| Summary: | Background: Colony morphology (size, color, edge, elevation, and texture), as observed on culture media, can be used to visually discriminate different microorganisms. Methods: This work introduces a hybrid method that combines standard pre-trained CNN keras models and classical machine-learning models for supporting colonies discrimination, developed in Petri-plates. In order to test and validate the system, images of three bacterial species (<i>Escherichia coli</i>, <i>Pseudomonas aeruginosa</i>, and <i>Staphylococcus aureus</i>) cultured in Petri plates were used. Results: The system demonstrated the following Accuracy discrimination rates between pairs of study groups: 92% for <i>Pseudomonas aeruginosa</i> vs. <i>Staphylococcus aureus</i>, 91% for <i>Escherichia coli</i> vs. <i>Staphylococcus aureus</i> and 84% <i>Escherichia coli</i> vs. <i>Pseudomonas aeruginosa</i>. Conclusions: These results show that combining deep-learning models with classical machine-learning models can help to discriminate bacteria colonies with good accuracy ratios.
|
|---|