Data description


For each clinical case, the provided data are:

  • Pre-operative 3T MRI images, including Gadolinium-enhanced T1w and T2 FLAIR scans.
  • Intra-operative Ultrasound (iUS) images, as a 3D volume covering the entire tumor region after craniotomy. Both pre-resection and post-resection iUS volumes will be provided.
  • Expert-labeled homologous anatomical landmarks, defined on all image modalities. These landmarks will be used to evaluate registration algorithms and rank the challenge participants.

All medical images used for the challenge were acquired for routine clinical care at St Olavs University Hospital (Trondheim, Norway), after patients gave their informed consent. The imaging data are available in both MINC-2 and NIFTI-1 formats. All images, MRI and iUS, are in the same referential.


Training dataset (23 cases)

Training data have been released to the public previously as a dataset article in Medical Physics in 2017, and the 23 patients collection is named REtroSpective Evaluation of Cerebral Tumors (RESECT). Details can be found in the related publication:

The RESECT database contains iUS volumes obtained at different surgical stages: before, during and after tumor resection.

More specifically, for the MRI-iUS registration task, 22 cases are available. For the iUS-iUS task, 17 cases are available. 


For each clinical cases, images to register are named:

  • Pre-operative MRI: CaseXX-FLAIR.nii.gz and CaseXX-T1.nii.gz

  • Intra-operative US, before resection: CaseXX-US-before.nii.gz

  • Intra-operative US, after resection: CaseXX-US-after.nii.gz


  • The landmarks of the data are in MINC tag file format with the extension .tag.

  • An easy way to visualize the MINC image pair with the homologous landmarks is to use the software 'register' that comes with MINC Toolkit ( To view the images, please use the following command in your terminal:
              register image1.mnc image2.mnc landmarks.tag

  • Each row of six entries, in world coordinates (unit = mm), represent a landmark pair. The first 3 columns are the x-, y-, and z-coordinate of landmarks belonging to image1 , and the latter 3 columns are the x-, y-, and z-coordinate of landmarks belonging to image2.

  • The reference image is always put as image1. In the RESECT database, this is the MRI or ultrasound before resection.
  • The world coordinates of the corresponding MINC and NIFTI files are the same.

Testing dataset (10 cases)

10 additional cases of tumour resection will be distributed only to the participating teams who have submitted their methodology manuscripts before the deadline, upon assigning the agreements. The format of the new cases will be exactly the same as the training data.