@misc{10481/108279,
year = {2025},
url = {https://hdl.handle.net/10481/108279},
abstract = {Flow cytometry is an advanced technique for analyzing cellular heterogeneity in biomedical research and clinical
diagnostics. Its ability to generate multiparametric data has facilitated advancements in disease classification problems, particularly
addressing challenges in distinguishing cell populations and predicting disease outcomes. In these classification tasks, most works
consist on either labeling individual cells based on their phenotypic markers or categorizing patient samples as healthy or diseased.
However, the complexity of flow cytometry data, characterized by hurdles such as spectral overlap, wide dynamic ranges or batch
effects require the usage of preprocessing strategies prior to modeling analysis. This research provides a comprehensive survey of
current preprocessing techniques for flow cytometry data used in classification tasks and discusses their specific applications, focusing
on four key aspects of data treatment: signal compensation and transformation, batch effect mitigation, imperfect data treatment, and
feature selection and class balance. Emphasis is placed on standardizing preprocessing workflows and addressing computational and
analytical difficulties posed by the size of modern flow cytometry datasets. The paper also includes a discussion on future opportunities
for improving preprocessing pipelines to improve the reproducibility of flow cytometry-based classification models. In short, this work
serves as a reference for experts in the field, consolidating best practices in preprocessing and providing guidelines for the
development of methodologies that optimize the classification of flow cytometry data.},
organization = {MCIN/AEI/10.13039/501100011033 PID2020-119032RB-I00},
organization = {University of Granada PP2024PP-07},
publisher = {IEEE},
keywords = {Flow cytometry},
keywords = {Preprocessing},
keywords = {Data quality},
title = {A survey of preprocessing techniques for flow cytometry data in classification tasks},
doi = {10.1109/TCBBIO.2025.3612573},
author = {Núñez Nepomuceno, David and Sáez Muñoz, José Antonio and Carmona Sáez, Pedro},
}