Using image processing and automated classification models to classify microscopic gram stain images

Abstract

Background and Objective: Fast and correct classification of bacterial samples are important for accurate diagnostics and treatment. Manual microscopic interpretation of Gram stain samples is both time consuming and operator dependent. The aim of this study was to investigate the potential for developing an automated algorithm for the classification of microscopic Gram stain images. Methods: We developed and tested two algorithms (using image processing an Casual Probabilistic Network (CPN) and a Random Forest (RF) classification) for the automated classification of Gram stain images. A dataset of 660 images including 33 microbial species (32 bacteria and one fungus) was split into training, validation, and test sets. The algorithms were evaluated based on their ability to correctly classify samples and general characteristics such as aggregation and morphology. Results: The CPN correctly classified 633/792 images to achieve an overall accuracy of 80% compared to the RF which correctly classified 782/792 images to achieve an overall accuracy of 99% (p < 0.001). The CPN performed well when distinguishing between GN and GP, with an accuracy of 95% (731/768). The RF also performed well in distinguishing between GN and GP, achieving an accuracy of 99% (767/768) (p < 0.001). Conclusions: The findings from this study show promising results regarding the potential for an automated algorithm for the classification of microscopic Gram stain images.

Keywords

• Gram stain
• Blood culture
• Machine learning
• Deep learning
• Automated microscopy
• Analytics