Feature Generation CLIs¶
Luna Pathology feature generation CLIs are installed as binaries as part of the installation. Please see the documentation of the CLIs on this page. For more details, please checkout our <link-to-tutorials>.
Tiling CLIs¶
As a whole slide image is too large for deep learning model training, a slide is often divded into a set of small tiles, and used for training. For tile-based whole slide image analysis, generating tiles and labels is an important and laborious step. With Luna tiling CLIs and tutorials, you can easily generate tile labels and get your data ready for downstream analysis.
load_slide¶
Load a slide to the datastore from the whole slide image table.
app_config - application configuration yaml file. See config.yaml.template for details.
datastore_id - datastore name. usually a slide id.
method_param_path - json parameter file with path to a WSI delta table.
job_tag: job tag to use for loading the slide
table_path: path to the whole slide image table
datastore_path: path to store data
load_slide [OPTIONS]
Options
- -a, --app_config <app_config>¶
Required application configuration yaml file. See config.yaml.template for details.
- -s, --datastore_id <datastore_id>¶
Required datastore name. usually a slide id.
- -m, --method_param_path <method_param_path>¶
Required json parameter file with path to a WSI delta table.
collect_tiles¶
Save tiles as a parquet file, indexed by slide id, address, and optionally patient_id.
app_config - application configuration yaml file. See config.yaml.template for details.
datastore_id - datastore name. usually a slide id.
method_param_path - json file with method parameters including input, output details.
input_label_tag: job tag used for generating tile labels
input_wsi_tag: job tag used for loading the slide
output_datastore: job tag for collecting tiles
root_path: path to output data
collect_tiles [OPTIONS]
Options
- -a, --app_config <app_config>¶
Required application configuration yaml file. See config.yaml.template for details.
- -s, --datastore_id <datastore_id>¶
Required datastore name. usually a slide id.
- -m, --method_param_path <method_param_path>¶
Required json file with method parameters including input, output details.
DSA CLIs¶
Digital Slide Archive (DSA) is a platform where you can manage your pathology images and annotations. DSA also provides APIs that we use to push model results to the platform. A set of CLIs are available to help you convert your pathologist or model-generated annotations and push them to DSA.
dsa_viz¶
DSA annotation builder
- data_config - yaml file with input, output, and method parameters.
The method parameters differs based on the source_type. Please refer to the example configurations files. Some common parameters are:
input: path to results to be visualized. This could be a TSV, bitmasks, GeoJson files. Please see the supported source types for more details.
output_folder: directory where the DSA compatible annotation json file will be saved
image_filename: name of the image file in DSA e.g. 123.svs
annotation_name: name of the annotation to be displayed in DSA
- source_type - string describing data source that is to be transformed into a dsa json.
supports stardist-polygon, stardist-cell, regional-polygon, qupath-polygon, bitmask-polygon, heatmap
dsa_viz [OPTIONS]
Options
- -d, --data_config <data_config>¶
Required path to your data config file that includes input/output parameters.
- -s, --source_type <source_type>¶
Required string describing data source that is to be transformed into a dsa json. supports stardist-polygon, stardist-cell, regional-polygon, qupath-polygon, bitmask-polygon, heatmap