Automated Identification of Cell Populations in Flow Cytometry Data with Transformers
- Resource Type
- Working Paper
- Authors
- Wödlinger, Matthias; Reiter, Michael; Weijler, Lisa; Maurer-Granofszky, Margarita; Schumich, Angela; Sajaroff, Elisa O.; Groeneveld-Krentz, Stefanie; Rossi, Jorge G.; Karawajew, Leonid; Ratei, Richard; Dworzak, Michael
- Source
- Computers in Biology and Medicine, Vol. 144 (2022)
- Subject
- Quantitative Biology - Quantitative Methods
Computer Science - Machine Learning
- Language
Acute Lymphoblastic Leukemia (ALL) is the most frequent hematologic malignancy in children and adolescents. A strong prognostic factor in ALL is given by the Minimal Residual Disease (MRD), which is a measure for the number of leukemic cells persistent in a patient. Manual MRD assessment from Multiparameter Flow Cytometry (FCM) data after treatment is time-consuming and subjective. In this work, we present an automated method to compute the MRD value directly from FCM data. We present a novel neural network approach based on the transformer architecture that learns to directly identify blast cells in a sample. We train our method in a supervised manner and evaluate it on publicly available ALL FCM data from three different clinical centers. Our method reaches a median F1 score of ~0.94 when evaluated on 519 B-ALL samples and shows better results than existing methods on 4 different datasets
Comment: The article has been published as an open access article in the Journal for Computers in Biology and Medicine: https://doi.org/10.1016/j.compbiomed.2022.105314