Rapid bacteria identification using structured illumination microscopy and machine learning

Abstract

Traditionally, optical microscopy is used to visualize the morphological features of pathogenic bacteria, of which the features are further used for the detection and identification of the bacteria. However, due to the resolution limitation of conventional optical microscopy as well as the lack of standard pattern library for bacteria identification, the effectiveness of this optical microscopy-based method is limited. Here, we reported a pilot study on a combined use of Structured Illumination Microscopy (SIM) with machine learning for rapid bacteria identification. After applying machine learning to the SIM image datasets from three model bacteria (including Escherichia coli, Mycobacterium smegmatis, and Pseudomonas aeruginosa), we obtained a classification accuracy of up to 98%. This study points out a promising possibility for rapid bacterial identification by morphological features.

Keywords

• Structured illumination microscopy
• bacterial classification
• principal component analysis
• support vector machine
• random forest