Skip to main content


AML-Cytomorphology_LMU | A Single-cell Morphological Dataset of Leukocytes from AML Patients and Non-malignant Controls

DOI: 10.7937/tcia.2019.36f5o9ld | Data Citation Required | Image Collection

Location Species Subjects Data Types Cancer Types Size Supporting Data Status Updated
Blood Human 200 Histopathology Acute Myeloid Leukemia 11GB Image Analyses Public, Complete 2019/10/24


The Munich AML Morphology Dataset contains 18,365 expert-labeled single-cell images taken from peripheral blood smears of 100 patients diagnosed with Acute Myeloid Leukemia at Munich University Hospital between 2014 and 2017, as well as 100 patients without signs of hematological malignancy. Image acquisition was done using a M8 digital microscope / scanner (Precipoint GmbH, Freising, Germany) at 100-fold optical magnification and oil immersion. Pathological and non-pathological leukocytes were classified into a standard morphological classification scheme derived from clinical practice by trained experts. To quantify inter- and intra-rater variability of examiners, a subset of images was re-annotated up to two times. The dataset has been used by the authors to train a convolutional neural network for single-cell morphology classification.

Data Access

Version 1: Updated 2019/10/24

Title Data Type Format Access Points Subjects Studies Series Images License
Tissue Slide Images Histopathology TIFF
Download requires IBM-Aspera-Connect plugin
200 18,365 CC BY 3.0
Abbreviations TXT CC BY 3.0
Annotations DAT and ZIP CC BY 3.0

Citations & Data Usage Policy

Data Citation Required: Users must abide by the TCIA Data Usage Policy and Restrictions. Attribution must include the following citation, including the Digital Object Identifier:

Data Citation

“Matek, C., Schwarz, S., Marr, C., & Spiekermann, K. (2019). A Single-cell Morphological Dataset of Leukocytes from AML Patients and Non-malignant Controls [Data set]. The Cancer Imaging Archive.

Detailed Description

Additional Information about Data

  • All single-cell images in this dataset were produced using the M8 digital microscope/scanner (Precipoint GmbH, Freising/Germany) from peripheral blood smears at 100x magnification and oil immersion. A coverage of 14.14 Pixels per Micron is given by the manufacturer.
  • The abbreviations used for morphological classes in annotations and the folder structure are defined in abbreviations.txt
  • Annotations are given in the file annotations.dat. In this file, the first column gives the name of the respective image file and the second column the morphological class assigned during the gold-standard annotation. If a single-cell image was re-annotated, the result of the first re-annotation process by a second independent annotator is given in the third column, and the result of the second re-annotation process after a time interval of 11 months by the same re-annotator in the fourth column. If a single-cell image was not re-annotated, the third and fourth column contain the value “nan”.
  • For details of the scanning and annotation process, please refer to:
    • Matek et al., Human-level recognition of blast cells in acute myeloid leukemia with convolutional neural networks., Nat. Mach. Intell. (2019)


We would like to acknowledge the following individuals and institutions:

  • The authors wish to thank Antje Holzäpfel for contributions to the annotation task.
  • German Research Foundation, grant SFB 1243.
  • Christian Matek gratefully acknowledges support from Deutsche José Carreras-Leukämie Stiftung.

Other Publications Using this Data

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

Publication Citation

Matek, C., Schwarz, S., Spiekermann, K.  et al.  Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks.  Nat Mach Intell   1,  538–544 (2019).

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. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. In Journal of Digital Imaging (Vol. 26, Issue 6, pp. 1045–1057). Springer Science and Business Media LLC.