@QuPath #tweetorial part 2... this time it's (almost) all annotations. 1/20

https://twitter.com/petebankhead/status/1295744964383694848?s=20

#bioimageanalysis #digitalpathology #opensource #javafx

I say 'almost all', because I need to mention the command list early: with 'Ctrl + L' you get a searchable list of everything in the menus.

Having told you that, I can now ignore the menus & focus on shortcuts - safe in the knowledge you can find things if you need them. 2/20

(If you *really* like the command list, you can turn it into a command bar and give it a special place at the top of the viewer... but I probably wouldn't unless I broke my 'L' key.) 3/20

Anyhow, annotations.

QuPath's annotation tools hang out on the top left of the toolbar & all have quick shortcuts to activate them. 4/20

*Most* of the time, you should have the 'Move' tool selected (to avoid annotating by accident).

Beside it live the rectangle, ellipse & line tools to draw... well, rectangles, ellipses & lines.

The 'Shift' key constrains their shapes if needed. 5/20

But there are more tools, with lots of tricks & shortcuts to use them efficiently.

For example, there are polygon & polyline tools - which switch to become freehand tools if you feel like dragging the mouse for a bit... 6/20

...a zoom-dependent brush (which quickly toggles to an eraser with the 'Alt' key)... 7/20

...a color-sensitive wand (also zoom-dependent, can become an eraser & incorporates any color transforms)... 8/20

...and optional snapping to avoid overlaps & help create dense annotations (press Ctrl + Shift when using the brush or wand).

These tricks are part of the reason QuPath is often used for #deeplearning annotation. 9/20

Toggle the display of annotations by pressing 'A' (or the toolbar button), or whether they are filled with 'Shift + F'.

If an annotation is selected, it remains displayed even when the others are hidden. 10/20

If you're not sure what other options you have, bring up the 'Command list' & start typing.

This helps find commands to duplicate, merge, split, fill or expand annotations.

Note: You can contract too - just use a negative expansion. 11/20

Once you know what's there, you can get creative.

For example, expand a line with 'Remove interior' selected & then split the result to get bands of a fixed width inside & out (perhaps after cleaning up the ends a little bit).

Handy for tumor margins, for example. 12/20

Under the 'Annotations' tab, there's a list of all the annotations for the current image.

Measurements for the current selected annotation are shown at the bottom. 13/20

Tip: press Enter with an annotation selected in the viewer to set its name & color*.

You can also 'lock' annotations to avoid accidentally editing them. Locked annotations can still be deleted (press 'Backspace').

*Or right-click it in the list & choose 'Set properties' 14/20

Names are displayed on the image (hide them by pressing 'N'), and descriptions appear as tooltips. 15/20

By default, selected annotations are in yellow.

If you want to select more than one, you can:
* choose them in the list
* click with the 'Move' tool selected & the 'Alt' key pressed
* turn on 'Selection mode' with the big 'S' button and draw around the ones you want 16/20

I say 'by default', because lots of QuPath is customizable. Click the cog wheel to change the preferences... using the search bar to find what you need. 17/20

When you're done, choose 'File -> Save' (or Ctrl + S, or agree when QuPath asks) & your annotations are saved.

No need to specify where: because you definitely followed the tip in the last tweetorial (right?) QuPath will store them in your project. 18/20

https://twitter.com/petebankhead/status/1295744979328016385?s=20

That should be all you need to keep your annotations inside QuPath.

If you need to get them *out*, there's a whole section in the docs describing ways to export them... as GeoJSON, WKB, WKT, binary images or labelled images. 19/20

https://qupath.readthedocs.io/en/latest/docs/advanced/exporting_annotations.html

That's all for now. Next time we'll get into detecting & classifying things. 20/20

https://qupath.github.io