Automated Immunophenotyping Assessment for Diagnosing Childhood Acute Leukemia using Set-Transformers

TL;DR

This work proposes the FCM-Former, a machine learning, self-attention based FCM-diagnostic tool, automating the immunophenotyping assessment in Childhood Acute Leukemia, the first work that automates the immunophenotyping assessment with FCM data in diagnosing pediatric Acute Leukemia.

Abstract

Acute Leukemia is the most common hematologic malignancy in children and adolescents. A key methodology in the diagnostic evaluation of this malignancy is immunophenotyping based on Multiparameter Flow Cytometry (FCM). However, this approach is manual, and thus time-consuming and subjective. To alleviate this situation, we propose in this paper the FCM-Former, a machine learning, self-attention based FCM-diagnostic tool, automating the immunophenotyping assessment in Childhood Acute Leukemia. The FCM-Former is trained in a supervised manner, by directly using flow cytometric data. Our FCM-Former achieves an accuracy of 96.5% assigning lineage to each sample among 960 cases of either acute B-cell, T-cell lymphoblastic, and acute myeloid leukemia (B-ALL, T-ALL, AML). To the best of our knowledge, the FCM-Former is the first work that automates the immunophenotyping assessment with FCM data in diagnosing pediatric Acute Leukemia.

Figures (1)

• Figure 1: FCM-Former architecture. The input consists of a sample, represented by the event matrix, and augmented with a class token. There is a sequence of three attention blocks, as introduced in c2, followed by a linear classification layer which predicts a label for each sample.