Loading...
 
Skip to main content
Scientific Volume Imaging B.V.

Scientific Volume Imaging

Deconvolution - Visualization - Analysis


™Huygens Object Analyzer

Object segmentation and analysis - Combine Artificial Intelligence with classic methods easily.

Object Analysis with and without AI


Huygens’ Object Analyzer combines comprehensive object-based statistics with advanced segmentation tools, including AI-driven options. Easily define regions of interest, select reference objects, and render in 3D—all in one intuitive interface. No training datasets needed!.
The quality of object segmentation relies on factors such as background signal, noise, object heterogeneity, staining inconsistencies and spatial overlap between different objects, which may require different segmentation approaches. The power of Huygens' Object Analyzer is the possibility to combine methods for classical segmentation such as thresholding and watershed, with options for deep-learning tools like Cellpose1, StarDist2, and Napari3, and interactive Artificial Intelligence (AI)-based segmentation using Meta’s Segment Anything Model 24. Our AI-based segmentation allows you to fully automatically segment objects or to extract objects with one-click from complex data, streamlining the process and improving analysis accuracy. Curious about other Huygens' AI solutions? See here! The Object Analyzer is available as an Advanced and Compact version which features are listed under the tab at the bottom page.

Huygens' segmentation
Raw data
Combining strengths of different (AI) segmentation methods Formation of blood vessels by HUVEC primary cells. The endothelial cells were segmented by classic thresholding (in red). Areas within the endothelial linings, i.e. the preliminary blood vessels, were segmented by Huygens AI segmentation, allowing for measurements on, for example, vessel diameter. Courtesy of Rogério Gomes dos Santos, PhD, Office of Research and Economic Development, Lousiana State University, Baton Rouge, USA.

Testimonials

We found Huygens Object Analyzer to be the most robust and accurate solution for 3D colocalisation analysis (intracellular vesicles) compared to other software. Dr. Neftali Flores Rodriguez, Sydney Microscopy & Microanalysis (SMM), University of Sydney, Australia.
The Object Analyser has been incredibly helpful, the thresholding is considerably better than anything I can do in Fiji.Dr. Joshua Reyniers, Biochemistry, University of Sussex, Brighton, United Kingdom.
We have lots of images spectacularly deconvolved with Huygens. Object Analyzer works with these images super efficiently.Dr. Jakub Kochan, Cell Biochemistry, Jagiellonian University, Krakow, Poland.

Segmentation options

The Object Analyzer offers multiple segmentation methods, each best suitable for different types of objects.

Seed & Threshold


A classic approach for segmenting features is to apply a threshold criterion where only pixels with intensities above the threshold are considered. Adjacent pixels can then be grouped together (labeled) forming a distinct object, More.

Courtesy of Dr. Barna Dudok MSc., Hungarian Academy of Sciences, Hungary.

 Watershed

Watershed
Threshold & Seed


When objects are very close to each other, the watershed segmentation method provides the solution to separate objects which else would merge in one object. More.


Courtesy of Mariette van der Corput, Erasmus MC, Rotterdam, The Netherlands.

AI segmentation


Huygens' AI segmentation tool allows segmentation of objects in close proximity to eachother, when the Threshold and the Watershed start to struggle. The AI tool allows both fully automatic as well as AI guided manual segmentation. More.


Courtesy of Dr. Nicolas Fête, Laboratory of Stem Cells Dynamics, Swiss Federal Institute of Technology of Lausanne, Switzerland.

Import masks from other software


Masks generated by other AI-based segmentation tools such as Cellpose1 or Stardist2 can be seamlessly used as labels for object segmentation in the Object Analyzer, enabling efficient and accurate analysis of complex datasets.


Courtesy of Dr. Nicolas Fête, Laboratory of Stem Cells Dynamics, Swiss Federal Institute of Technology of Lausanne, Switzerland.


HeLa TOM20 MeGFP Decon Rotated

Interactive Visualisation


After object segmentation, users can use intuitive tools to identify and isolate key components, streamlining the analysis process. The interactive visualization lets you explore the objects in a dynamic, user-friendly environment. This seamless workflow enables users to make informed decisions with clarity and precision. The segmented objects are visualized using high-quality continuous Iso Surface Ray Tracing, which lets you rotate, zoom, and manipulate the visualized data, enabling a deeper understanding of the objects' structure and properties.

Huygens' interactive 2D and 3D Visualization:
3D visualizaton of mitochondria, different colors indicate the mitochondrial structures are not attached to each other. Visualized on deconvolved data with Huygens' Object Analyzer. Courtesy of Dr. Rainer Kurre. Integrated Bioimaging Facility iBiOs. Center for Cellular Nanoanalytics, Osnabrück University, Osnabrück, Germany.

Built-in Statistics


In addition to easy segmentation and interactive visualisation, built-in statistics provide immediate insights into the segmented objects. These integrated tools automatically calculate and display key metrics such as volumes, surface areas, distances, and other relevant properties, all without the need for external software. With just a few clicks, users can access detailed statistical analysis, helping to quickly assess the characteristics of each segment. This feature streamlines the process, making it easier to interpret complex data and make data-driven decisions efficiently. The statistics can be exported for use in spreadsheets or Matlab.

Statistical Analysis Post-Segmentation with Huygens: After segmentation of your objects Huygens offers a broad range of preset statistics, in this case the distances between telomeres in fetal brain cells was measured. Analysis was performed on deconvolved data. Courtesy of Mariette van der Corput, Erasmus MC, Rotterdam, The Netherlands.
Statistics
ROI

Regions Of Interest


Using the Region of Interest (ROI) option, users can select a specific set of objects for analysis, or to designate them as anchors, reference points used for spatial and morphological comparisons. Once an anchor is set, the tool provides detailed quantitative data such as the distance to other objects, spatial relationships, and differences in morphology including volumes and surface areas. Additionally, users can define ROIs by simply drawing a circle around a desired area. This allows for focused analysis on selected clusters or individual objects, streamlining tasks such as neighborhood analysis, density measurements, or targeted feature extraction.

Setting a Region Of Interest Distance between lymphocytes measured by setting of a Region Of Interest within the Object Analyzer. Analysis on deconvolved data. Courtesy of Georgios Chamilos, FORTH Institute of Molecular Biology and Biotechnology, Crete, Greece.

Track Analyzer


The Track Analyzer, integrated into the Object Analyzer, enables users to seamlessly analyse results from the Object Tracker. This allows extraction and quantification of a broad range of parameters, such as the distance between objects, morphological characteristics, and dynamic migration patterns over time.

Analysing objects in a time series Distance between a lymphocyte and fungus measured in a time series. Analysis on deconvolved data. Courtesy of Georgios Chamilos, FORTH Institute of Molecular Biology and Biotechnology, Crete, Greece.


Track Analyzer

Experience how easy it is to automatically segment and analyze images with Huygens' Object Analyzer Compact. Use intuitive segmentation tools, Anchor and ROI selections, and numerous filtering options to fine-tune your analysis. The Object Analyzer Advanced allows you to design analysis pipelines, perform batch analysis, and offers more advanced analysis tools such as cluster analysis.

Features included in both Object Analyzer Compact and Advanced:

Obtain both visual and quantitative information for all kinds of objects.
Automatically segment your data, or use custom settings.
Upload results from AI-based segmentation tools such as Cellpose, Stardist and MicroSAM.
Automatic AI segmentation, based on Meta's powerful SAM2, efficiently segments objects like organelles, densely clustered cells, and nuclei.
AI-guided manual segmentation provides a targeted one-click approach for more complex images, such as those containing numerous structures or background elements.
AI-powered 3D segmentation accurately identifies and separates complex structures within 3D images.
Easily adjust the AI segmentation with easy to use tools and powerful visualisation.
Watershed, cluster-based analysis.
Full analysis of 3D/Multi-channel/Time series with a single click.
Measure/count any object instantly.
Perform Object Colocalization.
Measure intensities, geometry, and more.
Intuitively select Anchors (reference objects) and Regions Of Interest.
Measure proximity between objects in the same or other channel.
Refine your analysis with object filter options.
Color objects based on their properties.
Export your object statistics for use in spreadsheets or Matlab.
Quickly get started with the Object Analyzer using the built-in tutorials.

Features exclusive to the Object Analyzer Advanced:

Create and edit templates with the Object Analysis Workflow Designer.
Set up batch analysis in the Workflow Processor.
Use advanced analysis tools (Cluster analysis, shrink wrap, surface-to-surface distances).
Use a custom selection to combine analysis parameters.
Segment, track* and analyze time series.

* Also requires an Object Tracking license.

References

1. Stringer C, Wang T, Michaelos M, Pachitariu M. Cellpose: a generalist algorithm for cellular segmentation. Nat Methods. 2021 Jan;18(1):100-106. doi: 10.1038/s41592-020-01018-x. Epub 2020 Dec 14. PMID: 33318659.
2. Schmidt, U., Weigert, M., Broaddus, C., Myers, G. (2018). Cell Detection with Star-Convex Polygons. In: Frangi, A., Schnabel, J., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds) Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. MICCAI 2018. Lecture Notes in Computer Science(), vol 11071. Springer, Cham. doi.org/10.1007/978-3-030-00934-2_30
3. Napari contributors (2019). napari: a multi-dimensional image viewer for python. doi:10.5281/zenodo.3555620%%% 4. Ravi N., Gabeur V., Hu Y., Hu R., Ryali C., Ma T., Khedr H., Rädle R., Rolland C., Gustafson L., Mintun E., Pan J., Vasudev Alwala K., Carion N., Wu C., Girshick R., Dollár P., Feichtenhofer C. SAM 2: Segment Anything in Images and Videos. https://ai.meta.com/research/publications/sam-2-segment-anything-in-images-and-videos/