v0.12.0

• Fix #70 by #73
• Fix #71 by #72

To allow different percentiles per channels

 .normalizePercentilesGlobal('DAPI', 0.1, 99.8, 10 ) 
 .normalizePercentilesGlobal('CY5', 0.5, 99, 6 ) 

fix 'constrainToParent(false)' behavior

Fix #68 & #59

• constrainToParent(false) has now a behavior close to Stardist extension one. All cells which cross the parent annotations are displayed. All cells fully outside the parent annotation are discarded.
• A padding parameter has been introduced to tell QuPath how many um should be taken into account around the parent annotation. The padding can be tuned in constrainToParent(false, padding)
• constrainToParent(true) is left unchanged

Allow up to 3 channels for cpsam

• Allow up to 3 channels for cpsam (#67) (Thanks to @loicsauteur)

Parallelizing operations

• Improving speed by parallelizing operations #66 (Thanks to @loicsauteur)
• Refactor useGPU into disableGPU
• Refactor saveTrainingImages into cleanTrainingDir

Migration to QuPath 0.6.x

First version compatible with QuPath 0.6.x

• Upgrade build tools from groovy to kotlin
• Update gradle version
• Remove deprecated methods from QuPath 0.5.x

v0.10.2-code

This is not a new release ; just to update the Soucre code package that wasn't pushed yet.

Last QuPath-0.5.x compatible version

This is the last version of the extension which is compatible with QuPath 0.5.x. Next versions will only be compatible with QuPath 0.6.x

• fix #61 by adding a new field for cellpose-sam
• fix #62 by initializing with empty strings instead of null

Add an option to skip testDir

• Fixes #58
• Update Javadoc

Add an option to not resave the training images

Fixes #56

Improved label image reading and code linting

From several forum posts, it was clear that for large tiles and large fields of view, the extension was having issues.

This caused tiles to be empty and the detections being incomplete.

It seems like it was caused by the way we used to read objects in using JTS.

This new update changes the way label images are converted to QuPath objects by using the same strategy as LaRoMe's Labels2Rois
https://github.com/BIOP/ijp-LaRoMe/blob/master/src/main/java/ch/epfl/biop/ij2command/Labels2Rois.java

Fundamentally, this should not change the way cells are detected now vs before, though no testing has been done. One thing to note is that if Cellpose ever allows for objects with holes to be detected, then the current strategy will need to be changed again.

What's Changed

• Refactor 092024 by @lacan in #52

Full Changelog: v0.9.5...v0.9.6