Published May 29, 2024 | Version 2.1
Dataset Open

ReMIND2Reg dataset (2023)

  • 1. ROR icon Harvard Medical School
  • 2. ROR icon Brigham and Women's Hospital

Contributors

  • 1. ROR icon Brigham and Women's Hospital
  • 2. ROR icon Harvard Medical School

Description

Official training and validation sets of ReMIND2Reg 2024.

The goal of the ReMIND2Reg dataset is to address the registration problem of multi-parametric pre-operative MRI and intra-operative 3D ultrasound (iUS) images. Specifically, we focus on the challenging problem of pre-operative to post-resection registration, requiring the estimation of large deformations and tissue resections. Preoperative MRI comprises two structural MRI sequences: contrast-enhanced T1-weighted (ceT1) and native T2-weighted (T2). However, not all sequences are available for all cases. For this reason, developed methods must have the flexibility to leverage incomplete data sets at inference time. 

The released data corresponds to a modified (pre-processed) subset of the Brain Resection Multimodal Imaging Database (ReMIND) from The Cancer Imaging Archive, released with a CC BY 4.0 license, which contains pre- and intra-operative data collected on 114 consecutive patients who were surgically treated with image-guided tumor resection between 2018 and 2022: https://doi.org/10.7937/3rag-d070.

For each patient, 3D intraoperative ultrasound data reconstructed from tracked 2D sweep were acquired during brain surgery after substantial tumor resection was completed to the degree that either the surgeon was satisfied with the microscopically-visible extent of resection or to identify the remaining portion of the tumor (_0000.nii.gz). Before surgery, contrast-enhanced T1 (ceT1) MR scans (_0001.nii.gz) and/or T2-SPACE (_0002.nii.gz) were acquired to identify the surgical target. 

The task is to find one solution for the registration of two pairs of images per patient:
1. 3D post-resection iUS and ceT1
2. 3D post-resection iUS and T2

The two main challenges are the significant variations in intensity distribution and local information between two imaging modalities (iUS and MR) and the estimation of large deformations with topological changes due to tissue resections . 

The released dataset includes training images of 99 patients with 99 3D iUS, 93 ceT1, and 62 T2, and validation images of 5 patients with 5 3D US, 5 ceT1, and 5 T2. The images are paired as described above with two image pairs per patient, resulting in 1585image pairs for training and 10 image pairs for validation. 

For details on the image acquisition (scanner details, etc.), please see https://doi.org/10.1101/2023.09.14.23295596.

All images are converted to NIfTI. When more than one pre-operative MR sequence was available, ceT1 was affinely co-registered to the T2 using NiftyReg; Ultrasound images were resampled in the pre-operative MR space. Images were cropped in the field of view of the iUS in an image size of 256x256x256 with a spacing of 0.5x0.5x0.5mm.

 

Data citation:
Juvekar, P., Dorent, R., Kögl, F., Torio, E., Barr, C., Rigolo, L., Galvin, C., Jowkar, N., Kazi, A., Haouchine, N., Cheema, H., Navab, N., Pieper, S., Wells, W. M., Bi, W. L., Golby, A., Frisken, S., & Kapur, T. (2023). The Brain Resection Multimodal Imaging Database (ReMIND) (Version 1) [dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/3rag-d070.

Files

ReMIND2Reg_dataset.zip

Files (3.2 GB)

Name Size Download all
md5:050887d39a48fa07c60a71ddf9fb3bf7
3.2 GB Preview Download

Additional details

Related works

Is derived from
10.7937/3RAG-D070 (DOI)

Funding

Ultrasound based neurosurgical navigation with uncertainty visualization R01EB032387
National Institutes of Health
Training & Dissemination P41EB028741
National Institutes of Health

Dates

Available
2024-05-16

References

  • Juvekar, P., Dorent, R., Kögl, F., Torio, E., Barr, C., Rigolo, L., Galvin, C., Jowkar, N., Kazi, A., Haouchine, N., Cheema, H., Navab, N., Pieper, S., Wells, W. M., Bi, W. L., Golby, A., Frisken, S., & Kapur, T. (2023). The Brain Resection Multimodal Imaging Database (ReMIND) (Version 1) [dataset]. The Cancer Imaging Archive. https://doi.org/10.7937/3RAG-D070
  • Juvekar, P., Dorent, R., Kogl, F., Torio, E., Barr, C., Rigolo, L., Galvin, C., Jowkar, N., Kazi, A., Haouchine, N., Cheema, H., Navab, N., Pieper, S., Wells, W. M., Bi, W. L., Golby, A., Frisken, S., & Kapur, T. (2023). ReMIND: The Brain Resection Multimodal Imaging Database. Cold Spring Harbor Laboratory. https://doi.org/10.1101/2023.09.14.23295596