Child pages
  • High Resolution Prostate Segmentations for the ProstateX-Challenge (PROSTATEx-Seg-HiRes)
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 12 Next »


We created 66 high resolution segmentations for randomly chosen T2-weighted volumes of the ProstateX challenge. The high resolution segmentations were obtained by considering the three scan directions: for each scan direction (axial, sagittal, coronal), the gland was manually delineated by a medical student, followed by a review and corrections of an expert urologist. These three anisotropic segmentations were fused to one isotropic segmentation by means of shape-based interpolation in the following manner: (1) The signed distance transformation of the three segmentations is computed. (2) The anisotropic distance volumes are transformed into an isotropic high-resolution representation with linear interpolation. (3) By averaging the distances, smoothing and thresholding them at zero, we obtained the fused segmentation. The resulting segmentations were manually verified and corrected further by the expert urologist if necessary. Serving as ground truth for training CNNs, these segmentations have the potential to improve the segmentation accuracy of automated algorithms. By considering not only the axial scans but also sagittal and coronal scan directions, we aimed to have higher fidelity of the segmentations especially at the apex and base regions of the prostate.

For a research project about automatic high resolution prostate segmentation, our medical partners created manually 66 ground truth segmentations of the following TCIA collection:

The segmentations were created by considering the axial, coronal and sagittal T2 weighted scans and have isotropic resolution.

The segmentations to standard DICOM representation were created with dcmqi.

Special Instructions: Please do not list this data before the publication of our research paper. This may take a few months. After publication of the manuscript, we’d like to include the paper’s reference into the dataset description if possible.

Data Access

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

Data TypeDownload all or Query/Filter
Segmentation Images (DICOM #.# GB)

Corresponding Original MR Images from PROSTATEx (DICOM, 1.0 GB)

Patient ID List (TXT)

Detailed Description

Image Statistics
Number of Patients
Number of Studies
Number of Series

Number of Images

Image Size (GB)

Note:  Please contact  with any questions regarding usage.

Citations & Data Usage Policy 

These collections are freely available to browse, download, and use for commercial, scientific and educational purposes as outlined in the Creative Commons Attribution 3.0 Unported License. Questions may be directed to Please be sure to acknowledge both this data set and TCIA in publications by including the following citations in your work:

Dataset Citation

Schindele, D., Meyer, A., Von Reibnitz, D. F., Kiesswetter, V., Schostak, M., Rak, M., & Hansen, C. (2019). High Resolution Prostate Segmentations for the ProstateX-Challenge [Data set]. The Cancer Imaging Archive.

TCIA 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. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository, Journal of Digital Imaging, Volume 26, Number 6, December, 2013, pp 1045-1057. DOI: 10.1007/s10278-013-9622-7

In addition to the dataset citation above, please be sure to cite the following if you utilize these data in your research:

Publication Citation

<coming soon>

Other Publications Using This Data

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

Version 1 (Current): 2020/01/08

Data TypeDownload all or Query/Filter
Segmentation Images (DICOM #.# GB)

Corresponding Original MR Images from PROSTATEx (DICOM, 1.0 GB)

Patient ID List (TXT)

          <selected illustrative figure can go here>

  • No labels