Related Experiment Video
Updated: Feb 26, 2026
08:56
Visual Detection of Multiple Nucleic Acids in a Capillary Array
Published on: November 15, 2017
7.8K
You Only Look Once (YOLO) based machine learning algorithm for real-time detection of loop-mediated isothermal
Biniyam Mezgebo1, Ryan Chaffee1, L Ricardo Castellanos1
1Department of Biomedical Sciences, Ross University School of Veterinary Medicine, Basseterre, Saint Kitts and Nevis.
Plos One
|February 24, 2026
Summary
Automated classification of Loop-mediated isothermal amplification (LAMP) results using machine learning (ML) and YOLOv8 image analysis significantly improves accuracy. This approach enhances real-time molecular diagnostics by reducing errors in visual interpretation.
Area of Science:
- Molecular Biology
- Biotechnology
- Artificial Intelligence
Background:
- Loop-mediated isothermal amplification (LAMP) is a rapid, affordable DNA amplification technique.
- Visual interpretation of LAMP results is subjective and prone to errors, impacting diagnostic accuracy.
Purpose of the Study:
- To develop an automated machine learning (ML) approach for classifying LAMP results using digital images.
- To enhance the accuracy and reliability of LAMP-based molecular diagnostics.
Main Methods:
- Utilized You Only Look Once (YOLOv8), an object detection algorithm, for automated tube localization and classification in LAMP images.
- Trained and tested the YOLOv8 model on digital images of LAMP assays.
Main Results:
- The ML model achieved 97.4% overall accuracy in classifying LAMP images as positive or negative.
- High precision (95.3%) and recall (96.8%) for positive cases, and strong performance for negative cases (93.3% precision, 95.8% recall).
Conclusions:
- The proposed ML approach offers a robust solution for automated, objective LAMP result interpretation.
- Demonstrated platform suitability for real-time molecular testing, improving assay performance and reducing diagnostic errors.
