Kaggle nucleiseg

segmentation/kaggle-nuclei-segmentation-tool/.bumpversion.cfg

@@ -0,0 +1,29 @@
+[bumpversion]
+current_version = 0.1.5-dev1
+commit = False
+tag = False
+parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
+serialize = 
+	{major}.{minor}.{patch}-{release}{dev}
+	{major}.{minor}.{patch}
+
+[bumpversion:part:release]
+optional_value = _
+first_value = dev
+values = 
+	dev
+	_
+
+[bumpversion:part:dev]
+
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
+
+[bumpversion:file:VERSION]
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:plugin.json]
+
+[bumpversion:file:src/polus/images/segmentation/kaggle_nuclei_segmentation/__init__.py]

segmentation/kaggle-nuclei-segmentation-tool/.dockerignore

@@ -0,0 +1,4 @@
+.venv
+out
+tests
+__pycache__

segmentation/kaggle-nuclei-segmentation-tool/.gitignore

@@ -0,0 +1 @@
+poetry.lock

segmentation/kaggle-nuclei-segmentation-tool/CHANGELOG.md

@@ -0,0 +1,5 @@
+# CHANGELOG
+
+## 0.1.5-dev1
+
+Initial release.

segmentation/kaggle-nuclei-segmentation-tool/Dockerfile

@@ -0,0 +1,23 @@
+FROM polusai/bfio:2.1.9
+
+# environment variables defined in polusai/bfio
+ENV EXEC_DIR="/opt/executables"
+ENV POLUS_IMG_EXT=".ome.tif"
+ENV POLUS_TAB_EXT=".csv"
+ENV POLUS_LOG="INFO"
+
+
+# Work directory defined in the base container
+WORKDIR ${EXEC_DIR}
+
+COPY pyproject.toml ${EXEC_DIR}
+COPY VERSION ${EXEC_DIR}
+COPY README.md ${EXEC_DIR}
+COPY src ${EXEC_DIR}/src
+
+RUN pip3 install ${EXEC_DIR} --no-cache-dir
+
+
+# Default command. Additional arguments are provided through the command line
+ENTRYPOINT ["python3", "-m", "polus.images.segmentation.kaggle_nuclei_segmentation"]
+CMD ["--help"]

segmentation/kaggle-nuclei-segmentation-tool/README.md

@@ -0,0 +1,29 @@
+# Kaggle Nuclei Segmentation (v0.1.5-dev1)
+
+Segments cell nuclei using U-Net in Tensorflow.
+
+# Reference
+Credits neural network architecture and pretrained model weights : https://github.com/axium/Data-Science-Bowl-2018
+
+# Description
+This WIPP plugin segments cell nuclei using U-Net in Tensorflow. Neural net architecture and pretrained weights are taken from Data Science Bowl 2018 entry by Muhammad Asim (reference given above). The unet expects the input height and width to be 256 pixels. To ensure that the plugin is able to handle images of all sizes, it adds reflective padding to the input to make the dimensions a multiple of 256. Following this a loop extracts 256x256 tiles to be processed by the network. In the end it untiles and removes padding from the output.
+
+## Building
+
+To build the Docker image for the conversion plugin, run `./build-docker.sh`.
+
+## Install WIPP Plugin
+
+If WIPP is running, navigate to the plugins page and add a new plugin. Paste the
+contents of `plugin.json` into the pop-up window and submit.
+
+## Options
+
+This plugin takes 3 input arguments and 1 output argument:
+
+| Name          | Description             | I/O    | Type   | Default |
+|---------------|-------------------------|--------|--------|--------- |
+| `--inpDir`       | Input image collection to be processed by this plugin | Input | collection |
+| `--filePattern`  | Filename pattern used to separate data | Input | string | .* |
+| `--outDir`       | Output collection | Output | collection |
+| `--preview`  | Generate an output preview | Input | boolean | False |

segmentation/kaggle-nuclei-segmentation-tool/VERSION

@@ -0,0 +1 @@
+0.1.5-dev1

segmentation/kaggle-nuclei-segmentation-tool/build-docker.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+version=$(<VERSION)
+docker build . -t polusai/kaggle-nuclei-segmentation-tool:${version}

segmentation/kaggle-nuclei-segmentation-tool/plugin.json

@@ -0,0 +1,63 @@
+{
+  "name": "Kaggle Nuclei Segmentation",
+  "version": "0.1.5-dev1",
+  "title": "Kaggle Nuclei Segmentation",
+  "description": "Segments cell nuclei using U-Net in Tensorflow. Neural net architecture and pretrained weights are taken from Data Science Bowl 2018 entry by Muhammad Asim",
+  "author": "Gauhar Bains,  Konstantin Taletskiy,Nick Schaub , Hamdah Shafqat Abbasi (gauhar.bains@labshare.org, Konstantin.Taletskiy@labshare.org, nick.schaub@nih.gov, hamdahshafqat.abbasi@nih.gov)",
+  "institution": "National Center for Advancing Translational Sciences, National Institutes of Health",
+  "repository": "https://github.com/PolusAI/image-tools",
+  "website": "https://ncats.nih.gov/preclinical/core/informatics",
+  "citation": "",
+  "containerId": "polusai/kaggle-nuclei-segmentation-tool:0.1.5-dev1",
+  "baseCommand": [
+    "python3",
+    "-m",
+    "polus.images.segmentation.kaggle_nuclei_segmentation"
+  ],
+  "inputs": [
+    {
+      "name": "inpDir",
+      "type": "collection",
+      "description": "Input image collection to be processed by this plugin",
+      "required": true
+    },
+    {
+      "name": "filePattern",
+      "type": "string",
+      "description": "Filename pattern used to separate data",
+      "required": false,
+      "default": ".*"
+    },
+    {
+      "name": "preview",
+      "type": "boolean",
+      "description": "Generate an output preview.",
+      "required": false
+    }
+  ],
+  "outputs": [
+    {
+      "name": "outDir",
+      "type": "collection",
+      "description": "Output collection"
+    }
+  ],
+  "ui": [
+    {
+      "key": "inputs.inpDir",
+      "title": "Input collection",
+      "description": "Input image collection to be processed by this plugin"
+    },
+    {
+      "key": "inputs.filePattern",
+      "title": "Filename pattern",
+      "description": "Filename pattern used to separate data",
+      "default": ".*"
+    },
+    {
+      "key": "inputs.preview",
+      "title": "preview",
+      "description": "Generate an output preview."
+    }
+  ]
+}

segmentation/kaggle-nuclei-segmentation-tool/pyproject.toml

@@ -0,0 +1,35 @@
+[tool.poetry]
+name = "polus-images-segmentation-kaggle-nuclei-segmentation"
+version = "0.1.5-dev1"
+description = "Segments cell nuclei using U-Net in Tensorflow. Neural net architecture and pretrained weights are taken from Data Science Bowl 2018 entry by Muhammad Asim"
+authors = ["Gauhar Bains,  Konstantin Taletskiy,Nick Schaub , Hamdah Shafqat Abbasi <gauhar.bains@labshare.org, Konstantin.Taletskiy@labshare.org, nick.schaub@nih.gov, hamdahshafqat.abbasi@nih.gov>"]
+readme = "README.md"
+packages = [{include = "polus", from = "src"}]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<3.12"
+bfio = {version = "2.1.9", extras = ["all"]}
+filepattern = ">=2.0.4,<3.0"
+typer = "^0.7.0"
+tensorflow = "^2.15.0"
+opencv-python-headless = "^4.9.0.80"
+
+[tool.poetry.group.dev.dependencies]
+bump2version = "^1.0.1"
+pytest = "^7.4"
+pytest-sugar = "^0.9.6"
+pre-commit = "^3.2.1"
+black = "^23.3.0"
+mypy = "^1.1.1"
+ruff = "^0.0.270"
+ipykernel = "^6.29.0"
+scikit-image = "0.19.3"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+pythonpath = [
+  "."
+]

segmentation/kaggle-nuclei-segmentation-tool/run-plugin.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+
+version=$(<VERSION)
+
+# Update with your data
+inpDir=/tmp/path/to/input
+outDir=/tmp/path/to/output
+filepattern=".*"
+
+
+container_input_dir="/inpDir"
+container_output_dir="/outDir"
+
+docker run -v $inpDir:/${container_input_dir} \
+           -v $outDir:/${container_output_dir} \
+            --user $(id -u):$(id -g) \
+            polusai/kaggle-nuclei-segmentation-plugin:${version} \
+            --inpDir ${container_input_dir} \
+            --filePattern ${filepattern} \
+            --outDir ${container_output_dir}

segmentation/kaggle-nuclei-segmentation-tool/src/polus/images/segmentation/kaggle_nuclei_segmentation/__init__.py

@@ -0,0 +1,3 @@
+"""Kaggle Nuclei Segmentation."""
+
+__version__ = "0.1.5-dev"

segmentation/kaggle-nuclei-segmentation-tool/src/polus/images/segmentation/kaggle_nuclei_segmentation/__main__.py

@@ -0,0 +1,103 @@
+"""Kaggle Nuclei Segmentation."""
+
+# Base packages
+import json
+import logging
+from os import environ
+from pathlib import Path
+from typing import Any
+
+import filepattern as fp
+import typer
+from polus.images.segmentation.kaggle_nuclei_segmentation.segment import segment
+
+logging.basicConfig(
+    format="%(asctime)s - %(name)-8s - %(levelname)-8s - %(message)s",
+    datefmt="%d-%b-%y %H:%M:%S",
+)
+POLUS_LOG = getattr(logging, environ.get("POLUS_LOG", "INFO"))
+logger = logging.getLogger("polus.images.segmentation.kaggle_nuclei_segmentation")
+logger.setLevel(POLUS_LOG)
+POLUS_IMG_EXT = environ.get("POLUS_IMG_EXT", ".ome.tif")
+BATCH_SIZE = 20
+app = typer.Typer(help="Kaggle Nuclei Segmentation.")
+
+
+def generate_preview(
+    inp_dir: Path,
+    file_pattern: str,
+    out_dir: Path,
+) -> None:
+    """Generate preview of the plugin outputs."""
+    fps = fp.FilePattern(inp_dir, file_pattern)
+    out_file = out_dir.joinpath("preview.json")
+    with Path.open(out_file, "w") as jfile:
+        out_json: dict[str, Any] = {
+            "filepattern": file_pattern,
+            "outDir": [],
+        }
+        for file in fps():
+            out_name = str(file[1][0])
+            out_json["outDir"].append(out_name)
+        json.dump(out_json, jfile, indent=2)
+    logger.info(f"generating preview data in {out_dir}")
+
+
+@app.command()
+def main(
+    inp_dir: Path = typer.Option(
+        ...,
+        "--inpDir",
+        "-i",
+        help="Input directory to be processed.",
+        exists=True,
+        readable=True,
+        file_okay=False,
+        resolve_path=True,
+    ),
+    file_pattern: str = typer.Option(
+        ".*",
+        "--filePattern",
+        "-f",
+        help="Filepattern used to filter inputs.",
+    ),
+    out_dir: Path = typer.Option(
+        ...,
+        "--outDir",
+        "-o",
+        help="Output directory.",
+        exists=True,
+        writable=True,
+        file_okay=False,
+        resolve_path=True,
+    ),
+    preview: bool = typer.Option(
+        False,
+        "--preview",
+        "-v",
+        help="Preview of expected outputs (dry-run)",
+        show_default=False,
+    ),
+) -> None:
+    """Kaggle Nuclei Segmentation."""
+    logger.info(f"inpDir: {inp_dir}")
+    logger.info(f"filePattern: {file_pattern}")
+    logger.info(f"outDir: {out_dir}")
+
+    if preview:
+        generate_preview(inp_dir, file_pattern, out_dir)
+        logger.info(f"generating preview data in : {out_dir}.")
+
+    if not preview:
+        fps = fp.FilePattern(inp_dir, file_pattern)
+        files = [str(file[1][0]) for file in fps()]
+        for ind in range(0, len(files), BATCH_SIZE):
+            logger.info("{:.2f}% complete...".format(100 * ind / len(files)))
+            batch = ",".join(files[ind : min([ind + BATCH_SIZE, len(files)])])
+            segment(batch, out_dir)
+
+        logger.info("100% complete...")
+
+
+if __name__ == "__main__":
+    app()