.skullstripped.img.gz
|   |   |-- S34.delineation.structure.label.hdr
|   |   `-- S34.delineation.structure.label.img.gz
|   |-- S35
|   |   |-- S35.delineation.skullstripped.hdr
|   |   |-- S35.delineation.skullstripped.img.gz
|   |   |-- S35.delineation.structure.label.hdr
|   |   `-- S35.delineation.structure.label.img.gz
|   |-- S36
|   |   |-- S36.delineation.skullstripped.hdr
|   |   |-- S36.delineation.skullstripped.img.gz
|   |   |-- S36.delineation.structure.label.hdr
|   |   `-- S36.delineation.structure.label.img.gz
|   |-- S37
|   |   |-- S37.delineation.skullstripped.hdr
|   |   |-- S37.delineation.skullstripped.img.gz
|   |   |-- S37.delineation.structure.label.hdr
|   |   `-- S37.delineation.structure.label.img.gz
|   |-- S38
|   |   |-- S38.delineation.skullstripped.hdr
|   |   |-- S38.delineation.skullstripped.img.gz
|   |   |-- S38.delineation.structure.label.hdr
|   |   `-- S38.delineation.structure.label.img.gz
|   |-- S39
|   |   |-- S39.delineation.skullstripped.hdr
|   |   |-- S39.delineation.skullstripped.img.gz
|   |   |-- S39.delineation.structure.label.hdr
|   |   `-- S39.delineation.structure.label.img.gz
|   |-- S40
|   |   |-- S40.delineation.skullstripped.hdr
|   |   |-- S40.delineation.skullstripped.img.gz
|   |   |-- S40.delineation.structure.label.hdr
|   |   `-- S40.delineation.structure.label.img.gz
|   `-- lpba40.label.xml
`-- lpba40.txt

41 directories, 164 files
		
 

The ISBR18 data set consists of T1-weighted MR Image data with expert segmentations of 84 individual structures. The 18 brain images were acquired at different laboratories. The T1-weighted images have been rotated to Talairach alignment (Talairach and Tournoux, 1988) and have have undergone ‘autoseg’ bias field correctio by the CMA (Center for Morphometric Analysis, Massachusetts General Hospital (MGH) in Boston). The ISBR18 brain data set can be downloaded from https://www.nitrc.org/projects/ibsr/.

ISBR18
|-- Atlases
|   |-- c1.hdr
|   |-- c1.img
|   |-- c10.hdr
|   |-- c10.img
|   |-- c11.hdr
|   |-- c11.img
|   |-- c12.hdr
|   |-- c12.img
|   |-- c13.hdr
|   |-- c13.img
|   |-- c14.hdr
|   |-- c14.img
|   |-- c15.hdr
|   |-- c15.img
|   |-- c16.hdr
|   |-- c16.img
|   |-- c17.hdr
|   |-- c17.img
|   |-- c18.hdr
|   |-- c18.img
|   |-- c2.hdr
|   |-- c2.img
|   |-- c3.hdr
|   |-- c3.img
|   |-- c4.hdr
|   |-- c4.img
|   |-- c5.hdr
|   |-- c5.img
|   |-- c6.hdr
|   |-- c6.img
|   |-- c7.hdr
|   |-- c7.img
|   |-- c8.hdr
|   |-- c8.img
|   |-- c9.hdr
|   `-- c9.img
|-- Heads
|   |-- c1.hdr
|   |-- c1.img
|   |-- c10.hdr
|   |-- c10.img
|   |-- c11.hdr
|   |-- c11.img
|   |-- c12.hdr
|   |-- c12.img
|   |-- c13.hdr
|   |-- c13.img
|   |-- c14.hdr
|   |-- c14.img
|   |-- c15.hdr
|   |-- c15.img
|   |-- c16.hdr
|   |-- c16.img
|   |-- c17.hdr
|   |-- c17.img
|   |-- c18.hdr
|   |-- c18.img
|   |-- c2.hdr
|   |-- c2.img
|   |-- c3.hdr
|   |-- c3.img
|   |-- c4.hdr
|   |-- c4.img
|   |-- c5.hdr
|   |-- c5.img
|   |-- c6.hdr
|   |-- c6.img
|   |-- c7.hdr
|   |-- c7.img
|   |-- c8.hdr
|   |-- c8.img
|   |-- c9.hdr
|   `-- c9.img
`-- Labels
    `-- IBSR_labels.m

10 directories, 73 files
 

CUMC12 consists of 18 images acquired at the Columbia University Medical Center on a 1.5 T GE scanner. Images were resliced coronally to a slice thickness of 3 mm, rotated into cardinal orientation, then segmented and manually labeled by one technician trained according to the Cardviews labeling scheme (Caviness et al., 1996) created at the CMA. The images have 128 labeled regions and can be downloaded from https://www.synapse.org/#!Synapse:syn3207203.

The file layout expected by the Python scripts used to run registration locally is:

CUMC12
|-- Atlases
|   |-- m1.hdr
|   |-- m1.img
|   |-- m10.hdr
|   |-- m10.img
|   |-- m11.hdr
|   |-- m11.img
|   |-- m12.hdr
|   |-- m12.img
|   |-- m2.hdr
|   |-- m2.img
|   |-- m3.hdr
|   |-- m3.img
|   |-- m4.hdr
|   |-- m4.img
|   |-- m5.hdr
|   |-- m5.img
|   |-- m6.hdr
|   |-- m6.img
|   |-- m7.hdr
|   |-- m7.img
|   |-- m8.hdr
|   |-- m8.img
|   |-- m9.hdr
|   `-- m9.img
|-- Heads
|   |-- m1.hdr
|   |-- m1.img
|   |-- m10.hdr
|   |-- m10.img
|   |-- m11.hdr
|   |-- m11.img
|   |-- m12.hdr
|   |-- m12.img
|   |-- m2.hdr
|   |-- m2.img
|   |-- m3.hdr
|   |-- m3.img
|   |-- m4.hdr
|   |-- m4.img
|   |-- m5.hdr
|   |-- m5.img
|   |-- m6.hdr
|   |-- m6.img
|   |-- m7.hdr
|   |-- m7.img
|   |-- m8.hdr
|   |-- m8.img
|   |-- m9.hdr
|   `-- m9.img
`-- Labels
    `-- CUMC_labels.m

3 directories, 49 files
 

This data set consist of 10 subjects scanned at the MGH/MIT/HMS Athinoula A. Martinos Center for Biomedical Imaging using a 3 T Siemens scanner and standard head coil. The data is inhomogeneity-corrected, affine-registered to the MNI152 template (Evans et al., 1992), and segmented using SPM2 software (Friston et al., 1995) into 74 regions according to the labeling protocol by Tourville and Guenther, 2003. The MGH10 brain data set can be downloaded from https://www.synapse.org/#!Synapse:syn3207203.

The file layout expected by the Python scripts to run registration locally is:

MGH10
|-- Atlases
|   |-- g1.hdr
|   |-- g1.img
|   |-- g10.hdr
|   |-- g10.img
|   |-- g2.hdr
|   |-- g2.img
|   |-- g3.hdr
|   |-- g3.img
|   |-- g4.hdr
|   |-- g4.img
|   |-- g5.hdr
|   |-- g5.img
|   |-- g6.hdr
|   |-- g6.img
|   |-- g7.hdr
|   |-- g7.img
|   |-- g8.hdr
|   |-- g8.img
|   |-- g9.hdr
|   `-- g9.img
|-- Heads
|   |-- g1.hdr
|   |-- g1.img
|   |-- g10.hdr
|   |-- g10.img
|   |-- g2.hdr
|   |-- g2.img
|   |-- g3.hdr
|   |-- g3.img
|   |-- g4.hdr
|   |-- g4.img
|   |-- g5.hdr
|   |-- g5.img
|   |-- g6.hdr
|   |-- g6.img
|   |-- g7.hdr
|   |-- g7.img
|   |-- g8.hdr
|   |-- g8.img
|   |-- g9.hdr
|   `-- g9.img
`-- Labels
    |-- g_labels.m
    `-- g_labels.txt

3 directories, 42 files