Child pages
  • An Expert-Annotated Dataset of Bone Marrow Cytology in Hematologic Malignancies (Bone-Marrow-Cytomorphology_MLL_Helmholtz_Fraunhofer)

Versions Compared


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




The dataset contains a collection of over 170,000 de-identified, expert-annotated cells from the bone marrow smears of 945 patients stained using the May-Grünwald-Giemsa/Pappenheim stain. The diagnosis distribution in the cohort included a variety of hematological diseases reflective of the sample entry of a large laboratory specialized in leukemia diagnostics. Image acquisition was performed using a brightfield microscope with 40x magnification and oil immersion.

Large datasets with a high quality of both data acquisition and annotation are key prerequisites to develop data-driven, computational methods in diagnostic medicine. In the case of bone marrow morphology, a key diagnostic method for a broad range of hematologic diseases, only few datasets are publicly available so far, which are orders of magnitude smaller than the one presented here. Inclusion of our dataset into TCIA provides both medical researchers and bioinformaticians with a public resource for education and algorithm improvement.

All samples were processed in the Munich Leukemia Laboratory (MLL), scanned using equipment developed at Fraunhofer IIS and post-processed using software developed at Helmholtz Munich.