The award-winning research was centered around developing neural network-based diagnostic support systems for morphologic examination of leukocytes in bone marrow and peripheral blood, which represents a key step in the diagnostic workup of many hematologic malignancies. The results pave the way for a faster and more precise characterization of these disease entities in the near future.
Christian Matek started the award-winning research during his time as a Dr. med. student jointly supervised by Prof. Dr. Karsten Spiekermann at the Department of Internal Medicine III at LMU University Medical Center (Director: Prof. Dr. Dr. Michael von Bergwelt) and the group of Dr. Carsten Marr at Helmholtz Munich. During his time as a postdoctoral researcher there, the method could be extended to cover bone marrow samples from a wide variety of patients. Currently, Dr. Matek works as a resident at the Institute of Pathology at Uniklinikum Erlangen.
References:
Christian Matek, Sebastian Krappe, Christian Münzenmayer, Torsten Haferlach, Carsten Marr; Highly accurate differentiation of bone marrow cell morphologies using deep neural networks on a large image data set. Blood 2021; 138 (20): 1917–1927. DOI: https://doi.org/10.1182/blood.2020010568
Christian Matek, Simone Schwarz, Karsten Spiekermann, Carsten Marr; Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks. Nat Mach Intell 1, 538–544 (2019). DOI: https://doi.org/10.1038/s42256-019-0101-9