Advanced #imageanalysis for #microscopy is accelerating research and development. Analysis of data and systematization are the key to higher efficiency in many fields, and scientific research methods are no exception. We are in the middle of the 4th industrial revolution, with #automation driving many advances, also in science. And science is everywhere. Advanced workflows for your image analysis will allow faster results from your large microscopy data sets without sacrificing quality. In this blog five examples of image analysis for biology research are shortly reviewed. You can get a good picture of how technology contributes to image analysis results and if you want to learn more about a specific example, just click to read a complete case study.
Volume electron microscopy tends to generate images dense with information. To analyze all the cellular and sub-cellular structures in minute detail, automated image analysis powered by deep learning is called for. An AI model was trained using APEER by ZEISS and then imported into arivis for comprehensive 3D analysis. Sample provided by Anna Steyer and Yannick Schwab, EMBL, Heidelberg, Germany.
To study the role of Wnt Signaling in organoid formation, researchers created an automated pipeline to segment images of organoids, differentiating not only between the lumen and the organoid’s outer layer but also between cell bodies in the organoid cell layer. Statistically relevant experiments can be conducted by scaling up this AI-powered image analysis strategy.
This case study demonstrates an automated image analysis workflow that classifies nuclei according to size, signal intensity and DNA damage foci. Advanced technology lies at the basis of the DNA damage analysis pipeline, which is easily scalable for high-content screening for genotoxicity.
Vesicles in a cell model were tagged with two vesicular transport markers and observed over time. The images were acquired with the award-winning ZEISS Lattice Lightsheet 7 and analyzed using arivis software. The image analysis pipeline included 3 steps: denoising, Waterdshed-based segmentation and object tracking.
Correlative data is required for meaningful measurement and screening for cytoskeleton regulation. An automated and scalable image analysis pipeline was set up to include a 3-step segmentation of nuclei, cell area and cell body to ensure correct cell identification.
Dr. Lorna Young of the Zech Lab in the Department of Molecular Physiology & Cell Signaling at the University of Liverpool
This blog post provides a peek at five (5) biology research case studies in which advanced image analysis solutions were used to enable complex experiments for accelerated scientific results.
Contact us to learn more about image segmentation powered by AI models and how to automate your image analysis pipelines.
An easy-to-use software solution from ZEISS for automated AI-driven image analysis in the cloud. The no-code interface allows any researcher to train and customize AI-based image segmentation models, for reproducible and reliable results.
The multi-dimensional image analysis platform from ZEISS. Its agile concept allows any researcher to put together push-button solutions for specific image analysis needs. Pipeline execution can be scaled up for high-throughput analysis using on-premises or cloud servers. The immersive VR environment allows productive and collaborative workflows for research and education.