Relationship between Artificial Intelligence-Based Cell Detection and Cytomorphological Variations Induced by Cell Processing Solutions: Usefulness of Data Augmentation in Artificial Intelligence Cytology
Acta Cytologica · 2025
DOI: 10.1159/000547485 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Cytologica, 2025. Verfasst von Nanako Sakabe und 4 weiteren Autor:innen. Beteiligte Einrichtung: Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan. Hauptthemen laut MEDLINE: Artificial Intelligence, Stomach Neoplasms, Deep Learning, Cytodiagnosis. Die Arbeit nennt 24 Literaturangaben.
Abstract (Originalsprache)
Introduction
Variations in cytomorphology due to differences in specimen preparation conditions hinder the implementation of artificial intelligence (AI) in cytology. In addition, small-scale research and insufficient datasets pose challenges. In this study, we aimed to examine the relationship between cytomorphological variations induced by cell processing solutions and AI-based cell detection accuracy and to demonstrate the usefulness of data augmentation in AI cytology.
Methods
Samples of untreated MKN45 human gastric cancer cells and cells treated with four different cell processing solutions were used to prepare the specimens. These specimens were subjected to Papanicolaou staining, and the areas and hue, saturation, and brightness (HSB) values of the nucleus and cytoplasm were analyzed mathematically and statistically. Deep learning (DL) models were developed with and without data augmentation, and AI-based cell detection rates were evaluated.
Results
Heparin sodium solution-treated (Hep) cells showed obvious differences from other groups and presented significant differences compared to control (Cont) cells in the analysis of areas and HSB values of the nucleus and cytoplasm. The AI-based cell detection rate of Hep cells was also significantly lower than that of Cont cells. The use of the DL model with data augmentation improved the AI-based cell detection rate for all samples.
Conclusion
We identified the key cytomorphological features that AI focuses on when recognizing cells and demonstrated that data augmentation is an effective technique for improving AI-based cell detection accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan.
- Clinical Engineering, Faculty of Medical Sciences, Juntendo University, Urayasu, Japan.
- Pathophysiology Sciences, Department of Integrated Health Sciences, Nagoya University Graduate School of Medicine, Nagoya, Japan, ikeda.katsuhide.y1@f.mail.nagoya-u.ac.jp.
Zitieren
APA
Sakabe, N., Yoshizaki, Y., Fukuda, K., Sato, S., & Ikeda, K. (2025). Relationship between Artificial Intelligence-Based Cell Detection and Cytomorphological Variations Induced by Cell Processing Solutions: Usefulness of Data Augmentation in Artificial Intelligence Cytology. Acta Cytologica. https://doi.org/10.1159/000547485
Vancouver
Sakabe N, Yoshizaki Y, Fukuda K, Sato S, Ikeda K. Relationship between Artificial Intelligence-Based Cell Detection and Cytomorphological Variations Induced by Cell Processing Solutions: Usefulness of Data Augmentation in Artificial Intelligence Cytology. Acta Cytologica. 2025. doi:10.1159/000547485
BibTeX
@article{Sakabe2025,
author = {Sakabe, Nanako and Yoshizaki, Yuma and Fukuda, Kenta and Sato, Shouichi and Ikeda, Katsuhide},
title = {Relationship between Artificial Intelligence-Based Cell Detection and Cytomorphological Variations Induced by Cell Processing Solutions: Usefulness of Data Augmentation in Artificial Intelligence Cytology},
journal = {Acta Cytologica},
year = {2025},
doi = {10.1159/000547485}
}
EUVIMED