Minimal Residual Disease Detection in Acute Myeloid Leukemia by RQ‐PCR and Multiparameter Flow Cytometry

Kern, Wolfgang; Schnittger, Susanne

doi:10.1002/9781444398595.ch18

Cited by 1 publication

(1 citation statement)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…cancer burden, an important measure for optimizing treatments and prognosis) can also be quantified from the analysis of FCM data. As a result, FCM immunophenotyping is routinely used in diagnosis and prognosis of blood and lymphoid cancers ( Diamond et al 1982 , Terstappen et al 1992 , Stetler-Stevenson and Braylan 2001 , Stetler-Stevenson et al 2001 , Weir and Borowitz 2001 , Kaleem et al 2003 , Kern et al 2003 , Freeman et al 2013 , Chiaretti et al 2014 , Rawstron et al 2018 ). It is also widely used to identify abnormal cell populations in association with nonneoplastic diseases including asthma, allergy, and autoimmunity ( Ebo et al 2005 , Boumiza et al 2005 , Wei et al 2007 , Smyth et al 2010 , Wolff et al 2010 , Lazarus et al 2012 , Irvin et al 2014 ).…”

Section: Introductionmentioning

confidence: 99%

A cell-level discriminative neural network model for diagnosis of blood cancers

Robles,

Jin,

Smyth

et al. 2023

Bioinformatics

View full text Add to dashboard Cite

Motivation Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes. Results We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes sample-level training data and predicts the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations. Availability and implementation The source code of CSNN and datasets used in the experiments are publicly available on GitHub (http://github.com/erobl/csnn). Raw FCS files can be downloaded from FlowRepository (ID: FR-FCM-Z6YK).

show abstract