EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Network Classification of Body Fluid Adenocarcinoma Cell Images Based on Hu Moment Invariant Features

Yessi Jusman, Rizqa Salsabiela, Julnila Husna Lubis

BIO Web of Conferences · 2026 · 264 · 01004

DOI: 10.1051/bioconf/202626401004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BIO Web of Conferences, online erschienen am 16.11.2026. Verfasst von Yessi Jusman und 2 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adenocarcinoma is one of the most common malignant cancers and can be identified through cytological examination of body fluid specimens, such as pleural and peritoneal fluids. However, manual microscopic assessment is time-consuming and highly dependent on the expertise of cytopathologists, resulting in diagnostic variability. Therefore, an automated classification system is required to assist in the early detection and diagnosis of adenocarcinoma cells. This study proposed an automated cytological classification for distinguishing adenocarcinoma and normal cells in body fluid images using Hu Moment Invariants and Artificial Neural Networks. Hu Moment Invariants were employed to extract shape-based features invariant to translation, rotation, and scaling. The extracted features were then classified using a Multilayer Perceptron (MLP) with three training algorithms: Conjugate Gradient Backpropagation (CGB), Gradient Descent with Momentum (GDM), and Levenberg-Marquardt (LM). Experimental results demonstrated that the Levenberg-Marquardt algorithm with 10 hidden neurons achieved the highest overall performance, with average training, validation, and testing accuracies of 79.26%, 79.27%, and 79.23%, respectively. These findings indicated that the combination of Hu Moment Invariants and MLP has served as a promising approach for automated cytological classification of adenocarcinoma cells in body fluid images and may support computer-aided diagnostic systems in clinical practice.

Zitieren

APA

Jusman, Y., Salsabiela, R., & Lubis, J. H. (2026). Neural Network Classification of Body Fluid Adenocarcinoma Cell Images Based on Hu Moment Invariant Features. BIO Web of Conferences, 264, 01004. https://doi.org/10.1051/bioconf/202626401004

Vancouver

Jusman Y, Salsabiela R, Lubis JH. Neural Network Classification of Body Fluid Adenocarcinoma Cell Images Based on Hu Moment Invariant Features. BIO Web of Conferences. 2026;264:01004. doi:10.1051/bioconf/202626401004

BibTeX
@article{Jusman2026,
  author = {Jusman, Yessi and Salsabiela, Rizqa and Lubis, Julnila Husna},
  title = {Neural Network Classification of Body Fluid Adenocarcinoma Cell Images Based on Hu Moment Invariant Features},
  journal = {BIO Web of Conferences},
  year = {2026},
  volume = {264},
  pages = {01004},
  doi = {10.1051/bioconf/202626401004}
}
Kostenlos starten →