Child pages
  • RSNA-ASNR-MICCAI-BraTS-2021

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.



Column
width70%

Summary

Excerpt


  This dataset includes brain MRI scans of adult brain glioma patients, comprising of 4 structural modalities (i.e., T1, T1c, T2, T2-FLAIR) and associated manually generated ground truth labels for each tumor sub-region (enhancement, necrosis, edema), as well as their MGMT promoter methylation status. These scans are a collection of data from existing TCIA collections, but also cases provided by individual institutions and willing to share with a cc-by license.

  The BraTS dataset describes a retrospective collection of brain tumor structural mpMRI scans of 2,040 patients, acquired from multiple different institutions under standard clinical conditions, but with different equipment and imaging protocols, resulting in a vastly heterogeneous image quality reflecting diverse clinical practice across different institutions. The 4 structural mpMRI scans included in the BraTS challenge describe a) native (T1) and b) post-contrast T1-weighted (T1Gd (Gadolinium)), c) T2-weighted (T2), and d) T2 Fluid Attenuated Inversion Recovery (T2-FLAIR) volumes, acquired with different protocols and various scanners from multiple institutions. Furthermore, data on the O[6]-methylguanine-DNA methyltransferase (MGMT) promoter methylation status is provided as a binary label. Notably, MGMT is a DNA repair enzyme that the methylation of its promoter in newly diagnosed glioblastoma has been identified as a favorable prognostic factor and a predictor of chemotherapy response.

   It is curated for computational image analysis of segmentation and prediction of the MGMT promoter methylation status.



Column


A note about available TCIA data which were converted for use in this Challenge 

Dr. Bakas's group has provided skull-stripped challenge TRAINING data in NIfTI that do not pose DUA-level risk of potential facial reidentification, and segmentations to go with them. Dr. Bakas's group has provided the skull-stripped challenge TEST data in NIfTI, and segmentations to go with them, available upon request through the helpdesk. If you want the DICOM, then as part of page 1 of

...

this Agreement form

...

 TCIA needs to have the citation for the (TCGA-GBM, CPTAC-GBM, Ivy GAP, TCGA-LGG, other facial-detail-retained Collections) filled in. These earlier data that pose enough reidentification risk that TCIA must keep them behind an explicit usage agreement follow this restriction.


Acknowledgements

We would like to acknowledge the individuals and institutions that have provided data for this collection:

...

Localtab Group


Localtab
activetrue
titleData Access

Data Access

Tcia license 4 international

Note to curators! This macro is for collections that are restricted due to facial reconstruction possibility.

Tcia head license access



Data TypeDownload all or Query/FilterLicense

Images , and Segmentations (NIfTI, 1.4 TB)


Complete dataset

Tcia button generator

complete data on faspex


(Download and apply the IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) 

Tcia cc by 4




BraTS 2021 Training set in batches of XXX PatientID Images, Segmentations (NIfTI, 1.4 TB)

  1. batch1 (ID PP to QQ) (XX GB)

    Tcia button generator

    batch1


  2. batch2 (ID XX to YY) (XX GB)

    Tcia button generator

    batch2



  3.  (and so on)



    (Download and apply the
    IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) 

Tcia cc by 4

BraTS 2021 Validation set in batches of XXX PatientID Images, Segmentations (NIfTI, 1.4 TB)


  1. Tcia button generator

    batch1




  2. Tcia button generator

    batch2


    (Download and apply the IBM-Aspera-Connect plugin to your browser to retrieve this faspex package) 

Tcia cc by 4

BraTS Task2 Radiogenomics Classifier task images (DICOM?, GB)

  1. link to faspex for nifti
  2. link to GDC/PDC if the detail are there

( is this open license stuff?)

BraTS Task2 Radiogenomics Classifier task molecular marker table (JSON/XLS/CSV spreadsheet, MB)

  1. download JSON/XLS/CSV spreadsheet  or 
  2. if external link that would go below not in this table

( is this open license stuff?)

Images from TCGA-LGG that have been transformed for use in this challenge  - 108 Subjects (DICOM, 8.5 GB)


Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/24282668/doiJNLP-JAMS4RFq.tcia?api=v2

TCGA-LGG batch1 

Note: Limited Access.
Click the Download  button to save a ".tcia" manifest file to your computer, which you must open with the  NBIA Data Retriever 

Tcia restricted license

Images from TCGA-GBM that have been transformed for use in this challenge- 135 subjects (DICOM, 6 GB)


Tcia button generator
urlhttps://wiki.cancerimagingarchive.net/download/attachments/24282666/doiJNLP-QoOaKUdn.tcia?api=v2

TCGA-GBM


Note: Limited Access.
Click the Download  button to save a ".tcia" manifest file, needs the NBIA Data Retriever

Tcia restricted license

Images from Ivy GAP that have been transformed for use in this challenge- XXX subjects (DICOM, XX GB)


Tcia button generator

Ivy GAP


Note: Limited Access.
Click the Download  button to save a ".tcia" manifest file, needs the  NBIA Data Retriever

Tcia restricted license

CPTAC-GBM DICOM


Tcia restricted license

UCSF-PDGM DICOM (note Evan didn't give this to us  –  only nifti so far) 



UPENN-GBM DICOM ( others)



Transformation matrices DICOM to NII (zip, XXMB)


Tcia button generator



Tcia cc by 4

Clinical data (CSV)



Tcia button generator



Tcia cc by 4

Tcia restricted license

Feature matrices (format, ##GB)

link or attachment

Tcia cc by 4

 the "challenge test set dataset" is sequestered on synapse as a tarball of nii & seg & age & diagnosis. 

Not available. Please see <website> for more detail.

n/a

Click the Versions tab for more info about data releases.

Additional Resources for this Dataset

Note to curators! Use this any time you are linking to NCI's IDC/GDC/PDC resources.  The links below are examples and will need to be tailored to point to the specific dataset (see parameters in URLS).

Nci_crdc additional resources


Note to curators! Below are examples for what to do with other external resources/links that don't fit into the above categories.

The following external resources have been made available by the data submitters.  These are not hosted or supported by TCIA, but may be useful to researchers utilizing this collection.

  • Software / Code on Github
  • Genomics data in DbGAP
  • Genomics data in Gene Expression Omnibus
  • RSNA or kaggle link to molecular marker table if they only provide us a link

TCIA Collections Used (in part) in these analyses

, for exact series see table above

:







Third Party Analyses of this Dataset

TCIA encourages the community to publish your analyses of our datasets. Below is a list of such third party analyses published using this Collection:

  • <these get filled in as groups cite the dataset in their papers related to analysis of the 2021 task 1 & task2 using this Collection's DOI>



Localtab
titleDetailed Description

Detailed Description

Image Statistics

Radiology Image StatisticsPathology Image Statistics

Modalities



Number of Patients



Number of Studies



Number of Series



Number of Images



Images Size (GB)
<< Add any additional information that didn't fit or belong in the Summary section. >>



  •  the "challenge test set dataset" is sequestered on synapse as a tarball of nii & seg & age & diagnosis. Not available. Please see <website> for more detail.

The data used in BraTS Challenges often have some overlap with other TCIA Collections, cases, and series. Some filters for handling these, so that you can work with statistically not-duplicated images, include these below:



Localtab
titleCitations & Data Usage Policy

Citations & Data Usage Policy

Tcia limited license policy

Info
titleData Citation

DOI goes here. Create using Datacite with information from Collection Approval form

44 authors, most with ORCiD. 


Info
titlePublication Citation

U.Baid, et al., "The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification", arXiv:2107.02314, 2021. 


Info
titleAcknowledgement

Required acknowledgements only (ex:The CPTAC program requests that publications using data from this program...). If they just want to thank someone, that goes in the Acknowledgement section underneath the Summary.


Info
titleTCIA Citation

Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. In Journal of Digital Imaging (Vol. 26, Issue 6, pp. 1045–1057). Springer Science and Business Media LLC.https://doi.org/10.1007/s10278-013-9622-7

Other Publications Using This Data

TCIA maintains a list of publications which leverage TCIA data. If you have a manuscript you'd like to add please contact the TCIA Helpdesk.


Localtab
titleVersions

Version X (Current): Updated yyyy/mm/dd

copy Access tab table here

<< One or two sentences about what you changed since last version.  No note required for version 1. >> 


...