Research Projects
MAINFRAME: Machine Learning for Advanced Integrated Diagnostics of Myeloid Neoplasms
With the advent of Machine Learning (ML) in medicine, hypothesis-driven approaches of data analysis and manual analog microscopy for research and diagnostic purposes in hematology seem outdated, tedious and often generate irreproducible results. With its capability to make sense of large and heterogenous data sets, ML is well suited to provide insights into disease biology using a data-driven approach and automatize bone marrow image analysis via computer vision or complex patient data relations utilizing clustering techniques. MAINFRAME is a series of interconnected ML projects building on two existing prototypes for the analysis of hematological databases and bone marrow image data in order to automatically detect malignant disease in bone marrow smears, stratify patients according to individual demographic, clinical, laboratory and genetic parameters, and illuminate important molecular alterations that drive malignant disease. MAINFRAME’s two prototypes are designed for the analysis of large cancer databases using both supervised as well as unsupervised ML and for computer vision in bone marrow microscopy. They provide the clinician with a faster, standardized and more accurate diagnostic tool allowing treatment concepts that are tailored to the patients’ individual needs while researchers benefit from data-driven analysis that may generate novel insights in the biology of myeloid neoplasms.
- Funded by: EKFZ - IIP
- Contact person: Karsten Wendt
- Project Website: link
- Funding period: 01/2023 - 12/2024