Skip to main content

Training Dataset

One zip file with training images and manual labels is available for downloading. They were randomly chosen from Multi-visit Advanced Pediatric (MAP) Brain Imaging Study, which is the pilot study of Baby Connectome Project (BCP), with the following imaging parameters:

  • T1-weighted MR images were acquired with 144 sagittal slices: TR/TE = 1900/4.38 ms, flip angle = 7º, resolution = 1×1×1 mm3;
  • T2-weighted MR images were obtained with 64 axial slices: TR/TE = 7380/119 ms, flip angle = 150º, resolution = 1.25×1.25×1.95 mm3.

The zip file contains T1- and T2-weighted MR images of 10 infant subjects (named as subject-1 to subject-10):

  • subject-?-T1: T1-weighted MR image
  • subject-?-T2: T2-weighted MR image
  • subject-?-label: manual segmentation

Notes on the manual segmentation

  • 0: Background (everything outside the brain)
  • 1: Cerebrospinal fluid (CSF)
  • 2: Gray matter (GM)
  • 3: White matter (WM)

Validation Dataset

One zip file with testing images is available for downloading. The zip file contains T1- and T2-weighted MR images from MAP:

1. MAP, 13 subjects (named as subject-11 to subject-23), with the same imaging parameters as the training images.


Testing Datasets

One zip file with testing images is available for downloading. The zip file contains T1- and T2-weighted MR images from 3 sites:

1. BCP, 6 subjects (named as subject-24 to subject-29), with the following imaging parameters:

  • T1-weighted images: TR/TE = 2400/2.24 ms, flip angle = 8º, resolution = 0.8×0.8×0.8 mm3;
  • T2-weighted images: TR/TE = 3200/564 ms, flip angle = VAR, resolution = 0.8×0.8×0.8 mm3.

2. Stanford University*, 5 subjects (named as subject-30 to subject-34), with the following imaging parameters:

  • T1-weighted images: TR/TE = 7.6/2.9 ms, flip angle = 11º, resolution = 0.94×0.94×0.80 mm3;
  • T2-weighted images: TR/TE = 2502/91.4 ms, flip angle = 90º, resolution = 1.00×1.00×0.80 mm3.

3. Emory University**, 5 subjects (named as subject-35 to subject-39), with the following imaging parameters:

  • T1-weighted images: TR/TE = 2400/2.19 ms, flip angle = 8º, resolution = 1×1×1 mm3;
  • T2-weighted images: TR/TE = 3200/561 ms, flip angle = 120º, resolution = 1×1×1 mm3.

For preprocessing, we have resampled all images into 1×1×1 mm3 to eliminate the effect of resolutions, and employed the same tools for skull stripping and intensity inhomogeneity correction.

Testing datasets are made available to each participating team, for a limited controlled time-window (12 days). When you are ready, please notify us of an email (li_wang@med.unc.edu) and we will send the testing datasets. The participants will analyze the images using their local computing infrastructure and will have to submit their segmentation results within 12 days.


Registration

Before registering a team, please read the Terms of Participation below:

  • By registering a team, you agree to respect the rules described on those pages and sign the Agreement-iSeg2019 (download). Once you have successfully registered and uploaded the signed agreement, you will be able to download the data.
  • We will not respond if the agreement is not signed.
  • Please use the institutional email corresponding to your affiliation. We will not respond if not.
  • We would greatly appreciate the submission of your results on our testing data, so we can include them into the iSeg-2019 webpage.
  • Please contact li_wang@med.unc.edu if you would like to submit your results.
  • Please inform the organizers if you would like to include the results in a planned publication.

Register a team of iSeg-2019


*We would like to express our special thanks and appreciation to Prof. Ian H. Gotlib and his lab members for providing these testing subjects.

**We would like to express our special thanks and appreciation to Prof. Sarah Shultz & Prof. Longchuan Li for providing these testing subjects.