Linux

ZEN and APEER – Open Ecosystem for integrated Machine-Learning Workflows

Open ecosystem for integrated machine-learning workflows to train and use machine-learning models for image processing and image analysis inside the ZEN software or on the APEER cloud-based platform

Highlights ZEN

• Simple User Interface for Labeling and Training
• Engineered Features Sets and Deep Feature Extraction + Random Forrest for Semantic Segmentation
• Object Classification workflows
• Probability Thresholds and Conditional Random Fields
• Import your own trained models as *.czann files (see: czmodel · PyPI)
• Import "AIModel Containes" from arivis AI for advanced Instance Segmentation
• Integration into ZEN Measurement Framework
• Support for Multi-dimensional Datasets and Tile Images
• open and standardized format to store trained models

ZEN Intellesis Segmentation

ZEN Intellesis - Pretrained Networks

Intellesis Object Classification

Highlights Aarivis AI

• Web-based tool to label datasets to train Deep Neural Networks
• Fully automated hyper-parameter tuning
• Export of trained models for semantic segmentation and AIModelContainer for Instance Segmentation

Annotation Tool

R wrapper around the OMERO Java Gateway, to enable access to OMERO via R using rJava

OpenImadis stands for Open Image Discovery: A platform for Image Life Cycle Management. It was previously called CID iManage (for Curie Image Database).

No image data conversions, no duplication.

- Uploads data to a secure server in the original format

- Unique id for data

Supports sharing and collaboration with access control

- Allows users to upload, view, update or download data based on their access privileges

Supports multiple ways of attaching meta-information

- Annotations, comments and file attachments

-Analysis results as query-able visual objects

Supports Archiving (data moving to another long-term storage but still searchable)

Facilitates custom visualization and analysis

- Access data from preferred analysis and visualization tools

- Access relevant bits of data to build efficient web and mobile application

Facilitate easy access to analysis and visualization applications hosted on other servers

- Run analysis on dedicated compute clusters

- Access applications hosted and published by other users

Highly Scalable

- Supports on-the-fly addition of server nodes to scale concurrent usage

This one example workflow from the Cell Profiler(CP)  Examples . CP is commonly used to count cells or other objects as well as percent-positives, by measuring the per-cell staining intensity. This pipeline shows how to do both of these tasks, and demonstrates how various modules may be used to accomplish the same result. 

In a few words, it used the IdentifyPrimaryObject module of CellProfiler to detect nuclei from a channel (e.g DAPI), then again the same module on another channel to detect another probe (e.g some particular histone)  .

Then objects (nuclei) are related to the second object (Histone), to create a parent child-relation ship: where nuclei can have histone has child. Nuclei are then filtered according to the property of having histone (positive) or not having histone (negtiveobject) related to them.  If needed, nuclei can be expanded in order to include touching object rather than object inside only.

The percentage of positive nuclei vs total number of nuclei can then be computed using the CalculateMath Module.

This workflow can be ran with data from 3D-SIM showing the centrosomes in order to compare the distribution of diameters of rings (or toroids) of different proteins from the centrioles or the peri centriolar material. It aims to reproduce the results of the Nature Cell Biology Paper Subdiffraction imaging of centrosomes reveals higher-order organizational features of pericentriolar material  from the same data set but with a different analysis method.

It is slightly different from the methods described in the paper itself, where the method was to work on a maximum intensity projection of a 3D-SIM stack, and then to fit circle to the centrioles to estimate the diameters of the toroids.

In this workflow, the images are read from the IDR , then process by thresholding (Maximum entropy auto thresholding with Image J), and processed by Analyze Particles  with different measurement sets, including the bouding box. Then the analysis of diameters and the statistical test are performed using R. All the code and data sets are available, and in the case of this paper have shown a layered organisation of the proteins.