arivis Vision4D 3.5 Release Notes August 2021

Summary of important changes in arivis Vision4D 3.5 which was released 2nd Aug 2021.

Top new features:

1. New Object Styles to define object's color, transparency, material, and representation by tag
2. Analysis Home screen with better access to sample pipelines
3. Machine Learning Object Classification and performance improvements in all ML tools (incl. GPU/CUDA support)
4. reworked Compartments operation supporting parent-child relationship with subjects within a certain distance and fast feature definition per level of hierarchy
5. analysis pipeline operations implemented as Python script
6. arivis VisionHub integration

General:

1. "What's new" intro screen
2. arivis VisionHub integration (up and download of pipelines, images and objects from/to VisionHub)
3. significantly faster SIS save (structural modifications)
4. Fix: incorrect scalebar length at certain pixel size ratios
5. Windows 7 is no longer supported

Import & Data Handling:

1. better support for import of HCA well plate datasets:
   1. Zeiss CZI well plate datasets
   2. GE XDCE datasets
   3. Yokogawa MLF and MMD datasets
2. support for import of ND2 float data
3. improved Nikon ND2 import using the latest ND2Read SDK
4. better support for importing Leica LEI time series
5. Olympus import using the latest IDAL library
6. improved edit support for tiles in manual mode of the Tile Sorter
7. much faster handling of a very large number of files to import
8. Fix: rare issue where old metadata prevented SIS from opening
9. Fix: Tile Sorter showing projection will update thumbnail after changing z-shift of a tile

4D Viewer:

1. New glass material style for object visualization
2. improved and simplified lightings settings
3. unified clipping planes front/back orientation
4. 360° video export in 4K resolution
5. Fix: end marker for 3D polyline objects
6. Fix: prevent wrong positioned objects created with the Drop Objects tool in MIP view mode

Analysis:

1. Improved Import Document Objects operation
2. Analysis Home Screen provides a well-organized starting point for your analyses
3. reworked input/output handling with support for multiple outputs from one operation
4. Tracking provides secondary output for tracked segments and optional output for non tracked
5. Seeded Region Growing provides optional output for the seeds
6. reworked and redesigned Compartments operation
7. Compartments operation supports creating parent-child relationships with subjects within a certain distance
8. Compartments operation may classify objects as inside, intersecting, or proximal to the reference
9. Compartments operation provide optional outputs for different relation subgroups
10. The Compartments operation now supports the easy creation of Custom Features (e.g. count of children or mean intensity) for contained children
11. Combine Outputs operation supports more than two inputs
12. Machine Learning Object Classification analysis operation with different classes as separate outputs
13. Visualize the disk location for temporary analysis files in the status bar
14. Warning if the free disk space might be exceeded on running an analysis pipeline
15. changed: No auto-select of a different input channel if the configured one is missing (warning for existing pipelines not fitting the data)
16. A new analysis pipeline operations to use a Python script to
    
    • • run a voxel operation or to
      • create or to
      • Modify segments

Performance:

1. improved: speed up segment creation for 2D data by avoiding surface precalculations
2. much increased performance when creating or modifying complex segment structures

Batch analysis:

1. allow to switch to batch analysis with the pipeline just configured
2. remember last batch analysis output folder
3. improved batch analysis configuration guidance
4. changed: use all image sets by default in batch analysis when adding new files
5. Fix: avoid potential problems working with a large number of objects (>10 million)
6. Fix: prevent unintentional jumping of the view during execution of the analysis pipeline step by step
7. Fix: preview for the Region Growing operation
8. Fix: potential problem with inconsistent error messages
9. Fix: avoid potential hang of the Membrane Detection operation
10. Fix: bug in Image Math which could cause strange pattern
11. Fix: potential crash with the ML segmenter
12. Fix: prevent missing entries in the Export Object Features operation (edge cases)
13. Fix: problem with saving the pipeline if some special Custom Compute Features are involved

Machine Learning:

1. New Machine Learning Object Classification Trainer
2. Run Machine Learning Object Classification to classify visible objects (no Analysis Pipeline needed)
3. ML Trainer (Image) allows to paint into a class other than the one displayed
4. ML Trainer (Image) - warning about 3D-features preview inaccuracy
5. ML Segmentation provides classes as separate outputs in the analysis pipeline
6. Machine Learning image operations benefit from CUDA hardware acceleration (if available)
7. Much improved Machine Learning (Image) performance

Objects:

1. New Object Styles allow to define the visual style of objects more easily including color, opacity, material and representation (surface, centroid or approximation)
2. Setting of objects styles by tag with the new Object Styles Dialog
3. Support for individual transparencies, colors and display type for single objects
4. Option to ignore scope offsets while copying objects
5. Tags are shown per image set
6. Fix: rare problem with the magic wand mode of the Manual Track tool
7. Fix: show color by time or by segment mode indication in the object table
8. Fix: prevent unexpected disappearance of feature columns

Scripting:

1. Integrated debugger for the Python script editor
2. SegmentBuilder script support
3. Dedicated scripting log
4. Preference to define script log verbosity
5. Scripting of object styles
6. Clean up of script API
7. More detailed script API documentation
8. Improved Script editor help pane UI
9. Fix: potential problem in handling pixel size