Feat/qupath (#209)

* added qupath flag in CLI tool, create project if flag is true

* added paquo dependency, formatted code

* moved qupath output directory under results_dir, moved paquo to optional dependencies

* created qupath extra in optional dependencies

* Update pyproject.toml

* removed type QuPathProject

* handled paquo import using global variable HAS_PAQUO

* included paquo in mypy ignored modules

* checck if qupath_proj is object

* ignore qupath_proj type

* reformatted code

* made paquo import global

---------

Co-authored-by: Jakub Kaczmarzyk <[email protected]>

.gitignore

@@ -172,5 +172,9 @@ cython_debug/
 # Version
 /wsinfer/_version.py
 
+#QuPath Project
+model-outputs-qupath/
+*.backup
+
 # Extras
 .DS_Store

pyproject.toml

@@ -80,6 +80,7 @@ docs = [
     "sphinx-copybutton",
 ]
 openslide = ["openslide-python"]
+qupath = ["paquo"]
 
 [project.urls]
 Homepage = "https://wsinfer.readthedocs.io"
@@ -125,6 +126,7 @@ module = [
     "skimage.morphology",
     "tifffile",
     "zarr.storage",
+    "paquo.*"
 ]
 ignore_missing_imports = "True"
 

wsinfer/cli/infer.py

@@ -24,6 +24,7 @@
 from ..modellib.run_inference import run_inference
 from ..patchlib import segment_and_patch_directory_of_slides
 from ..write_geojson import write_geojsons
+from ..qupath import make_qupath_project
 
 
 def _num_cpus() -> int:
@@ -252,6 +253,13 @@ def get_stdout(args: list[str]) -> str:
     help="JIT-compile the model and apply inference optimizations. This imposes a"
     " startup cost but may improve performance overall.",
 )
+@click.option(
+    "--qupath",
+    is_flag=True,
+    default=False,
+    show_default=True,
+    help="Create a QuPath project containing the inference results",
+)
 def run(
     ctx: click.Context,
     *,
@@ -263,6 +271,7 @@ def run(
     batch_size: int,
     num_workers: int = 0,
     speedup: bool = False,
+    qupath: bool = False,
 ) -> None:
     """Run model inference on a directory of whole slide images.
 
@@ -378,3 +387,5 @@ def run(
 
     csvs = list((results_dir / "model-outputs-csv").glob("*.csv"))
     write_geojsons(csvs, results_dir, num_workers)
+    if qupath:
+        make_qupath_project(wsi_dir, results_dir)

wsinfer/qupath.py

@@ -0,0 +1,71 @@
+from __future__ import annotations
+
+import sys
+import json
+from pathlib import Path
+
+try:
+    from paquo.projects import QuPathProject
+
+    HAS_PAQUO = True
+except Exception:
+    HAS_PAQUO = False
+
+
+def add_image_and_geojson(
+    qupath_proj: QuPathProject,
+    *,
+    image_path: Path | str,
+    geojson_path: Path | str,
+) -> None:
+    with open(geojson_path) as f:
+        try:
+            geojson_features = json.load(f)["features"]
+        except Exception as e:
+            print(f"Unable to find features key:: {e}")
+
+    entry = qupath_proj.add_image(image_path)
+    try:
+        entry.hierarchy.load_geojson(geojson_features)
+    except Exception as e:
+        print(f"Failed to run load_geojson function with error:: {e}")
+
+
+def make_qupath_project(wsi_dir: Path, results_dir: Path) -> None:
+    if not HAS_PAQUO:
+        print(
+            """Cannot find QuPath.
+QuPath is required to use this functionality but it cannot be found.
+If QuPath is installed, please use define the environment variable
+PAQUO_QUPATH_DIR with the location of the QuPath installation.
+If QuPath is not installed, please install it from https://qupath.github.io/."""
+        )
+        sys.exit(1)
+    else:
+        print("Found QuPath successfully!")
+        QUPATH_PROJECT_DIRECTORY = results_dir / "model-outputs-qupath"
+
+        csv_files = list((results_dir / "model-outputs-csv").glob("*.csv"))
+        slides_and_geojsons = []
+
+        for csv_file in csv_files:
+            file_name = csv_file.stem
+
+            json_file = results_dir / "model-outputs-geojson" / (file_name + ".json")
+            image_file = wsi_dir / (file_name + ".svs")
+
+            if json_file.exists() and image_file.exists():
+                matching_pair = (image_file, json_file)
+                slides_and_geojsons.append(matching_pair)
+            else:
+                print(f"Skipping CSV: {csv_file.name} (No corresponding JSON)")
+
+        with QuPathProject(QUPATH_PROJECT_DIRECTORY, mode="w") as qp:
+            for image_path, geojson_path in slides_and_geojsons:
+                try:
+                    add_image_and_geojson(
+                        qp, image_path=image_path, geojson_path=geojson_path
+                    )
+                except Exception as e:
+                    print(f"Failed to add image/geojson with error:: {e}")
+        print("Successfully created QuPath Project!")