CellPathfinder, High Content Analysis Software

The intuitive, easy-to-use interface guides the user throughout the process, including the easy graphing of image data. Yokogawa machine-learning function dramatically increasing its target recognition capability. It analyzes and digitizes complex, high degree-of-difficulty high content imaging experiment data, such as from 3D culture systems and live imaging, using several evaluation systems. The CellPathfinder software is a powerful tool for HCA.

CellPathfinder(R3.04.02) Software Update and release of Deep Learning option. :About Deep learning

You can download trial software. Software download

CallPathfinder Resolves Difficulties

For screening

CellPathfinder resolves screening bottlenecks.

  • A specialized interface for inspecting multiple samples makes image comparison easy, improving efficiency
  • Advanced analysis using AI is possible through simple operation, even for beginners
  • Various graph creation functions and simple image and video creation, reducing hassles at the time of reporting

For cancer research and regenerative medicine screening

CellPathfinder provides leading HCA through proprietary analysis technology.

  • Label-free analysis of samples that you don’t want to stain is possible using Yokogawa’s proprietary image generation technology “CE Bright Field”
  • Newly-developed easy-to-use machine-learning (standard function) makes previously difficult phenomena detection easy
  • Detection of rare events (CTC, etc.) with high speed and high accuracy

 

Applications

Applications

Simple workflow from images to analysis and graphs

1. Display image data

Display image data

・Easy to compare images between wells

 

2. Load and execute analysis protocol

 Load and execute analysis protocol

・Easy-to-understand graphical icons
・Choose a preset template for your analysis

 

3. Gating

Gating

・Specific populations can be extracted by gating the feature value data of recognized objects
・The extracted populations can be analyzed further

 

4. Make the graphs

Make the graphs

・Various graph options to visualize the results
・The link between graph and images enables quick visual check of images by clicking data points

 

5. To examine further details…list the profiles of interesting cells

To examine further details

・Images and numerical data can be collected by clicking cells

Yokogawa technology

Machine-learning

Machine-learning functionality allows for unbiased digitization in experiments evaluated through appearance.
Automated shape recognition can be performed by simply clicking on the shape you wish the software to learn.

Machine-learning

 

CE Bright Field(Contrast-enhanced Bright Field )

By using Yokogawa’s “CE-Bright Field” proprietary image creation technology, two types of images can be output from bright field images. The first is an image resembling a phase-difference image, created from a regular DPC (digital phase contrast) image, and is effective for cytoplasm recognition. The second is an image resembling a fluorescence image, effective for nuclear recognition.

CE Bright Field

Abundant analysis functions

3D analysis

・Analysis of Z-stack images in three-dimensional space. ・The volume and the location of objects in 3D space can be quantified.

3D analysis

 

Label-free Analysis

The recognition of cells without the use of labeling is possible using images created with CE Bright Field technology.
Time, cost and effects on cells due to fluorescent labeling are eliminated from phenotype analysis.

labelfree

 

Image Stitching*1

Tiled images are generated through image stitching and analyzed, allowing for accurate quantification.
Ideal for analysis spanning across fields, such as of spheroids, tissue sections and neurites.

Tiling

 

Manual Region definition*1

Manual region of analysis regions is possible for complex trends that are difficult to identify through automated image processing.
Morphology in the defined regions can be visualized, facilitating analysis.

Manual Region definition
Data provided by Dr. Yasuhito Shimada, Mie University Graduate School of Medicine

 

*1: Coming soon

Benefits of Adopting Deep Learning

Deep learning-based image recognition has gained much attention in recent years.
Yokogawa has also been observing this situation and, by recognizing patterns in images to identify what the images show, we succeeded in dramatically improving the recognition accuracy.

Improve analysis accuracy

Deep Learning improves recognition accuracy, particularly in bright field images.
It has become possible to accurately recognize even low-contrast areas, such as cell borders.
It is also easy to eliminate debris from the image and prevent mis-recognition.

No expertise in image analysis required

Image analysis is achieved by simple, intuitive operations, such as using a pen to color the cells of interest, enclosing them in a rectangle, or selecting the cell groups you want to categorize.

Save time for creating analysis protocols

You don't have to spend much time on creating analysis protocols. By simply selecting several representative patterns, you can obtain better results than the ones by using the conventional Machine Learning methods.

Phenotypic analysis can be conducted without object recognition

The difference between the images can be quantified without recognition of individual objects.
It is possible to conduct phenotypic analysis even when you are unsure what feature quantities are effective but "something is different".

Cell Recognition (Deep Area Finder)

High-accuracy recognition of targeted areas, such as cells and intracellular organelles.
This is effective when the accuracy of existing recognition techniques is not enough, and the expertise in image analysis is not available.

Original image

Original image

Recognition result

Recognition result

Cell Counts (Deep Cell Detector)

Intuitive cell counting
Detect cells without establishing a complicated image analysis protocol. Particularly effective for analyzing high-density cultured cells and bright field analysis.

Original image

Original image

Recognition result

Recognition result

Cell Classification (Deep Image Gate)

Classification of recognized cells into any grouping.
You can intuitively categorize complicated phenotypes without selecting feature quantities.

Classification of cell cycle (G1, Early S, SG2M) using the Fucci system

  • Added 0–6.8μM etoposide to HeLa cells with Fucci
  • 48-hours time lapse over 1 hour intervals at 10x; 488nm and 561nm
6.8uM Etoposide

6.8uM Etoposide

Control

Control

Ratio of cells in each cell cycle at each well.

Ratio of cells in each cell cycle at each well.

EC50/IC50 Calculation (Deep Image Response)

Evaluating whole images to calculate EC50/IC50 from positive/negative controls and concentration data.
Comprehensively analyzes complicated phenotypes without creating protocols for cell recognition and selecting any feature.

 

Dose response curve

Dose response curve

Total Solution - from Imaging to Analysis -

Offering Total Solutions, from Measurement to Analysis Plate transport via robot, measurement using CellVoyager or CQ1, data management using CellLibrarian, and image analysis using CellPathfinder. We offer optimum combinations matched to user’s needs and budgets.

System

Large image: Click

Related products

CV8000 CV8000
  • Ultimate HCA system for high-quality imaging and high-throughput screening with water immersion objectives and multiple cameras
  • Built-in robot pipettor for kinetic assays
CQ1 CQ1
  • Bench top size confocal system
  • Simple operation and automated image acquisition of many sample
  • Live cell imaging
CellLibrarian CellLibrarian
  • Management of image data acquired by CellVoyager and CQ1
  • Through the internet, group members and collaborators can access, visualize and share their image data
  • CellPathfinder runs analysis on data in CellLibrarian

※Data acquired in CellVoyager CV1000 are not supported.
※CellPathfinder system contain the software and the workstation.

System configuration

・Software
・Workstation
・Displays

Specifications of the workstation
Model: Dell Precision
CPU: Intel® Xeon
Memory:128 GB
HDD: System(C:) 4TB Storage, (D:) 4TB
OS: Windows® Microsoft Windows10 IoT Enterprise
GPU: System(C:) Quadro K620 or Quadro P620 (High-performance GPU is not selected.), Quadro RTX5000 (High-performance GPU is selected.)

We post our information to the following SNSs.
Please follow us.

 

Yokogawa Life Science

•Twitter @Yokogawa_LS
•Facebook Yokogawa Life Science
•LinkedIn Yokogawa Life Science

 

Yokogawa's Official Social Media Account List

Social Media Account List

Application Note
Application Note
Application Note
Application Note
Overview:

The CQ1 confocal image acquisition mechanism with the distinctive CSU® unit has a function to sequentially acquire fine cell images along the Z-axis and capture information from the entire thickness of
cells which include heterogenic populations of various cell cycle stages. In addition, saved digital images can be useful for precise observation and analysis of spatial distribution of intracellular molecules.
The CQ1 capability to seamlessly analyze images and obtain data for things such as cell population statistics to individual cell morphology will provide benefits for both basic research and drug discovery
targetingM-cell cycle phase.

Application Note
Overview:

List of Selected Publications : CV8000, CV7000, CV6000

Yokogawa Technical Report
Overview:

We have been developing a prototype of a genomic drug test support system using our CSU confocal scanner. This system administers chemical compounds that serve as potential drug candidates into living cells, which are the most basic components of all living organisms, records the changes in the amount and localization of target molecules inside cells with the CSU confocal scanner and a highly sensitive CCD camera, and processes and quantifies the captured high-resolution image data.

Yokogawa Technical Report
18.6 MB
Yokogawa Technical Report
6.1 MB
Overview:

In this tutorial, we will learn how to perform cell tracking with CellPathfinder through the analysis of test images.

Overview:

In this tutorial, a method for analyzing ramified structure, using CellPathfinder, for the analysis of the vascular endothelial cell angiogenesis function will be explained.

Overview:

In this tutorial, we will learn how to perform time-lapse analysis of objects with little movement using CellPathfinder, through calcium imaging of iPS cell-derived cardiomyocytes.

Overview:

In this tutorial, we will observe the change in number and length of neurites due to nerve growth factor (NGF) stimulation in PC12 cells.

Overview:

In this tutorial, image analysis of collapsing stress fibers will be performed, and concentration-dependence curves will be drawn for quantitative evaluation.

Overview:

In this tutorial, we will identify the cell cycles G1-phase, G2/M-phase, etc. using the intranuclear DNA content.

Overview:

In this tutorial, spheroid diameter and cell (nuclei) count within the spheroid will be analyzed.

Overview:

In this tutorial, a method for analyzing ramified structure, using CellPathfinder, for the analysis of the vascular endothelial cell angiogenesis function will be explained.

Overview:

In this tutorial, using images of zebrafish whose blood vessels are labeled with EGFP, tiling of the images and recognition of blood vessels within an arbitrary region will be explained.

Overview:

Decoding Artificial Intelligence: The brain, the myth, and the legend

Looking for more information on our people, technology and solutions?


Contact Us
Top