Related Experiment Video
Updated: Aug 29, 2025
05:57
In Vitro Assay of Bacterial Adhesion onto Mammalian Epithelial Cells
Published on: May 16, 2011
25.9K
A simple AI-enabled method for quantifying bacterial adhesion on dental materials.
Hao Ding1, Yunzhen Yang1, Xin Li2,3
1Dental Materials Science, Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong Kong, Pokfulam, Hong Kong.
Biomaterial Investigations in Dentistry
|September 9, 2022
Summary
A new artificial intelligence (AI) method directly quantifies bacterial adhesion on dental materials using Scanning Electron Microscope (SEM) images. This AI approach offers a faster, cheaper, and more accurate alternative to traditional methods for dental material research.
Area of Science:
- Dental Materials Science
- Microbiology
- Artificial Intelligence in Imaging
Background:
- Bacterial adhesion to dental materials is crucial for material performance and oral health.
- Current methods for quantifying bacterial adhesion are indirect and provide estimated results.
- A direct, accurate, and efficient method for measuring bacterial adhesion is needed.
Purpose of the Study:
- To develop and validate a simple artificial intelligence (AI) method for direct quantification of initial bacterial adhesion on dental materials.
- To utilize Scanning Electron Microscope (SEM) images for AI-driven bacterial adhesion analysis.
- To compare the AI method with existing techniques for bacterial quantification.
Main Methods:
- Dental zirconia and PMMA nano-structured surfaces were inoculated with specific oral bacteria (Porphyromonas gingivalis, Fusobacterium nucleatum, Streptococcus mutans).
- Bacterial adhesion was evaluated using SEM images at various time points.
- Image pre-processing and bacterial area measurement were performed using Fiji software with a machine learning plugin.
- The AI method was validated against the Confocal Laser Scanning Microscopy (CLSM) live/dead staining method.
Main Results:
- A strong linear correlation (r² > 0.98) was observed between the adhered bacterial area and time for P. gingivalis and F. nucleatum on zirconia.
- The AI method showed strong positive association (Pearson's correlation coefficient r > 0.9) with the CLSM method for S. mutans on PMMA.
- The AI method demonstrated comparability with established bacterial quantification techniques.
Conclusions:
- SEM images can be directly analyzed for bacterial adhesion quantification using a simple AI-enabled method.
- The proposed AI method offers a direct, efficient, and potentially more accurate approach to studying bacterial adhesion on dental materials.
- This AI method reduces time, cost, and labor compared to traditional bacterial counting techniques.
