Page History

Description

This dataset contains DICOM-SEG (DSO) conversions of the “Segmentation the Segmentation Labels and Radiomic Features for the Pre-operative Scans of the TCGA-LGG collection” and “Segmentation collection and Segmentation Labels and Radiomic Features for the Pre-operative Scans of the TCGA-GBM collection” TCIA collection analysis datasets, registered to the original spaces of the DICOM volumes from which they were derived. The MR volumes provided in the original segmentation datasets (T1 pre-contrast, T1 post-contrast, T2, FLAIR) are in NIfTI format, co-registered to an atlas space, and re-sampled to 1mm isotropic resolution. The provided original automatic and semi-automatic segmentations are also in the space and resolution of this atlas space. This dataset contains DICOM-SEG versions of the same segmentations, transformed back into the space of the DICOM MR patient datasets released in the original original TCGA-GBM and and TCGA-LGG datasets. For each patient in the segmentation dataset, each of the original NIfTI MR volumes has been registered and resampled back to their original patient space and resolution using 3DSlicer’s BRAINSFit module. The affine transformation files from these registrations are saved, and used to register and resample both the semi-automatic and automatic segmentations into the spaces of each original MR DICOM dataset. The resulting dataset contains four sets of registered segmentations for each base original segmentation, as each segmentation has been registered to the unique spacing and resolution of the untransformed pre-contrast T1, post-contrast T1, T2, and FLAIR DICOM datasets. These resulting NIfTI segmentations are then converted into DICOM-SEG datasets using the software package dcmqi. DICOM-SEG metadata values specifying tissue type, algorithm properties, and study qualities are encoded in JSON objects, which are provided in this dataset. Registration files Affine transformations from the original NIfTI datasets to the TCGA DICOM datasets are also made available for download in ITK transform format.

Please also cite the following original datasets and manuscript when citing this dataset:

...

• TCGA-LGG DICOM Image Data - 108 subjects (8.5 GB)
• TCGA-GBM DICOM Image Data - 135 subjects (6 GB)

• DICOM Segmentations, Registration Transformations, and DCMQI metadata

• TCGA_DSO_Key.csv (Maps file names to DICOM UIDS)

  Derived Data Set including
  
• Processed NIFTI images with segmentations and radiomic features
• Registration Transformations
DICOM Segementation Objects