Open dataset · MR

Prostate158 - 3T prostate MRI

Expert-annotated biparametric 3T prostate MRI: T2W, ADC and DWI series with zonal anatomy and prostate cancer lesion masks.

The sample cases below open read-only in the MedSeg editor - no account needed. Open the full dataset to copy all 473 cases into your workspace, run AI models, and segment.

MR 473 cases CC-BY-4.0 Reference masks Pathology
Prostate158 - 3T prostate MRI - example case rendered in the MedSeg editor
Example case with its reference segmentation - straight from the catalog, rendered by MedSeg.

Browse sample cases

These cases open instantly in the browser-based editor - scroll the slices, inspect the reference masks, window the image. No account needed.

Open the full dataset in MedSeg → All 473 cases - copy into your workspace to run AI and segment.

About this dataset

Prostate158 is an expert-annotated 3T biparametric prostate MRI dataset for segmentation of prostate anatomical zones and cancerous lesions. The source data provides T2-weighted, ADC and DWI NIfTI series for each study. Reader-specific reference masks are kept as separate masks in MedSeg instead of being merged: T2 anatomy masks are attached to the T2 series, T2 lesion masks to the T2 series, and ADC lesion masks to the ADC series.

The training deposit contains 139 studies and the test deposit contains 19 additional studies. The Zenodo records are open access; this catalog entry treats the dataset as CC BY 4.0, in line with the companion Data in Brief article's version-of-record license. Users should still cite the upstream Prostate158 papers and Zenodo deposits.

FactValue
Cases473
Series473
Size3.0 GB
ModalityMR
Reference masksYes
LicenseCC-BY-4.0
PublisherProstate158 authors / Charite Universitatsmedizin Berlin
Version1
DOI10.1016/j.dib.2022.108739

What you can do with it in MedSeg

Copied cases behave like normal project series - the public image bytes are linked, not duplicated, so copies are instant and take no extra storage.

  1. Copy cases into a project.
    Filter, multi-select, copy - reference masks come along if you want them.
  2. Run AI segmentation.
    TotalSegmentator, MRSegmentator, nnInteractive 3D clicks/scribbles, or text-prompted VoxTell.
  3. Edit and measure.
    Brush, lasso, fill, oblique planes, volumes in ml - in the browser.
  4. Train your own nnU-Net.
    Correct masks on a handful of cases and train a custom model on hosted GPUs.

Citation

If you use this dataset in your research, cite the source per its license terms.

Adams, L. C., Makowski, M. R., Engel, G., Rattunde, M., Busch, F., Asbach, P., Niehues, S. M., Vinayahalingam, S., van Ginneken, B., Litjens, G., & Bressem, K. K. (2022). Prostate158 - An expert-annotated 3T MRI dataset and algorithm for prostate cancer detection. Computers in Biology and Medicine, 148, 105817. Adams, L. C., et al. (2022). Dataset of prostate MRI annotated for anatomical zones and cancer. Data in Brief, 45, 108739.

License: CC-BY-4.0

Open data still carries obligations - attribution at minimum. Check the license terms and the source publication before publishing work built on this dataset. MedSeg is a research tool, not a medical device.

More public datasets