Machine learning for microscopy

4th January 2018

Zeiss Zen Intellesis, a new machine learning capability that enables researchers to perform advanced analysis of their imaging samples across multiple microscopy methods has been launched. The first algorithmic solution introduced by the  platform makes integrated, easy to use, powerful segmentation for 2D and 3D datasets available to the routine microscopy user. The software is available for the company’s full range of optical, confocal, X-ray, electron and ion microscopes.

Dr. Markus Weber, co-CEO of the Zeiss Microscopy Business Group, says, “This is an important first step in our goal to rapidly bring new solutions to our customers through digitalisation. By adding robust new capabilities such as machine learning to our microscopy systems, we are initiating a step-change in the way our customers in industry and academia manage and process vast amounts of imaging data generated by a range of imaging modalities. This enables them to easily and intelligently obtain scalable, quantitative insight.”

Zeiss Zen Intellesis allows users to train machine learning classifications on Zeiss image data sets as well as on any images readable by the software for any Zeiss microscopes. It applies that trained classifier across large, multi-dimensional datasets. It allows for multiple spatially registered datasets, acquired using correlative microscopy and classical image analysis tools, to be used in parallel during classification. It also works with 6D datasets, including multichannel 3D stacks or tile images.

In a geological example, a researcher might study sulfide mineralogical distribution using both coaxial light and backscattered electron imaging modalities. These techniques are first spatially registered before training a classifier, operating on both datasets at the same time. Once trained, this classifier can then be applied rapidly across a large area that is truly representative of subsurface geological heterogeneity, enabling large area mineralogical analysis using quantitative correlative microscopy. 

In addition to geological research that includes petroleum and mining industries, applications are currently in development for life sciences, materials science, metals research, manufacturing and assembly, and routine laboratory microscopy.



Twitter Icon © Setform Limited