Acute myeloid leukemia (AML) is the second most frequent leukemia entity in children and adolescents, and definitely the most aggressive variant. Despite continued progress and refinement of therapeutic approaches, about 35% of pediatric patients with the disease still suffer from relapse.
Multiparameter flow-cytometry (FCM) is one of the methodologies most useful to monitor the number of remaining leukemic cells in bone marrow (minimal residual disease, MRD) in AML patients, because it is widely available and applicable to most patients.
Recently, we have developed algorithms and a software for automated MRD assessment in acute lymphoblastic leukemia (ALL) in a EU project called AutoFLOW. However, AML is a related but independent disorder with a much more complex pathology and complexity. The goal of the PhD is to develop an independent approach and strategy for assessment of AML FCM Data.
In this project, you are able to make use of our already established large database of FCM-MRD data from children with AML generated during the course of our previous projects as well as of the algorithms developed therein. You will use this extensive experience gained to develop improved methods based on Transformers and related Deep Learning methods that help to move our existing software towards a market-ready product for automated quantification of MRD in AML. You will work in a team of computer scientists from TU and medical experts from the St.Anna Children’s Cancer Research Institute.
- Applicants should hold a master’s degree in Computer Science, Mathematics or similar
- Applicants should have profound knowledge of Machine Learning, in particular Deep Learning
- Experience with C++ and Python Deep Learning frameworks advantageous