EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid MIL Architecture for Multi-Class Classification of Bacterial Microscopic Images

Aisulu Ismailova, Gulbanu Yessenbayeva, Kuanysh Kadirkulov, Raushan Moldasheva, Elmira Eldarova, Gulnaz Zhilkishbayeva, Shynar Kodanova, Shynar Yelezhanova, Valentina Makhatova, Alexander Nedzved

Computers · 10.03.2026 · 15 (3) · 180

DOI: 10.3390/computers15030180 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 10.03.2026. Verfasst von Aisulu Ismailova und 9 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper addresses the problem of multi-class classification of bacterial microscopic images using a rigorous experimental protocol designed to prevent information leakage and improve performance. The dataset consists of 2034 images representing 33 taxa, organized by class. Data integrity checks confirmed the absence of corrupted or unreadable files. To formalize image characteristics and ensure quality control, indirect geometric and textural features were calculated, including minimum frame size, brightness statistics (mean and standard deviation), Shannon entropy, Laplace variance, and Sobel gradient energy. Quality checks revealed a small proportion of images with extreme brightness (2.5074%), while no samples with critically low sharpness according to the selected criteria were detected. Statistical analysis of interclass differences using the Kruskal–Wallis test with multiple comparison correction demonstrated the high discriminatory power of texture features, specifically gradient energy (ε2 = 0.819987) and Laplace variance (ε2 = 0.709904). Feature correlations were consistent with their physical interpretation, revealing a strong positive relationship between sharpness and gradient energy. Principal component analysis confirmed a strong structural pattern, with the first two components explaining 75.5766% of the total variance. For a unified comparison, classical machine learning, transfer learning, and modern deep architectures were evaluated within a single protocol.

Förderung

  • Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan

Zitieren

APA

Ismailova, A., Yessenbayeva, G., Kadirkulov, K., Moldasheva, R., Eldarova, E., Zhilkishbayeva, G., Kodanova, S., Yelezhanova, S., Makhatova, V., & Nedzved, A. (2026). A Hybrid MIL Architecture for Multi-Class Classification of Bacterial Microscopic Images. Computers, 15(3), 180. https://doi.org/10.3390/computers15030180

Vancouver

Ismailova A, Yessenbayeva G, Kadirkulov K, Moldasheva R, Eldarova E, Zhilkishbayeva G, et al. A Hybrid MIL Architecture for Multi-Class Classification of Bacterial Microscopic Images. Computers. 2026;15(3):180. doi:10.3390/computers15030180

BibTeX
@article{Ismailova2026,
  author = {Ismailova, Aisulu and Yessenbayeva, Gulbanu and Kadirkulov, Kuanysh and Moldasheva, Raushan and Eldarova, Elmira and Zhilkishbayeva, Gulnaz and Kodanova, Shynar and Yelezhanova, Shynar and Makhatova, Valentina and Nedzved, Alexander},
  title = {A Hybrid MIL Architecture for Multi-Class Classification of Bacterial Microscopic Images},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {3},
  pages = {180},
  doi = {10.3390/computers15030180}
}
Kostenlos starten →