Related Experiment Video
Updated: Mar 29, 2026
Use of Image Cytometry for Quantification of Pathogenic Fungi in Association with Host Cells
Published on: June 19, 2013
Machine Learning-Assisted Classification of Pathogenic Yeasts Using Laser Light Scattering and Conventional
Xiaoxuan Liu1, Shamanth Shankarnarayan2, Zexi Cheng1
1Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T6G 1H9, Canada.
Abstract:
Yeast infections are a major concern in clinical settings, and several known species are recognized for their antifungal drug resistance, especially the multidrug-resistant pathogen Candidozyma auris. It is of increasing importance to identify pathogenic yeasts to improve treatment outcomes. We present a technique to identify these yeast pathogens using machine learning with a neural network (DenseNet-201) on images obtained from laser light scattering and conventional microscopy. We performed the binary classification of seven species of pathogenic yeast based on their light scattering patterns and their microscopy images. We achieved an average classification accuracy of 95.3% for light scattering patterns and 96.6% for microscopy images of the yeast cells. We also demonstrate high classification accuracy when isolating Candidozyma auris images from all other species combined, at an average of 95.1% for light scattering patterns and 96.7% for microscopy images. The high average classification accuracies suggest that both light scattering and microscopy image data can be combined with machine learning models to classify pathogenic yeasts.
Insights
Accurately identifying pathogenic yeasts like Candida auris is crucial for effective treatment. This study uses machine learning on laser light scattering and microscopy images, achieving high accuracy in classifying yeast species.
Area of Science:
- Medical Mycology
- Computational Biology
- Biophotonics
Background:
- Antifungal drug resistance in pathogenic yeasts, particularly multidrug-resistant Candida auris, poses significant clinical challenges.
- Accurate and rapid identification of yeast pathogens is essential for improving patient treatment outcomes and infection control.
Purpose of the Study:
- To develop and evaluate a machine learning-based technique for identifying pathogenic yeast species.
- To assess the efficacy of using laser light scattering patterns and conventional microscopy images for yeast classification.
Main Methods:
- A neural network model (DenseNet-201) was employed for image analysis.
- Binary classification was performed on seven pathogenic yeast species using data from laser light scattering and microscopy images.
- Performance was evaluated by calculating classification accuracy for individual species and for isolating Candida auris.
Main Results:
- High average classification accuracy was achieved: 95.3% for light scattering patterns and 96.6% for microscopy images.
- Excellent accuracy was demonstrated in isolating Candida auris from other species, with averages of 95.1% (light scattering) and 96.7% (microscopy).
Conclusions:
- Machine learning models, when combined with laser light scattering and microscopy image data, show significant potential for accurate pathogenic yeast classification.
- This approach offers a promising method for identifying key yeast pathogens, aiding in clinical diagnostics and treatment strategies.
Related Concept Videos
01:28Methods of Classification and Identification
01:16Confocal Fluorescence Microscopy