Child pages
  • ROI Masks Defining Low-Grade Glioma Tumor Regions In the TCGA-LGG Image Collection (TCGA-LGG-Mask)
Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 4 Next »

Special Instruction:

The dataset should not be listed until a related manuscript is published.

The dataset will need a jnlp and DOI. They have a Box link  per Jan 31 and Martin already uploaded the Matlab data there.

  • Shared List Name: TCGA-LGG – MATLAB ROI
  • Authors: Chang Su, Martin Vallières, Harrison Bai


Data Citation

Chang Su, Martin Vallières, Harrison Bai. (2017) TCGA-LGG – MATLAB ROI. The Cancer Imaging Archive.


This collection contains 406 ROI masks in MATLAB format defining the low grade glioma (LGG) tumour region on T1-weighted, T2-weighted, T1-weighted post-contrast and T2-flair MR images of 108 different patients from the TCGA-LGG dataset. The ROI masks were used to extract texture features in order to develop radiomic-based multivariable models for the prediction of isocitrate dehydrogenase 1 (IDH1) mutation, 1p/19q codeletion status, histological grade and tumour progression. 

Clinical data, VASARI scores and source code used in this study are also available with this collection. Please see the DOI below for more details and link to access the whole dataset. Please contact Martin Vallières ( of the Medical Physics Unit of McGill University for any scientific inquiries about this dataset.

The analysis results are presented in the following study:

Publication Citation

Hao Zhou, Martin Vallières, Harrison X. Bai, Chang Su, Haiyun Tang, Derek Oldridge, Zishu Zhang, Bo Xiao, Weihua Liao, Yongguang Tao, Jianhua Zhou, Paul Zhang, Li Yang; MRI features predict survival and molecular markers in diffuse lower-grade gliomas. Neuro Oncol 2017 now256. doi: 10.1093/neuonc/now256


  • No labels