Releases: mianalysis/mia
Releases · mianalysis/mia
Version 1.7.9
Version 1.7.8
New plugin features
- File browser is larger by default
Other
- General bugfixes
Version 1.7.7
New module features
- CellposeDetection can now process 3D timepoints individually and reports current progress in MIA status bar
Other
- Changed function visibility in RunScript
- General bugfixes
Version 1.7.6
New module features
- Classes can be automatically assigned in ManuallyIdentifyObjects
- ApplyDeepImageJ can convert images to RGB before processing
Other
- Fixed rendering of points in ManuallyIdentifyObjects
- General bug fixes.
Version 1.7.5
New modules
- LineHoughDetection will identify lines in images. This works in a similar way to other Hough-based detectors in MIA in that detection can be either the N strongest features or all features above a specific score.
New module features
- Improved memory handling for SegmentAnything-based modules (ManuallyIdentifyObjects and ApplySegmentAnything).
- MetadataExtractor can now operate on fixed strings (not just filenames, filepaths, etc.).
Other
- General bug fixes.
Version 1.7.4
New modules
- CreateClassImage creates an image for multiple object sets, where all pixels within an object set have a user-defined index. This way, class images for deep learning training can be easily generated. For example, all nuclei pixels can be assigned a value of "1", all cytoplasmic pixels a value of "2" and so on. The most recently added pixels are written onto the image, irrespective of what's already there, so object overlap can be handled by selecting the dominant objects last in the list.
- CreateObjectGrid will generate a dense array of objects in 2D that fill an image region. The area of each cell in the grid can be specified. This is useful for modules such as ApplySegmentAnything, where the centroids of this grid can be used as inputs.
New module features
- In AddTracks, track rendering with a limited history (i.e. only showing most recent 10 frames) can fade out.
- The maximum output object area can now be defined in ApplySegmentAnything. This prevents excessively large objects being detected, which can take a long time for large image areas.
Other
- Numeric parameters no longer require any value. This means the value can be removed prior to insertion of dynamically-generated fields.
- General bug fixes.
Version 1.7.3
New module features
- ManuallyIdentifyObjects now supports keyboard shortcuts for primary operations (add new objects, remove objects, etc.). These are listed next to each button.
Other
- Bugfix for saving image stacks
Version 1.7.2
Other
- Added dependency to ApplySegmentAnything so MIA won't crash if SAMJ isn't present
Version 1.7.1
New modules
- ApplySegmentAnything creates objects using Meta's Segment Anything and the SAMJ plugin. This takes centroids of specified input objects as the point locations for segmenting objects.
- MeasureDistancesToNeightbours calculates the mean, min, max and standard deviation distances to N neighbouring objects in either the same object class or another class. These can be limited at a maximum distance.
New module features
- ImageSaver can now export images as file sequences. This includes the option to break hyperstacks down by each dimension, or keep some combined. Filename indices can be either single valued (e.g. _0001) or dimension based (e.g. _C0001_Z0002_T0001)
- ApplyDeepImageJModel can now process models that output single image classifications (rather than just pixel classification). In these cases, classifications and probabilities of being in that class are added as measurements to the relevant input image.
- Updated MeasureObjectCurvature to offer optional calculation in 3D. When in 3D only absolute curvature values are exported.
- ManuallyIdentifyObjects will show all selected objects as overlays, rather than just most recently selected object.
Other
- Updated SAMJ (Segment Anything) integration for ManuallyIdentifyObjects to be compatible with latest version of SAMJ.
- More errors and warnings will now be written to Excel log sheet
- "About" documentation page will now show version of current MIA.
- General bugfixes
Version 1.7.0
New modules
- TileStack module converts a large image into a tiled stack. This also works for hyperstacks and be set to place tiles along either of the C,Z or T axes, even if these axes already have dimensions larger than 1. Includes optional tile overlap.
- StitchTiles module will reverse tiling created using above module. Applies linear interpolation between tiles when overlap is specified. These two modules are useful when dealing with large images in DeepImageJ for example.
New module features
- Updated ObjectMeasurementCalculator to include the same options as ImageMeasurementCalculator. These modules now use a common abstract module from which they inherit much of their functionality.
- SetLookupTable can now also apply any LUTs available to ImageJ. Added the option to invert a LUT prior to applying it.
- ShowImage has additional composite display modes (invert, max and min), which can be used to display inverted (on a white background) LUTs without generating a totally white image.
Other
- Moved "Measurement" class to a slightly different location.
- General bugfixes