Machine Learning

Machine learning techniques enable supervised and unsupervised feature selection and clustering of highly multi-parametric data sets. We offer a range of easy-to-use machine learning tools for its Harmony® high content imaging and analysis software and Signals Image Artist™ image analysis and data management platform.

The PhenoLOGIC™ plug-in provides supervised machine learning for Harmony and Signals Image Artist software platforms.

PhenoLOGIC enables biologists using Harmony to train the software to develop the image analysis algorithms. While other systems may require an image analysis expert to create an algorithm, PhenoLOGIC uses proprietary machine-learning technology to make it easy for you to do it on your own. Using a learn-by-example approach, images can be segmented with just a few clicks of the mouse and then tailored algorithms developed quickly and easily.

The PhenoLOGIC machine-learning option enables our Harmony high content analysis software to recognize different cell populations and regions using a simple learn-by-example approach. Just click on a few cells of each class to teach the software what it is looking for, and PhenoLOGIC will do the rest. Image analysis that might have taken hours can be completed in a matter of minutes.

Using advanced proprietary machine-learning technology, PhenoLOGIC sets parameters for optimal image segmentation and cell classification. The software combines the most meaningful parameters, whether it's two, three, four or more, to achieve accurate classification of cells. The result is highly robust and statistically relevant results.