Related Experiment Video
Updated: Nov 7, 2025
08:08
Automated Measurement of Cryptococcal Species Polysaccharide Capsule and Cell Body
Published on: January 11, 2018
7.6K
Analysis of the Nosema Cells Identification for Microscopic Images.
Soumaya Dghim1, Carlos M Travieso-González1, Radim Burget2
1Signals and Communications Department (DSC), Institute for Technological Development and Innovation in Communications (IDeTIC), University of Las Palmas de Gran Canaria (ULPGC), Las Palmas de Gran Canaria, 35001 Canary Islands, Spain.
Sensors (Basel, Switzerland)
|April 30, 2021
Summary
This study developed automated methods for detecting Nosema disease cells in microscopic images. The VGG-16 deep learning model achieved 96.25% accuracy, offering a robust solution for this economically significant bee disease.
Area of Science:
- Agricultural Science
- Computer Science
- Veterinary Medicine
Background:
- Nosema disease poses a significant economic threat to bee populations.
- Accurate and efficient detection of Nosema cells is crucial for disease management.
Purpose of the Study:
- To develop and evaluate automated methods for recognizing and identifying Nosema cells in microscopic images.
- To compare the performance of traditional machine learning with deep learning approaches for Nosema detection.
Main Methods:
- Image processing techniques were used for feature extraction from microscopic images.
- Machine learning models, including Artificial Neural Networks (ANN) and Support Vector Machines (SVM), were applied.
- Deep learning models, specifically Convolutional Neural Networks (CNN) and transfer learning (AlexNet, VGG-16, VGG-19), were investigated.
Main Results:
- The VGG-16 pre-trained neural network achieved the highest accuracy of 96.25% in identifying Nosema cells.
- Deep learning approaches, particularly transfer learning, demonstrated superior performance compared to traditional machine learning methods.
- The study successfully differentiated Nosema cells from other objects in microscopic images.
Conclusions:
- Automated detection of Nosema disease using deep learning, especially VGG-16, is highly accurate and effective.
- These computational approaches offer a robust solution for managing Nosema disease, mitigating economic losses in beekeeping.
- The findings highlight the potential of advanced image processing and machine learning in veterinary diagnostics.
