User Manual

We provide a step-by-step user manual here. The user needs to install python3.6 or greater.

1. Divide Whole Slide Images into image tiles

Open cli folder and use extract_tiles_from_wsi_openslide.py to divide WSI into smaller tiles.

 cd quick_annotator\cli
 python extract_tiles_from_wsi_openslide.py 

2. Open terminal, go to QA's directory

cd quick_annotator
python QA.py

3. Open Chrome, go to

http://localhost:5555

The user could change the port number in the config.ini file.

4. Create a new project, add images to the project

5. Follow instruction on the page: Make Patches, (Re)train Model 0, Embed Patches, View Embedding

The image below shows, make patches successfully completed, and the next step is (Re)train Model which trains for AutoEncoder.

6. Go to Embed Page table, hover over a dot, and direct to annotation page to make annotations

Users can also decide where to annotate by moving the selection square on the annotation page.

7. Make annotation and upload them to training set

8. Train a classifier, and then check prediction results when the model is ready

Like the red arrow shows, the user clicks on Retrain Dl From base to train a new model.

As blue arrow points, the prediction result is red, indicating that the prediction layer is not available since there is no model available.

see Navigation Bar

9. Select a patch from the image, import the deep learning output, and modify based on that.

10. Repeat 6-9.

11. Download DL model, output, or annotation files by clicking Download in the top menu bar.