Authors:Roxane Licandro1;Michael Reiter2;Markus Diem2;Michael Dworzak3;Angela Schumich4 andMartin Kampel2
Affiliations:1TU Wien and Medical University of Vienna, Austria;2TU Wien, Austria;3Medical University of Vienna and Labdia Labordiagnostik GmbH, Austria;4Labdia Labordiagnostik GmbH, Austria
Keyword(s):Clustering, Machine Learning, Flow Cytometry, Acute Myeloid Childhood Leukaemia, Minimal Residual Disease.
RelatedOntology Subjects/Areas/Topics:Applications ;Bioinformatics and Systems Biology ;Clustering ;Medical Imaging ;Pattern Recognition ;Software Engineering ;Theory and Methods
Abstract:Acute Myeloid Leukaemia (AML) is a rare type of blood cancer in children. This disease originates fromgenetic alterations of hematopoetic progenitor cells, which are involved in the hematopoiesis process, andleads to the proliferation of undifferentiated (leukaemic) cells. Flow CytoMetry (FCM) measurements enablethe assessment of the Minimal Residual Disease (MRD), a value which clinicians use as powerful predictorfor treatment response and diagnostic tool for planning patients’ individual therapy. In this work we proposemachine learning applications for the automatic MRD assessment in AML. Recent approaches focus on childhoodAcute Lymphoblastic Leukaemia (ALL), more common in this population. We perform experimentsregarding the performance of state-of-the-art algorithms and provide a novel GMM formulation to estimateleukaemic cell populations by learning background (non-cancer) populations only. Additionally, combinationof backgrounds of different leukaemia types are evaluated regarding their ability to predict MRD in AML. Theresults suggest that background populations and combinations of these are suitable to assess MRD in AML.(More)
Acute Myeloid Leukaemia (AML) is a rare type of blood cancer in children. This disease originates from
genetic alterations of hematopoetic progenitor cells, which are involved in the hematopoiesis process, and
leads to the proliferation of undifferentiated (leukaemic) cells. Flow CytoMetry (FCM) measurements enable
the assessment of the Minimal Residual Disease (MRD), a value which clinicians use as powerful predictor
for treatment response and diagnostic tool for planning patients’ individual therapy. In this work we propose
machine learning applications for the automatic MRD assessment in AML. Recent approaches focus on childhood
Acute Lymphoblastic Leukaemia (ALL), more common in this population. We perform experiments
regarding the performance of state-of-the-art algorithms and provide a novel GMM formulation to estimate
leukaemic cell populations by learning background (non-cancer) populations only. Additionally, combination
of backgrounds of different leukaemia types are evaluated regarding their ability to predict MRD in AML. The
results suggest that background populations and combinations of these are suitable to assess MRD in AML.