An AI-directed analytical study on the optical transmission microscopic images of Pseudomonas aeruginosa in planktonic and biofilm states
2024

AI Study on Pseudomonas aeruginosa Biofilms

publication 10 minutes Evidence: high

Author Information

Author(s): Sengupta Bidisha, Alrubayan Mousa, Wang Yibin, Mallet Esther, Torres Angel, Solis Ravyn, Wang Haifeng, Pradhan Prabhakar

Primary Institution: Cornell University

Hypothesis

Can a deep learning-based AI model accurately detect biofilms produced by Pseudomonas aeruginosa?

Conclusion

The study demonstrates that an AI model can efficiently detect different degrees of biofilm structures with high accuracy.

Supporting Evidence

  • The AI model was designed using large-volume bright field images of bacterial biofilms.
  • Aptamer DNA templated silver nanocluster was used to prevent biofilm formation.
  • Different degrees of biofilm structures can be detected using ResNet18 and ResNet34 backbones.

Takeaway

Scientists used a computer program to help find and understand sticky germs that can cause problems in health and food. They found that the program works really well!

Methodology

The study used a deep learning AI model with U-Net and ResNet enhancements to analyze images of bacterial biofilms.

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication