ENH: Rename histopathology folder to match overall naming scheme (#512)

Top-level folder has been renamed from `hi-ml-histopathology` to hi-ml-cpath, the Python namespace from `histopathology` to `health_cpath`.

.amlignore

@@ -20,7 +20,7 @@ node_modules
 cifar-10-python.tar.gz
 cifar-10-batches-py/
 None/
-hi-ml-histopathology/testSSL/test_outputs
+hi-ml-cpath/testSSL/test_outputs
 test_outputs/
 lightning_logs/
 # Downloaded datasets

.codecov.yml

@@ -10,7 +10,7 @@ flags:
     paths:
       - hi-ml-azure
     carryforward: true
-  hi-ml-histopathology:
+  hi-ml-cpath:
     paths:
-      - hi-ml-histopathology
+      - hi-ml-cpath
     carryforward: true

.github/workflows/cpath-pr.yml

@@ -1,4 +1,4 @@
-name: Histopathology PR
+name: Pathology PR
 on:
   push:
     branches: [ main ]
@@ -7,16 +7,16 @@ on:
   pull_request:
     branches: [ main ]
     paths:
-      - "hi-ml-histopathology/**"
-      - ".github/workflows/histopathology-pr.yml"
+      - "hi-ml-cpath/**"
+      - ".github/workflows/cpath-pr.yml"
       # When the core hi-ml libraries change, test the histo test too, to find problems with backwards compatibility
       - "hi-ml-azure/**"
       - "hi-ml/**"
 
 env:
   pythonVersion: 3.7
-  folder: hi-ml-histopathology
-  module_for_coverage_reporting: histopathology
+  folder: hi-ml-cpath
+  module_for_coverage_reporting: health_cpath
   HIML_TENANT_ID: ${{ secrets.HIML_TENANT_ID }}
   HIML_RESOURCE_GROUP: ${{ secrets.HIML_RESOURCE_GROUP }}
   HIML_SUBSCRIPTION_ID: ${{ secrets.HIML_SUBSCRIPTION_ID }}

.gitignore

@@ -164,7 +164,7 @@ temp_requirements.txt
 cifar-10-python.tar.gz
 cifar-10-batches-py/
 None/
-hi-ml-histopathology/testSSL/test_outputs
+hi-ml-cpath/testSSL/test_outputs
 test_outputs/
 lightning_logs/
 # Downloaded datasets

.pre-commit-config.yaml

@@ -40,10 +40,10 @@ repos:
     files: ^hi-ml-azure/
     args: [--config, hi-ml-azure/.flake8]
   - id: flake8
-    name: flake8 ./hi-ml-histopathology/
-    alias: flake8-hi-ml-histopathology
-    files: ^hi-ml-histopathology/
-    args: [--config, hi-ml-histopathology/.flake8]
+    name: flake8 ./hi-ml-cpath/
+    alias: flake8-hi-ml-cpath
+    files: ^hi-ml-cpath/
+    args: [--config, hi-ml-cpath/.flake8]
   - id: flake8
     name: flake8 ./hi-ml-multimodal/
     alias: flake8-hi-ml-multimodal

Makefile

@@ -42,7 +42,7 @@ conda_update:
 	conda env update -n $(CONDA_DEFAULT_ENV) --file hi-ml/environment.yml
 
 # Set the conda environment for local development work, that contains all packages need for hi-ml, hi-ml-azure
-# and hi-ml-histopathology with hi-ml and hi-ml-azure installed in editable mode
+# and hi-ml-cpath with hi-ml and hi-ml-azure installed in editable mode
 conda: conda_update call_pip_local
 
 ## Actions
@@ -120,10 +120,10 @@ combine: pip_test
 	mkdir -p coverage
 	cp hi-ml/.coverage coverage/hi-ml-coverage
 	cp hi-ml-azure/.coverage coverage/hi-ml-azure-coverage
-	cp hi-ml-histopathology/.coverage coverage/hi-ml-histopathology-coverage
+	cp hi-ml-cpath/.coverage coverage/hi-ml-cpath-coverage
 	cp .coveragerc coverage/
 	cd coverage && \
-		coverage combine hi-ml-coverage hi-ml-azure-coverage hi-ml-histopathology-coverage &&  \
+		coverage combine hi-ml-coverage hi-ml-azure-coverage hi-ml-cpath-coverage &&  \
 		coverage html && \
 		coverage xml && \
 		pycobertura show --format text --output coverage.txt coverage.xml

README.md

@@ -12,7 +12,7 @@ This repository consists of two Python packages, as well as project-specific cod
 
 * PyPi package [hi-ml-azure](https://pypi.org/project/hi-ml-azure/) - providing helper functions for running in AzureML.
 * PyPi package [hi-ml](https://pypi.org/project/hi-ml/) - providing ML components.
-* hi-ml-histopathology: Models and workflows for working with histopathology images
+* hi-ml-cpath: Models and workflows for working with histopathology images
 
 ## Getting started
 
@@ -24,7 +24,7 @@ For just the AzureML helper functions:
 
 * Install from `pypi` via `pip`, by running `pip install hi-ml-azure`
 
-For the histopathology workflows, please follow the instructions [here](hi-ml-histopathology/README.md).
+For the histopathology workflows, please follow the instructions [here](hi-ml-cpath/README.md).
 
 If you would like to contribute to the code, please check the [developer guide](docs/source/developers.md).
 

docs/source/conf.py

@@ -21,7 +21,7 @@ import sys
 # Make the source code for both packages available here
 sys.path.insert(0, os.path.abspath('../../hi-ml/src'))
 sys.path.insert(0, os.path.abspath('../../hi-ml-azure/src'))
-sys.path.insert(0, os.path.abspath('../../hi-ml-histopathology/src'))
+sys.path.insert(0, os.path.abspath('../../hi-ml-cpath/src'))
 sys.path.insert(0, os.path.abspath('../../hi-ml-multimodal/src'))
 
 # -- Project information -----------------------------------------------------
@@ -72,7 +72,7 @@ html_theme = 'sphinx_rtd_theme'
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = []  # type: ignore
 
-modindex_common_prefix = ["health_azure.", "health_ml.", "histopathology."]
+modindex_common_prefix = ["health_azure.", "health_ml.", "health_cpath."]
 
 source_suffix = {
     '.rst': 'restructuredtext',

docs/source/debugging.md

@@ -20,7 +20,7 @@ We provide a set of example debugging configs for each of hi-ml module:
 
 * [launch.json in hi-ml](https://github.com/microsoft/hi-ml/tree/main/hi-ml/.vscode/launch.json)
 * [launch.json in hi-ml-azure](https://github.com/microsoft/hi-ml/tree/main/hi-ml-azure/.vscode/launch.json)
-* [launch.json in hi-ml-histopathology](https://github.com/microsoft/hi-ml/tree/main/hi-ml-histopathology/.vscode/launch.json)
+* [launch.json in hi-ml-cpath](https://github.com/microsoft/hi-ml/tree/main/hi-ml-cpath/.vscode/launch.json)
 
 VS Code restricts debugging to user-written code only by default. If you want to step through external code and
 standard libraries functions, set `"justMyCode": false` inside the debugging config block in the `launch.json` file.

docs/source/developers.md

@@ -15,14 +15,14 @@ at once or individual projects separately in VSCode.
 * To open all projects at once, use VSCode's "Open Workspace from File", and
   select `himl-projects.code-workspace`.
 * To open individual projects, use VSCode's "Open Folder", and select one of the
-  folders `hi-ml-azure`, `hi-ml`, or `hi-ml-histopathology`
+  folders `hi-ml-azure`, `hi-ml`, or `hi-ml-cpath`
 
 ## Creating a Conda environment
 
 Different projects in this repository use different Conda environments:
 
 * The `himl` Conda environment should be used for work on the `hi-ml` and `hi-ml-azure` projects.
-* The `HimlHisto` Conda environment should be used for work on `hi-ml-histopathology`.
+* The `HimlHisto` Conda environment should be used for work on `hi-ml-cpath`.
 
 Please select the right Python interpreter for your project (or all projects if using the `himl-projects` workspace)
 inside VSCode, by choosing "Python: Select Interpreter" from the command palette (Ctrl-Shift-P on VSCode for Windows)
@@ -138,7 +138,7 @@ When running the tests locally, they can either be run against the source direct
 
 ### Test discovery in VSCode
 
-All tests in the repository should be picked up automatically by VSCode. In particular, this includes the tests in the `hi-ml-histopathology` folder, which
+All tests in the repository should be picked up automatically by VSCode. In particular, this includes the tests in the `hi-ml-cpath` folder, which
 are not always necessary when working on the core `hi-ml` projects.
 
 ## Creating a New Release

docs/source/dsa.md

@@ -52,7 +52,7 @@ upload annotations to a deployed DSA.
 For example:
 
 ```shell
-SCRIPT="hi-ml-histopathology/src/histopathology/utils/girder.py"
+SCRIPT="hi-ml-cpath/src/histopathology/utils/girder.py"
 python $SCRIPT \
     --run-id "Experiment_transformer_Gleason_run_0" \
     --dsa-url "https://my-deployed-dsa.azure.com/" \

docs/source/histopathology.md

@@ -1,12 +1,12 @@
 # HI-ML Tools for Computational Pathology
 
-The directory [`hi-ml-histopathology`](https://github.com/microsoft/hi-ml/tree/main/hi-ml-histopathology) contains code
+The directory [`hi-ml-cpath`](https://github.com/microsoft/hi-ml/tree/main/hi-ml-cpath) contains code
 for runnning experiments in Computational Pathology.
 
 ## Setting up your computer
 
 The tools for computational pathology cannot be as a Python package, but rather directly from the Git repository. Please
-follow the instructions in [README](https://github.com/microsoft/hi-ml/blob/main/hi-ml-histopathology/README.md) to set
+follow the instructions in [README](https://github.com/microsoft/hi-ml/blob/main/hi-ml-cpath/README.md) to set
 up your local Python environment.
 
 ## Onboarding to Azure
@@ -34,13 +34,13 @@ Please follow the [detailed instructions](public_datasets.md) to download and pr
 
 ## New Model configurations
 
-To define your own model configuration, place a class definition in the directory `histopathology.configs`. The class should
+To define your own model configuration, place a class definition in the directory `health_cpath.configs`. The class should
 inherit from a
 [LightningContainer](https://github.com/microsoft/hi-ml/blob/39911d217c919d8213ad36c9c776f69369d98509/hi-ml/src/health_ml/lightning_container.py#L24).
 As an example, please check the [HelloWorld
 model](https://github.com/microsoft/hi-ml/blob/0793cbd1a874920d04b0a8f1298a7a112cfd712c/hi-ml/src/health_ml/configs/hello_world.py#L232)
 or the [base class for the MIL
-models](https://github.com/microsoft/hi-ml/blob/1d96c9bcdb326ad4d145ab082f45a2116d776a76/hi-ml-histopathology/src/histopathology/configs/classification/BaseMIL.py#L39).
+models](https://github.com/microsoft/hi-ml/blob/1d96c9bcdb326ad4d145ab082f45a2116d776a76/hi-ml-cpath/src/histopathology/configs/classification/BaseMIL.py#L39).
 
 ## Mount datasets
 
@@ -49,7 +49,7 @@ or mount them. "Mounting" here means that the dataset will be loaded on-demand o
 docs](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-train-with-datasets#mount-vs-download)). This is ideal if you expect that
 you will only need a small number of files, or if the disk of your machine is too small to download the full dataset.
 
-You can mount the dataset by executing this script in `<root>/hi-ml-histopathology`:
+You can mount the dataset by executing this script in `<root>/hi-ml-cpath`:
 
 ```shell
 python src/histopathology/scripts/mount_azure_dataset.py --dataset_id PANDA

docs/source/panda_model.md

@@ -22,11 +22,11 @@ You will also need to run the dataset preparations for the PANDA dataset, as des
 
 ## Running the model as-is
 
-If you have a GPU available, you can run training on that machine, by executing in `<root>/hi-ml-histopathology`:
+If you have a GPU available, you can run training on that machine, by executing in `<root>/hi-ml-cpath`:
 
 ```shell
 conda activate HimlHisto
-python ../hi-ml/src/health_ml/runner.py --model histopathology.SlidesPandaImageNetMILBenchmark
+python ../hi-ml/src/health_ml/runner.py --model health_cpath.idesPandaImageNetMILBenchmark
 ```
 
 Running the model will automatically mount (download on-the-fly) the PANDA dataset from Azure. To enable that, you will
@@ -44,7 +44,7 @@ addition, you can turn on fine-tuning of the encoder, which will improve the res
 
 ```shell
 conda activate HimlHisto
-python ../hi-ml/src/health_ml/runner.py --model histopathology.SlidesPandaImageNetMILBenchmark --is_finetune --cluster=<your_cluster_name>
+python ../hi-ml/src/health_ml/runner.py --model health_cpath.idesPandaImageNetMILBenchmark --is_finetune --cluster=<your_cluster_name>
 ```
 
 Then the script will output "Successfully queued run number ..." and a line prefixed "Run URL: ...". Open that
@@ -87,16 +87,16 @@ This will mean that the job starts faster, but may not run at maximum speed beca
 To use cross-validation, supply the additional commandline flag `--crossval_count=5` for 5-fold cross-validation, like:
 
 ```shell
-python ../hi-ml/src/health_ml/runner.py --model histopathology.SlidesPandaImageNetMILBenchmark --crossval_count=5 --cluster=<your_cluster_name>
+python ../hi-ml/src/health_ml/runner.py --model health_cpath.idesPandaImageNetMILBenchmark --crossval_count=5 --cluster=<your_cluster_name>
 ```
 
 Cross-validation will start 5 training runs in parallel. For this reason, cross-validation can only be used in AzureML.
 
 To compute aggregated metrics of the hyperdrive run in Azure ML, replace the `run_id` in
-`hi-ml-histopathology/src/histopathology/scripts/aggregate_metrics_crossvalidation.py` with the Run ID of the hyperdrive
+`hi-ml-cpath/src/histopathology/scripts/aggregate_metrics_crossvalidation.py` with the Run ID of the hyperdrive
 run, and run the script as follows:
 
 ```shell
 conda activate HimlHisto
-python hi-ml-histopathology/src/histopathology/scripts/aggregate_metrics_crossvalidation.py
+python hi-ml-cpath/src/histopathology/scripts/aggregate_metrics_crossvalidation.py
 ```

docs/source/public_datasets.md

@@ -39,7 +39,7 @@ repository. To prepare:
 
 - In the last statement, where we upload the full dataset to Azure, replace `<your_storage_account>` with the
   name of your Azure storage account.
-- For Python to pick up the paths in `hi-ml-histopathology/src/histopathology/scripts/tcga_dataset_prep.py`, you need to
+- For Python to pick up the paths in `hi-ml-cpath/src/histopathology/scripts/tcga_dataset_prep.py`, you need to
   add the `hi
 
 Note: Depending on the speed of your internet connection, this script can run for several hours because it downloads
@@ -64,8 +64,8 @@ do
 done
 # Create a summary file dataset.csv with all file paths and class labels
 cd ..
-export PYTHONPATH=`pwd`/hi-ml-histopathology/src
-python hi-ml-histopathology/src/histopathology/scripts/tcga_dataset_prep.py
+export PYTHONPATH=`pwd`/hi-ml-cpath/src
+python hi-ml-cpath/src/histopathology/scripts/tcga_dataset_prep.py
 # Upload
 azcopy copy TCGA-Crck https://<your_storage_account>.blob.core.windows.net/datasets/ --recursive
 ```

docs/source/runner.md

@@ -25,9 +25,9 @@ that class:
 `health_ml.configs` namespace. It can be in any module/folder inside of that namespace.
 - If the class is outside of the `health_ml.configs` (as would be normal if using the `himl-runner` from a package),
 you need to provide some "hints" where to start searching. It is enough to provide the start of the namespace string:
-for example, `--model histopathology.PandaImageNetMIL` is effectively telling the runner to search for the
+for example, `--model health_cpath.PandaImageNetMIL` is effectively telling the runner to search for the
 `PandaImageNetMIL` class _anywhere_ in the `histopathology` namespace. You can think of this as
-`histopathology.*.PandaImageNetMIL`
+`health_cpath.*.PandaImageNetMIL`
 
 ## Running ML experiments in Azure ML
 

docs/source/ssl_on_tile_dataset.md

@@ -16,11 +16,11 @@ from the Cancer Genome Atlas (TCGA) with accompanying binarized MicroSatellite I
 TCGA-CRCk, the dataset is already tiled, i.e., the WSI are not available. In [public_datasets.md](./public_datasets.md)
 you will find instructions on how to download and setup the TCGA-CRCk dataset.
 
-To train an image encoder using SSL locally run this in the `hi-ml-histopathology` folder, with the `HimlHisto` conda
+To train an image encoder using SSL locally run this in the `hi-ml-cpath` folder, with the `HimlHisto` conda
 enviroment activated:
 
 ```bash
-python ../hi-ml/src/health_ml/runner.py --model histopathology.CRCK_SimCLR
+python ../hi-ml/src/health_ml/runner.py --model health_cpath.CRCK_SimCLR
 ```
 
 The model class
@@ -76,7 +76,7 @@ the TCGA-CRCk dataset. Assuming you are using a total of 8  GPUs (e.g. 1 node wi
 Azure you can start training with the following command in the repository root folder:
 
 ```bash
-python hi-ml/src/health_ml/runner.py --model histopathology.CRCK_SimCLR --cluster CLUSTER_NAME --conda_env hi-ml-histopathology/environment.yml
+python hi-ml/src/health_ml/runner.py --model health_cpath.CRCK_SimCLR --cluster CLUSTER_NAME --conda_env hi-ml-cpath/environment.yml
 ```
 
 A SimCLR run with 200 epochs, 8 GPUs, and a batch size of 48 (per GPU) takes about 6 hours. On Azure we use

docs/source/whole_slide_images.md

@@ -37,7 +37,7 @@ The suitable AzureML base Docker images are therefore the ones containing `cuda1
 
 ## Performance
 
-An exploratory set of scripts for comparing loading images with OpenSlide or cuCIM, and performing tiling using both libraries can be found at [`slide_image_loading`](https://github.com/microsoft/hi-ml/tree/main/hi-ml-histopathology/other/slide_image_loading).
+An exploratory set of scripts for comparing loading images with OpenSlide or cuCIM, and performing tiling using both libraries can be found at [`slide_image_loading`](https://github.com/microsoft/hi-ml/tree/main/hi-ml-cpath/other/slide_image_loading).
 
 ### Loading and saving at lowest resolution
 

hi-ml-azure/run_pytest.py

@@ -50,7 +50,7 @@ class RunPytestConfig(param.Parameterized):
     coverage_module: str = param.String(
         default="",
         doc="This value is used as an argument to --cov of pytest to collect code coverage for the specified pyhton "
-        "module. For example, in the subfolder hi-ml-histopathology, one can collect code coverage for the "
+        "module. For example, in the subfolder hi-ml-cpath, one can collect code coverage for the "
         "histopathology module by setting `module=histopathology`. If set to '' (default), no coverage is collected."
     )
     cluster: str = param.String(default="", doc="The name of the AzureML compute cluster where the script should run.")

hi-ml-cpath/.vscode/launch.json

@@ -22,7 +22,7 @@
             "request": "launch",
             "program": "${workspaceFolder}/../hi-ml/src/health_ml/runner.py",
             "args": [
-                "--model=histopathology.configs.classification.DeepSMILECrck",
+                "--model=health_cpath.configs.classification.DeepSMILECrck",
                 "--cluster=lite-testing-ds2",
             ],
             "console": "integratedTerminal"
@@ -33,7 +33,7 @@
             "request": "launch",
             "program": "${workspaceFolder}/../hi-ml/src/health_ml/runner.py",
             "args": [
-                "--model=histopathology.DeepSMILECrck",
+                "--model=health_cpath.DeepSMILECrck",
             ],
             "console": "integratedTerminal"
         },
@@ -43,7 +43,7 @@
             "request": "launch",
             "program": "${workspaceFolder}/../hi-ml/src/health_ml/runner.py",
             "args": [
-                "--model=histopathology.SlidesPandaImageNetMIL",
+                "--model=health_cpath.SlidesPandaImageNetMIL",
                 "--pl_fast_dev_run=10",
                 "--crossval_count=0",
                 "--batch_size=2",
@@ -60,7 +60,7 @@
             "request": "launch",
             "program": "${workspaceFolder}/../hi-ml/src/health_ml/runner.py",
             "args": [
-                "--model=histopathology.TilesPandaImageNetMIL",
+                "--model=health_cpath.TilesPandaImageNetMIL",
                 "--pl_fast_dev_run=10",
                 "--crossval_count=0",
                 "--batch_size=2",

hi-ml-cpath/.vscode/settings.json

@@ -67,5 +67,10 @@
         "${workspaceFolder}/src",
         "${workspaceFolder}/testhisto",
         "${workspaceFolder}/testSSL"
-    ]
+    ],
+    "workbench.colorCustomizations": {
+      "activityBar.background": "#4B0769",
+      "titleBar.activeBackground": "#690A93",
+      "titleBar.activeForeground": "#FDF9FF"
+    }
  }

hi-ml-cpath/Makefile

@@ -46,7 +46,7 @@ flake8:
 
 # run mypy, assuming test requirements already installed
 mypy:
-	mypy --install-types --show-error-codes --non-interactive --package histopathology
+	mypy --install-types --show-error-codes --non-interactive --package health_cpath
 	mypy --install-types --show-error-codes --non-interactive --package SSL
 	mypy --install-types --show-error-codes --non-interactive --package testhisto
 	mypy --install-types --show-error-codes --non-interactive --package testSSL
@@ -60,14 +60,14 @@ pytest:
 
 # run pytest with coverage on package
 pytest_coverage:
-	pytest --cov=histopathology --cov SSL --cov-branch --cov-report=html --cov-report=xml --cov-report=term-missing --cov-config=.coveragerc
+	pytest --cov=health_cpath --cov SSL --cov-branch --cov-report=html --cov-report=xml --cov-report=term-missing --cov-config=.coveragerc
 
 # Run regression tests and compare performance
 regression_test_tilespandaimagenetmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.TilesPandaImageNetMIL --batch_size=2 \
-	--cluster pr-gpu --mount_in_azureml --conda_env hi-ml-histopathology/environment.yml \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.TilesPandaImageNetMIL --batch_size=2 \
+	--cluster pr-gpu --mount_in_azureml --conda_env hi-ml-health_cpath/environment.yml \
 	--regression_test_folder=testhisto/RegressionTestResults/TilesPANDAImageNetMIL/\
 	HD_4ab0d833-fe55-44e8-aa04-cbaadbcc2733_0 --regression_test_csv_tolerance=0.5 --is_finetune \
 	--regression_metrics='test/accuracy,test/macro_accuracy,test/weighted_accuracy,test/auroc,test/ISUP 0,test/ISUP 1,\
@@ -77,8 +77,8 @@ regression_test_tilespandaimagenetmil:
 regression_test_slidespandaimagenetmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.SlidesPandaImageNetMILBenchmark \
-	--cluster pr-gpu --mount_in_azureml --conda_env hi-ml-histopathology/environment.yml \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.SlidesPandaImageNetMILBenchmark \
+	--cluster pr-gpu --mount_in_azureml --conda_env hi-ml-cpath/environment.yml \
 	--regression_test_folder=testhisto/RegressionTestResults/SlidesPANDAImageNetMIL/\
 	HD_0e805b91-319d-4fde-8bc3-1cea3a6d08dd_0 --regression_test_csv_tolerance=0.5 --is_finetune \
 	--regression_metrics='test/accuracy,test/macro_accuracy,test/weighted_accuracy,test/auroc,test/ISUP 0,test/ISUP 1,\
@@ -88,9 +88,9 @@ regression_test_slidespandaimagenetmil:
 regression_test_tcgacrcksslmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.TcgaCrckSSLMIL \
-	--cluster pr-gpu --conda_env hi-ml-histopathology/environment.yml --max_epochs=50 \
-	--regression_test_folder=hi-ml-histopathology/testhisto/RegressionTestResults/\
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.TcgaCrckSSLMIL \
+	--cluster pr-gpu --conda_env hi-ml-cpath/environment.yml --max_epochs=50 \
+	--regression_test_folder=hi-ml-cpath/testhisto/RegressionTestResults/\
 	TcgaCrckSSLMIL/HD_d76ef6cd-0403-4923-b8fa-dfd2827c5d74 --regression_test_csv_tolerance=0.5 \
 	--regression_metrics=test/accuracy,test/auroc,test/f1score,test/precision,test/recall;\
 	}
@@ -98,9 +98,9 @@ regression_test_tcgacrcksslmil:
 regression_test_crck_simclr:
 	{ \
 	cd ../; \
-	python hi-ml/src/health_ml/runner.py --model=histopathology.CRCK_SimCLR \
-	--cluster pr-gpu --conda_env hi-ml-histopathology/environment.yml \
-	--regression_test_folder=hi-ml-histopathology/testhisto/RegressionTestResults/CRCK_SimCLR/\
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.CRCK_SimCLR \
+	--cluster pr-gpu --conda_env hi-ml-cpath/environment.yml \
+	--regression_test_folder=hi-ml-cpath/testhisto/RegressionTestResults/CRCK_SimCLR/\
 	CRCK_SimCLR_1653673515_42d53d78 --regression_test_csv_tolerance=0.5 \
 	 --regression_metrics=ssl_online_evaluator/val/AreaUnderRocCurve,\
 	ssl_online_evaluator/val/AreaUnderPRCurve,ssl_online_evaluator/val/AccuracyAtThreshold05 --max_epochs=200;\
@@ -113,9 +113,9 @@ regression tests: regression_test_tilespandaimagenetmil regression_test_slidespa
 smoke_test_slidespandaimagenetmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.SlidesPandaImageNetMILBenchmark \
-	--mount_in_azureml --conda_env hi-ml-histopathology/environment.yml --is_finetune \
-	--conda_env hi-ml-histopathology/environment.yml --crossval_count=0 --num_top_slides=2 --num_top_tiles=2 \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.SlidesPandaImageNetMILBenchmark \
+	--mount_in_azureml --conda_env hi-ml-cpath/environment.yml --is_finetune \
+	--conda_env hi-ml-cpath/environment.yml --crossval_count=0 --num_top_slides=2 --num_top_tiles=2 \
 	--pl_limit_train_batches=2 --pl_limit_val_batches=2 --pl_limit_test_batches=2 \
 	--max_bag_size=3 --max_bag_size_inf=3 --max_epochs=2;\
 	}
@@ -124,8 +124,8 @@ smoke_test_slidespandaimagenetmil:
 smoke_test_tilespandaimagenetmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.TilesPandaImageNetMIL \
-	--mount_in_azureml --conda_env hi-ml-histopathology/environment.yml \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.TilesPandaImageNetMIL \
+	--mount_in_azureml --conda_env hi-ml-cpath/environment.yml \
 	--is_finetune --batch_size=2 --crossval_count=0 --num_top_slides=2 --num_top_tiles=2 \
 	--pl_limit_train_batches=2 --pl_limit_val_batches=2 --pl_limit_test_batches=2 \
 	--max_bag_size=3 --max_bag_size_inf=3 --max_epochs=2;\
@@ -135,8 +135,8 @@ smoke_test_tilespandaimagenetmil:
 smoke_test_tcgacrcksslmil:
 	{ \
 	cd ../ ;\
-	python hi-ml/src/health_ml/runner.py --model=histopathology.TcgaCrckSSLMIL \
-	--conda_env hi-ml-histopathology/environment.yml --crossval_count=1 \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.TcgaCrckSSLMIL \
+	--conda_env hi-ml-cpath/environment.yml --crossval_count=1 \
 	--pl_limit_train_batches=2 --pl_limit_val_batches=2 --pl_limit_test_batches=2 \
 	--max_bag_size=3 --max_bag_size_inf=3 --max_epochs=2;\
 	}
@@ -145,8 +145,8 @@ smoke_test_tcgacrcksslmil:
 smoke_test_crck_simclr:
 	{ \
 	cd ../; \
-	python hi-ml/src/health_ml/runner.py --model=histopathology.CRCK_SimCLR \
-	--conda_env hi-ml-histopathology/environment.yml \
+	python hi-ml/src/health_ml/runner.py --model=health_cpath.CRCK_SimCLR \
+	--conda_env hi-ml-cpath/environment.yml \
 	--pl_limit_train_batches=2 --pl_limit_val_batches=2 --pl_limit_test_batches=2 \
 	--is_debug_model=True --num_workers=0 --max_epochs=2; \
 	}

hi-ml-cpath/README.md

@@ -13,7 +13,7 @@ readthedocs](https://hi-ml.readthedocs.io/en/latest/histopathology.html).
 For working on the histopathology folder, please create a separate Conda environment.
 
 ```shell
-cd hi-ml-histopathology
+cd hi-ml-cpath
 make env
 ```
 
@@ -23,7 +23,7 @@ from the command palette.
 In the event of dependencies update, you can update your conda environment by running the following:
 
 ```shell
-cd hi-ml-histopathology
+cd hi-ml-cpath
 make conda_update
 ```
 
@@ -36,15 +36,15 @@ In addition, please download an AzureML workspace configuration file for the wor
 * Select "Download config file".
 * Save that file into the the repository root.
 
-Once that config file is in place, all Python runs that you start inside the `hi-ml-histopathology` folder will automatically use this config file.
+Once that config file is in place, all Python runs that you start inside the `hi-ml-cpath` folder will automatically use this config file.
 
 ## Running histopathology models
 
-To test your setup, please execute in the `hi-ml-histopathology` folder:
+To test your setup, please execute in the `hi-ml-cpath` folder:
 
 ```shell
 conda activate HimlHisto
-python ../hi-ml/src/health_ml/runner.py --model histopathology.TcgaCrckImageNetMIL  --cluster=training-nd24
+python ../hi-ml/src/health_ml/runner.py --model health_cpath.TcgaCrckImageNetMIL  --cluster=training-nd24
 ```
 
 This should start an AzureML job in the AzureML workspace that you configured above via `config.json`. You may need to adjust the name of
@@ -52,12 +52,12 @@ the compute cluster (`training-nd24` in the above example).
 
 ### Conda environment
 
-If you start your jobs in the `hi-ml-histopathology` folder, they will automatically pick up the Conda environment file that is present in that folder.
-If you start your jobs in a different folder, you need to add the `--conda_env` option to point to the file `<repo_root>/hi-ml-histopathology/environment.yml`.
+If you start your jobs in the `hi-ml-cpath` folder, they will automatically pick up the Conda environment file that is present in that folder.
+If you start your jobs in a different folder, you need to add the `--conda_env` option to point to the file `<repo_root>/hi-ml-cpath/environment.yml`.
 
 ## Running histopathology tests
 
-In the `hi-ml-histopathology` folder, run
+In the `hi-ml-cpath` folder, run
 
 ```shell
 make call_pytest

hi-ml-cpath/other/slide_image_loading/src/Histopathology/preprocessing/create_tiles_dataset.py

@@ -13,8 +13,8 @@ from monai.data.dataset import Dataset
 from monai.data.image_reader import WSIReader
 from tqdm import tqdm
 
-from histopathology.datasets.panda_dataset import LoadPandaROId, PandaDataset
-from histopathology.preprocessing import tiling
+from health_cpath.datasets.panda_dataset import LoadPandaROId, PandaDataset
+from health_cpath.preprocessing import tiling
 
 CSV_COLUMNS = ['slide_id', 'tile_id', 'image', 'mask', 'tile_x', 'tile_y', 'occupancy',
                'data_provider', 'slide_isup_grade', 'slide_gleason_score']

hi-ml-cpath/other/slide_image_loading/src/profile_load_image.py

@@ -14,7 +14,7 @@ import numpy as np
 
 from health_azure import DatasetConfig, submit_to_azure_if_needed
 
-from histopathology.preprocessing.create_tiles_dataset import process_slide, save_tile, generate_tiles
+from health_cpath.preprocessing.create_tiles_dataset import process_slide, save_tile, generate_tiles
 
 
 def profile_cucim(input_file: Path,
@@ -137,7 +137,7 @@ def profile_main(mount_point: Path,
                  label: str,
                  process: Callable) -> None:
     def wrap_main() -> None:
-        from histopathology.preprocessing.create_tiles_dataset import main
+        from health_cpath.preprocessing.create_tiles_dataset import main
         main(process,
              panda_dir=mount_point,
              root_output_dir=output_folder / label,

hi-ml-cpath/src/health_cpath/configs/SSL/CRCK_SimCLRContainer.py

@@ -7,9 +7,9 @@ from typing import Any
 
 from SSL.lightning_containers.ssl_container import EncoderName, SSLContainer, SSLDatasetName
 from SSL.utils import SSLTrainingType
-from histopathology.datasets.default_paths import TCGA_CRCK_DATASET_ID
-from histopathology.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDatasetWithReturnIndex
-from histopathology.configs.SSL.HistoSimCLRContainer import HistoSSLContainer
+from health_cpath.datasets.default_paths import TCGA_CRCK_DATASET_ID
+from health_cpath.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDatasetWithReturnIndex
+from health_cpath.configs.SSL.HistoSimCLRContainer import HistoSSLContainer
 
 
 class SSLDatasetNameHiml(SSLDatasetName, Enum):  # type: ignore

hi-ml-cpath/src/health_cpath/configs/SSL/PANDA_SimCLRContainer.py

@@ -8,9 +8,9 @@ from typing import Any
 from SSL.lightning_containers.ssl_container import EncoderName, SSLContainer, SSLDatasetName
 from SSL.utils import SSLTrainingType
 from health_azure.utils import is_running_in_azure_ml
-from histopathology.datasets.panda_tiles_dataset import PandaTilesDatasetWithReturnIndex
-from histopathology.configs.SSL.HistoSimCLRContainer import HistoSSLContainer
-from histopathology.datasets.default_paths import PANDA_TILES_DATASET_ID
+from health_cpath.datasets.panda_tiles_dataset import PandaTilesDatasetWithReturnIndex
+from health_cpath.configs.SSL.HistoSimCLRContainer import HistoSSLContainer
+from health_cpath.datasets.default_paths import PANDA_TILES_DATASET_ID
 
 
 class SSLDatasetNameHiml(SSLDatasetName, Enum):  # type: ignore

hi-ml-cpath/src/health_cpath/configs/classification/BaseMIL.py

@@ -21,14 +21,14 @@ from health_ml.lightning_container import LightningContainer
 from health_ml.utils.checkpoint_utils import get_best_checkpoint_path
 from health_ml.utils.common_utils import CHECKPOINT_FOLDER, DEFAULT_AML_UPLOAD_DIR
 
-from histopathology.datamodules.base_module import CacheLocation, CacheMode, HistoDataModule
-from histopathology.datasets.base_dataset import SlidesDataset
-from histopathology.models.deepmil import TilesDeepMILModule, SlidesDeepMILModule, BaseDeepMILModule
-from histopathology.models.transforms import EncodeTilesBatchd, LoadTilesBatchd
-from histopathology.utils.deepmil_utils import EncoderParams, PoolingParams
-from histopathology.utils.output_utils import DeepMILOutputsHandler
-from histopathology.utils.naming import MetricsKey, PlotOption, SlideKey, ModelKey
-from histopathology.utils.tiles_selection_utils import TilesSelector
+from health_cpath.datamodules.base_module import CacheLocation, CacheMode, HistoDataModule
+from health_cpath.datasets.base_dataset import SlidesDataset
+from health_cpath.models.deepmil import TilesDeepMILModule, SlidesDeepMILModule, BaseDeepMILModule
+from health_cpath.models.transforms import EncodeTilesBatchd, LoadTilesBatchd
+from health_cpath.utils.deepmil_utils import EncoderParams, PoolingParams
+from health_cpath.utils.output_utils import DeepMILOutputsHandler
+from health_cpath.utils.naming import MetricsKey, PlotOption, SlideKey, ModelKey
+from health_cpath.utils.tiles_selection_utils import TilesSelector
 
 
 class BaseMIL(LightningContainer, EncoderParams, PoolingParams):

hi-ml-cpath/src/health_cpath/configs/classification/DeepSMILECrck.py

@@ -14,18 +14,18 @@ damage response defect classification directly from H&E whole-slide images. arXi
 from typing import Any
 
 from health_ml.networks.layers.attention_layers import AttentionLayer
-from histopathology.configs.run_ids import innereye_ssl_checkpoint_crck_4ws
-from histopathology.datamodules.base_module import TilesDataModule
-from histopathology.datamodules.tcga_crck_module import TcgaCrckTilesDataModule
-from histopathology.datasets.default_paths import TCGA_CRCK_DATASET_ID
-from histopathology.models.encoders import (
+from health_cpath.configs.run_ids import innereye_ssl_checkpoint_crck_4ws
+from health_cpath.datamodules.base_module import TilesDataModule
+from health_cpath.datamodules.tcga_crck_module import TcgaCrckTilesDataModule
+from health_cpath.datasets.default_paths import TCGA_CRCK_DATASET_ID
+from health_cpath.models.encoders import (
     HistoSSLEncoder,
     ImageNetEncoder,
     ImageNetSimCLREncoder,
     SSLEncoder,
 )
-from histopathology.configs.classification.BaseMIL import BaseMILTiles
-from histopathology.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDataset
+from health_cpath.configs.classification.BaseMIL import BaseMILTiles
+from health_cpath.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDataset
 
 
 class DeepSMILECrck(BaseMILTiles):

hi-ml-cpath/src/health_cpath/configs/classification/DeepSMILEPanda.py

@@ -6,22 +6,22 @@ from typing import Any, Optional, Set
 
 from health_azure.utils import is_running_in_azure_ml
 from health_ml.networks.layers.attention_layers import AttentionLayer
-from histopathology.configs.run_ids import innereye_ssl_checkpoint_binary
-from histopathology.datamodules.panda_module import (
+from health_cpath.configs.run_ids import innereye_ssl_checkpoint_binary
+from health_cpath.datamodules.panda_module import (
     PandaSlidesDataModule,
     PandaTilesDataModule)
-from histopathology.datasets.panda_tiles_dataset import PandaTilesDataset
-from histopathology.models.encoders import (
+from health_cpath.datasets.panda_tiles_dataset import PandaTilesDataset
+from health_cpath.models.encoders import (
     HistoSSLEncoder,
     ImageNetEncoder,
     ImageNetSimCLREncoder,
     SSLEncoder)
-from histopathology.configs.classification.BaseMIL import BaseMILSlides, BaseMILTiles, BaseMIL
-from histopathology.datasets.panda_dataset import PandaDataset
-from histopathology.datasets.default_paths import (
+from health_cpath.configs.classification.BaseMIL import BaseMILSlides, BaseMILTiles, BaseMIL
+from health_cpath.datasets.panda_dataset import PandaDataset
+from health_cpath.datasets.default_paths import (
     PANDA_DATASET_ID,
     PANDA_TILES_DATASET_ID)
-from histopathology.utils.naming import PlotOption
+from health_cpath.utils.naming import PlotOption
 
 
 class BaseDeepSMILEPanda(BaseMIL):

hi-ml-cpath/src/health_cpath/configs/classification/DeepSMILESlidesPandaBenchmark.py

@@ -14,18 +14,18 @@ from health_ml.networks.layers.attention_layers import (
     TransformerPoolingBenchmark
 )
 from health_ml.deep_learning_config import OptimizerParams
-from histopathology.datasets.panda_dataset import PandaDataset
-from histopathology.datamodules.panda_module_benchmark import PandaSlidesDataModuleBenchmark
-from histopathology.models.encoders import (
+from health_cpath.datasets.panda_dataset import PandaDataset
+from health_cpath.datamodules.panda_module_benchmark import PandaSlidesDataModuleBenchmark
+from health_cpath.models.encoders import (
     HistoSSLEncoder,
     ImageNetEncoder_Resnet50,
     ImageNetSimCLREncoder,
     SSLEncoder,
 )
-from histopathology.configs.classification.DeepSMILEPanda import DeepSMILESlidesPanda
-from histopathology.models.deepmil import SlidesDeepMILModule
-from histopathology.utils.deepmil_utils import EncoderParams, PoolingParams
-from histopathology.utils.naming import MetricsKey, ModelKey, SlideKey
+from health_cpath.configs.classification.DeepSMILEPanda import DeepSMILESlidesPanda
+from health_cpath.models.deepmil import SlidesDeepMILModule
+from health_cpath.utils.deepmil_utils import EncoderParams, PoolingParams
+from health_cpath.utils.naming import MetricsKey, ModelKey, SlideKey
 
 
 class PandaSlidesDeepMILModuleBenchmark(SlidesDeepMILModule):

hi-ml-cpath/src/health_cpath/datamodules/base_module.py

@@ -15,10 +15,10 @@ from torch.utils.data import DataLoader
 from health_ml.utils.bag_utils import BagDataset, multibag_collate
 from health_ml.utils.common_utils import _create_generator
 
-from histopathology.utils.wsi_utils import image_collate
-from histopathology.models.transforms import LoadTilesBatchd
-from histopathology.datasets.base_dataset import SlidesDataset, TilesDataset
-from histopathology.utils.naming import ModelKey
+from health_cpath.utils.wsi_utils import image_collate
+from health_cpath.models.transforms import LoadTilesBatchd
+from health_cpath.datasets.base_dataset import SlidesDataset, TilesDataset
+from health_cpath.utils.naming import ModelKey
 
 from monai.transforms.compose import Compose
 from monai.transforms.io.dictionary import LoadImaged

hi-ml-cpath/src/health_cpath/datamodules/panda_module.py

@@ -6,9 +6,9 @@ from typing import Tuple
 
 from health_ml.utils.split_dataset import DatasetSplits
 
-from histopathology.datamodules.base_module import SlidesDataModule, TilesDataModule
-from histopathology.datasets.panda_dataset import PandaDataset
-from histopathology.datasets.panda_tiles_dataset import PandaTilesDataset
+from health_cpath.datamodules.base_module import SlidesDataModule, TilesDataModule
+from health_cpath.datasets.panda_dataset import PandaDataset
+from health_cpath.datasets.panda_tiles_dataset import PandaTilesDataset
 
 
 class PandaTilesDataModule(TilesDataModule):

hi-ml-cpath/src/health_cpath/datamodules/panda_module_benchmark.py

@@ -12,8 +12,8 @@ from typing import Tuple
 
 from health_ml.utils.split_dataset import DatasetSplits
 
-from histopathology.datamodules.base_module import SlidesDataModule
-from histopathology.datasets.panda_dataset import PandaDataset
+from health_cpath.datamodules.base_module import SlidesDataModule
+from health_cpath.datasets.panda_dataset import PandaDataset
 
 
 class PandaSlidesDataModuleBenchmark(SlidesDataModule):

hi-ml-cpath/src/health_cpath/datamodules/tcga_crck_module.py

@@ -7,8 +7,8 @@ from typing import Tuple
 
 from health_ml.utils.split_dataset import DatasetSplits
 
-from histopathology.datamodules.base_module import TilesDataModule
-from histopathology.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDataset
+from health_cpath.datamodules.base_module import TilesDataModule
+from health_cpath.datasets.tcga_crck_tiles_dataset import TcgaCrck_TilesDataset
 
 
 class TcgaCrckTilesDataModule(TilesDataModule):

hi-ml-cpath/src/health_cpath/datasets/base_dataset.py

@@ -12,7 +12,7 @@ import torch
 from sklearn.utils.class_weight import compute_class_weight
 from torch.utils.data import Dataset
 
-from histopathology.utils.naming import SlideKey
+from health_cpath.utils.naming import SlideKey
 
 
 class TilesDataset(Dataset):

hi-ml-cpath/src/health_cpath/datasets/panda_dataset.py

@@ -13,7 +13,7 @@ from monai.transforms import MapTransform
 
 from health_ml.utils import box_utils
 
-from histopathology.datasets.base_dataset import SlidesDataset
+from health_cpath.datasets.base_dataset import SlidesDataset
 
 try:
     from cucim import CuImage

hi-ml-cpath/src/health_cpath/datasets/panda_tiles_dataset.py

@@ -9,9 +9,9 @@ from typing import Any, Callable, Optional, Tuple, Union
 import pandas as pd
 from torchvision.datasets.vision import VisionDataset
 
-from histopathology.datasets.base_dataset import TilesDataset
-from histopathology.models.transforms import load_pil_image
-from histopathology.utils.naming import TileKey
+from health_cpath.datasets.base_dataset import TilesDataset
+from health_cpath.models.transforms import load_pil_image
+from health_cpath.utils.naming import TileKey
 
 from SSL.data.dataset_cls_utils import DataClassBaseWithReturnIndex
 

hi-ml-cpath/src/health_cpath/datasets/tcga_crck_tiles_dataset.py

@@ -10,8 +10,8 @@ import pandas as pd
 
 from torchvision.datasets.vision import VisionDataset
 
-from histopathology.datasets.base_dataset import TilesDataset
-from histopathology.models.transforms import load_pil_image
+from health_cpath.datasets.base_dataset import TilesDataset
+from health_cpath.models.transforms import load_pil_image
 from SSL.data.dataset_cls_utils import DataClassBaseWithReturnIndex
 
 

hi-ml-cpath/src/health_cpath/datasets/tcga_prad_dataset.py

@@ -8,7 +8,7 @@ from typing import Optional, Union
 
 import pandas as pd
 
-from histopathology.datasets.base_dataset import SlidesDataset
+from health_cpath.datasets.base_dataset import SlidesDataset
 
 
 class TcgaPradDataset(SlidesDataset):

hi-ml-cpath/src/health_cpath/models/deepmil.py

@@ -13,13 +13,13 @@ from torchmetrics import AUROC, F1, Accuracy, ConfusionMatrix, Precision, Recall
 
 from health_ml.utils import log_on_epoch
 from health_ml.deep_learning_config import OptimizerParams
-from histopathology.models.encoders import IdentityEncoder
-from histopathology.utils.deepmil_utils import EncoderParams, PoolingParams
+from health_cpath.models.encoders import IdentityEncoder
+from health_cpath.utils.deepmil_utils import EncoderParams, PoolingParams
 
-from histopathology.datasets.base_dataset import TilesDataset
-from histopathology.utils.naming import MetricsKey, ResultsKey, SlideKey, ModelKey, TileKey
-from histopathology.utils.output_utils import (BatchResultsType, DeepMILOutputsHandler, EpochResultsType,
-                                               validate_class_names)
+from health_cpath.datasets.base_dataset import TilesDataset
+from health_cpath.utils.naming import MetricsKey, ResultsKey, SlideKey, ModelKey, TileKey
+from health_cpath.utils.output_utils import (BatchResultsType, DeepMILOutputsHandler, EpochResultsType,
+                                             validate_class_names)
 
 RESULTS_COLS = [ResultsKey.SLIDE_ID, ResultsKey.TILE_ID, ResultsKey.IMAGE_PATH, ResultsKey.PROB,
                 ResultsKey.CLASS_PROBS, ResultsKey.PRED_LABEL, ResultsKey.TRUE_LABEL, ResultsKey.BAG_ATTN]

hi-ml-cpath/src/health_cpath/models/encoders.py

@@ -13,9 +13,9 @@ from torch import Tensor as T, nn
 from torchvision.models import resnet18
 from torchvision.transforms import Compose
 
-from histopathology.utils.layer_utils import (get_imagenet_preprocessing,
-                                              load_weights_to_model,
-                                              setup_feature_extractor)
+from health_cpath.utils.layer_utils import (get_imagenet_preprocessing,
+                                            load_weights_to_model,
+                                            setup_feature_extractor)
 from SSL.lightning_modules.ssl_classifier_module import SSLClassifier
 from SSL.utils import create_ssl_image_classifier
 from SSL import encoders

hi-ml-cpath/src/health_cpath/models/transforms.py

@@ -13,7 +13,7 @@ from monai.config.type_definitions import KeysCollection
 from monai.transforms.transform import MapTransform, Randomizable
 from torchvision.transforms.functional import to_tensor
 
-from histopathology.models.encoders import TileEncoder
+from health_cpath.models.encoders import TileEncoder
 
 PathOrString = Union[Path, str]
 

hi-ml-cpath/src/health_cpath/preprocessing/create_panda_tiles_dataset.py

@@ -23,9 +23,9 @@ from monai.data.image_reader import WSIReader
 from tqdm import tqdm
 from health_ml.utils.box_utils import Box
 
-from histopathology.preprocessing import tiling
-from histopathology.utils.naming import SlideKey, TileKey
-from histopathology.datasets.panda_dataset import PandaDataset, LoadPandaROId
+from health_cpath.preprocessing import tiling
+from health_cpath.utils.naming import SlideKey, TileKey
+from health_cpath.datasets.panda_dataset import PandaDataset, LoadPandaROId
 
 CSV_COLUMNS = (
     'slide_id',

hi-ml-cpath/src/health_cpath/preprocessing/create_tiles_dataset.py

@@ -17,10 +17,10 @@ from monai.data import Dataset
 from monai.data.image_reader import WSIReader
 from tqdm import tqdm
 
-from histopathology.datasets.base_dataset import SlidesDataset
-from histopathology.preprocessing import tiling
-from histopathology.preprocessing.loading import LoadROId, segment_foreground
-from histopathology.utils.naming import SlideKey, TileKey
+from health_cpath.datasets.base_dataset import SlidesDataset
+from health_cpath.preprocessing import tiling
+from health_cpath.preprocessing.loading import LoadROId, segment_foreground
+from health_cpath.utils.naming import SlideKey, TileKey
 
 logging.basicConfig(format='%(asctime)s %(message)s', filemode='w')
 logger = logging.getLogger()
@@ -291,7 +291,7 @@ def main(slides_dataset: SlidesDataset, root_output_dir: Union[str, Path],
 
 
 if __name__ == '__main__':
-    from histopathology.datasets.tcga_prad_dataset import TcgaPradDataset
+    from health_cpath.datasets.tcga_prad_dataset import TcgaPradDataset
 
     # Example set up for an existing slides dataset:
     main(slides_dataset=TcgaPradDataset("/tmp/datasets/TCGA-PRAD"),

hi-ml-cpath/src/health_cpath/preprocessing/loading.py

@@ -12,7 +12,7 @@ from health_ml.utils import box_utils
 from monai.data.image_reader import WSIReader
 from monai.transforms import MapTransform
 
-from histopathology.utils.naming import SlideKey
+from health_cpath.utils.naming import SlideKey
 
 
 def get_luminance(slide: np.ndarray) -> np.ndarray:

hi-ml-cpath/src/health_cpath/scripts/generate_crossval_report.py

@@ -11,16 +11,16 @@ from matplotlib import pyplot as plt
 
 from health_azure.utils import get_aml_run_from_run_id, get_workspace
 from health_ml.utils.reports import HTMLReport
-from histopathology.utils.analysis_plot_utils import (add_training_curves_legend, plot_confusion_matrices,
-                                                      plot_crossval_roc_and_pr_curves,
-                                                      plot_crossval_training_curves)
-from histopathology.utils.output_utils import (AML_LEGACY_TEST_OUTPUTS_CSV, AML_TEST_OUTPUTS_CSV,
-                                               AML_VAL_OUTPUTS_CSV)
-from histopathology.utils.report_utils import (collect_crossval_metrics, collect_crossval_outputs,
-                                               crossval_runs_have_val_and_test_outputs, get_best_epoch_metrics,
-                                               get_best_epochs, get_crossval_metrics_table, get_formatted_run_info,
-                                               collect_class_info)
-from histopathology.utils.naming import MetricsKey, ModelKey
+from health_cpath.utils.analysis_plot_utils import (add_training_curves_legend, plot_confusion_matrices,
+                                                    plot_crossval_roc_and_pr_curves,
+                                                    plot_crossval_training_curves)
+from health_cpath.utils.output_utils import (AML_LEGACY_TEST_OUTPUTS_CSV, AML_TEST_OUTPUTS_CSV,
+                                             AML_VAL_OUTPUTS_CSV)
+from health_cpath.utils.report_utils import (collect_crossval_metrics, collect_crossval_outputs,
+                                             crossval_runs_have_val_and_test_outputs, get_best_epoch_metrics,
+                                             get_best_epochs, get_crossval_metrics_table, get_formatted_run_info,
+                                             collect_class_info)
+from health_cpath.utils.naming import MetricsKey, ModelKey
 
 
 def generate_html_report(parent_run_id: str, output_dir: Path,

hi-ml-cpath/src/health_cpath/scripts/tcga_dataset_prep.py

@@ -5,10 +5,10 @@
 from pathlib import Path
 
 import pandas as pd
-from histopathology.datasets.default_paths import TCGA_CRCK_DATASET_ID
+from health_cpath.datasets.default_paths import TCGA_CRCK_DATASET_ID
 
-from histopathology.utils.tcga_utils import extract_fields
-from histopathology.datasets.tcga_prad_dataset import TcgaPradDataset
+from health_cpath.utils.tcga_utils import extract_fields
+from health_cpath.datasets.tcga_prad_dataset import TcgaPradDataset
 
 
 def check_dataset_csv_paths(dataset_dir: Path) -> None:

hi-ml-cpath/src/health_cpath/utils/analysis_plot_utils.py

@@ -17,7 +17,7 @@ import seaborn as sns
 from sklearn.manifold import TSNE
 from sklearn.metrics import auc, precision_recall_curve, roc_curve, confusion_matrix
 
-from histopathology.utils.naming import ResultsKey
+from health_cpath.utils.naming import ResultsKey
 
 TRAIN_STYLE = dict(ls='-')
 VAL_STYLE = dict(ls='--')

hi-ml-cpath/src/health_cpath/utils/deepmil_utils.py

@@ -8,7 +8,7 @@ from torch import nn
 from pathlib import Path
 from typing import Optional, Tuple
 from torchvision.models.resnet import resnet18, resnet50
-from histopathology.models.encoders import (
+from health_cpath.models.encoders import (
     HistoSSLEncoder,
     ImageNetEncoder,
     ImageNetEncoder_Resnet50,
@@ -16,7 +16,7 @@ from histopathology.models.encoders import (
     SSLEncoder,
     TileEncoder,
 )
-from histopathology.utils.download_utils import get_checkpoint_downloader
+from health_cpath.utils.download_utils import get_checkpoint_downloader
 from health_ml.networks.layers.attention_layers import (
     AttentionLayer,
     GatedAttentionLayer,

hi-ml-cpath/src/health_cpath/utils/girder.py

@@ -35,8 +35,8 @@ from girder_client import GirderClient
 from health_azure.logging import logging_to_stdout
 from health_azure.utils import get_aml_run_from_run_id
 
-from histopathology.utils.naming import ResultsKey
-from histopathology.utils.output_utils import AML_TEST_OUTPUTS_CSV
+from health_cpath.utils.naming import ResultsKey
+from health_cpath.utils.output_utils import AML_TEST_OUTPUTS_CSV
 
 
 TypeRectangleJSON = Dict[str, Union[str, float, Dict[str, str]]]