Automated counting of prostate cell types with image processing and machine learning
PLOS One · 04.05.2026 · 21 (5) · e0340628
DOI: 10.1371/journal.pone.0340628 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.05.2026. Verfasst von Babak Kamali Doust Azad und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Prostatic Neoplasms, Machine Learning, Prostate. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Traditional cell counting in clinical and research settings often relies on hemocytometry, a manual technique that is labor-intensive and prone to human error. These limitations in precision and throughput can hinder the development of effective diagnostic and therapeutic strategies, particularly in the context of prostate cancer. Recent advances in machine learning have shown considerable promise in enhancing the accuracy and efficiency of cell enumeration. In this study, we present a novel software system for the automated counting of prostate cancer cells, integrating image processing with deep learning methodologies. Unique to our approach, the system robustly utilizes images acquired from conventional mobile phone cameras, offering a highly accessible and scalable solution. It applies a convolutional neural network (CNN) in conjunction with a selective search algorithm to accurately identify regions of interest (ROIs), followed by robust image analysis algorithms for precise cell detection and quantification. This two-stage pipeline addresses the inherent variability and extraneous content in mobile-captured images, which is a significant advancement over methods reliant on controlled microscopic environments. Experimental evaluations demonstrate that the proposed method achieves superior accuracy compared to conventional manual counting approaches. This automated framework offers a practical, scalable solution that may significantly improve the reliability and efficiency of cell counting in both research and clinical diagnostics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran.
- Department of Biomedical Engineering, Tehran Islamic Azad University of Medical Sciences, Tehran, Iran.
- Department of Mechanical Engineering, Tarbiat Modares University, Tehran, Iran.
- Urology Research Center, Tehran University of Medical Sciences, Tehran, Iran.
- Department of Medical Laboratory Sciences, TeMS.C., Islamic Azad University Tehran, Tehran, Iran.
ORCID-Profile: Mohammadreza Kolahdouz
Zitieren
APA
Azad, B. K. D., Hakimi, A. N., Tabatabaei, S. M., Arezouchi, B. M., Keshtiban, M. M., Mirzaei, A., Nafian, F., Khatami, F., Aghamir, M. K., & Kolahdouz, M. (2026). Automated counting of prostate cell types with image processing and machine learning. PLOS One, 21(5), e0340628. https://doi.org/10.1371/journal.pone.0340628
Vancouver
Azad BKD, Hakimi AN, Tabatabaei SM, Arezouchi BM, Keshtiban MM, Mirzaei A, et al. Automated counting of prostate cell types with image processing and machine learning. PLOS One. 2026;21(5):e0340628. doi:10.1371/journal.pone.0340628
BibTeX
@article{Azad2026,
author = {Azad, Babak Kamali Doust and Hakimi, Aryan Norouzzadeh and Tabatabaei, Seyed Mohammad and Arezouchi, Bahar Mohammadi and Keshtiban, Mohsen Mashhadi and Mirzaei, Akram and Nafian, Fatemeh and Khatami, Fatemeh and Aghamir, Mohammad Kazem and Kolahdouz, Mohammadreza},
title = {Automated counting of prostate cell types with image processing and machine learning},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {5},
pages = {e0340628},
doi = {10.1371/journal.pone.0340628}
}
EUVIMED