MHub / GC - Add the GC Tiger challenge winner LB2 model

models/gc_tiger_lb2/__init__.py

@@ -0,0 +1 @@
+from .utils import *

models/gc_tiger_lb2/config/default.yml

@@ -0,0 +1,31 @@
+general:
+  data_base_dir: /app/data
+  version: 1.0
+  description: Tiger challenge winner LB2 (dicom:sm to json with TIL score)
+
+execute:
+- DicomImporter
+- TiffConverter
+- TigerLB2Runner
+- ReportExporter
+- DataOrganizer
+
+modules:
+  DicomImporter:
+    source_dir: input_data
+    import_dir: sorted_data
+    sort_data: True
+    meta: 
+      mod: sm
+
+  ReportExporter:
+    includes:
+    - data: til_score
+      label: TIL score
+      value: value
+
+  DataOrganizer:
+    target_dir: output_data
+    require_data_confirmation: true
+    targets:
+      - json-->[i:sid]/gc_tiger_lb2_til_score.json

models/gc_tiger_lb2/config/tiff_pipeline.yml

@@ -0,0 +1,21 @@
+general:
+  data_base_dir: /app/data
+  version: 1.0
+  description: Tiger challenge winner LB2 (tiff:sm to json with TIL score)
+
+execute:
+- FileStructureImporter
+- TigerLB2Runner
+- DataOrganizer
+
+modules:
+  FileStructureImporter:
+    input_dir: input_data
+    structures:
+      - $instanceID@instance/wsi.tif@tiff:mod=sm
+
+  DataOrganizer:
+    target_dir: output_data
+    require_data_confirmation: true
+    targets:
+      - json-->[i:instanceID]/gc_tiger_lb2_til_score.json

models/gc_tiger_lb2/dockerfiles/Dockerfile

@@ -0,0 +1,54 @@
+# Specify the base image for the environment
+FROM mhubai/base:latest
+
+# Specify/override authors label
+LABEL authors="[email protected]"
+
+# install required dependencies for algorithm
+RUN pip3 install --no-cache-dir torch==2.0.1+cu118 torchvision==0.15.2+cu118 -f https://download.pytorch.org/whl/torch_stable.html
+
+# Install ASAP
+RUN apt-get update \
+    && apt-get -y install curl libpython3.8-dev \
+    && curl --remote-name --location "https://github.com/computationalpathologygroup/ASAP/releases/download/ASAP-2.1/ASAP-2.1-py38-Ubuntu2004.deb" \
+    && dpkg --install ASAP-2.1-py38-Ubuntu2004.deb || true \
+    && apt-get -f install --fix-missing --fix-broken --assume-yes \
+    && ldconfig -v \
+    && apt-get clean \
+    && echo "/opt/ASAP/bin" > /usr/local/lib/python3.8/dist-packages/asap.pth \
+    && rm ASAP-2.1-py38-Ubuntu2004.deb
+
+# Install tiger LB2 algorithm
+#   - Clone tiger LB2 codebase (master branch, fixed to commit 720f8dfca4624792c8e57915c4222efec5a0c2d4)
+#   - Subsequently we remove the .git directory to procuce a compacter docker layer
+RUN git clone https://github.com/vuno/tiger_challenge.git /vuno && \
+    cd /vuno && git reset --hard 720f8dfca4624792c8e57915c4222efec5a0c2d4 && \
+    rm -rf /vuno/.git
+
+# Install tiger LB2 dependencies
+RUN pip3 install --no-cache-dir -r /vuno/requirements.txt
+
+# Reinstall correct version of Numpy to function with ASAP 2.1
+RUN pip3 install --no-cache-dir --force-reinstall numpy==1.22
+
+# Enforce minimum version of panimg (with WSI fix)
+RUN pip3 install --no-cache-dir panimg>=0.13.2
+
+# Download and install model weights file from zenodo
+RUN rm -rf /vuno/pretrained_weights && \
+    wget https://zenodo.org/record/8112176/files/pretrained_weights.zip -O /vuno/pretrained_weights.zip && \
+    unzip /vuno/pretrained_weights.zip -d /vuno && \
+    rm /vuno/pretrained_weights.zip
+
+# Clone the main branch of MHubAI/models TODO
+#RUN git stash \
+# && git sparse-checkout set "models/gc_tiger_lb2" \
+# && git fetch https://github.com/MHubAI/models.git main \
+# && git merge FETCH_HEAD
+
+# Add model and algorithm code bases to python path
+ENV PYTHONPATH="/vuno:/app"
+
+# Set default entrypoint
+ENTRYPOINT ["python3", "-m", "mhubio.run"]
+CMD ["--config", "/app/models/gc_tiger_lb2/config/default.yml"]

models/gc_tiger_lb2/meta.json

@@ -0,0 +1,113 @@
+{
+  "id": "c5397909-0397-489f-8744-6bf3952e9a1c",
+  "name": "tiger_lb2",
+  "title": "TIGER challenge winner: Team VUNO",
+  "summary": {
+    "description": "Participants in the TIGER challenge will have to develop computer algorithms to analyze H&E-stained whole-slide images of breast cancer histopathology, to perform three tasks:  detection of lymphocytes and plasma cells, which are the main types of cells considered as tumor-infiltrating lymphocytes; segmentation of invasive tumor and tumor-associated stroma, which are the main tissue compartments considered when identifying relevant regions for the TILs; compute an automated TILs score, one score per slide, based on the output of detection and segmentation.",
+    "inputs": [
+      {
+        "label": "Whole-slide image",
+        "description": "H&E-stained whole-slide image of breast cancer histopathology",
+        "format": "DICOM",
+        "modality": "SM",
+        "bodypartexamined": "Breast",
+        "slicethickness": "",
+        "non-contrast": false,
+        "contrast": false
+      }
+    ],
+    "outputs": [
+      {
+        "type": "Prediction",
+        "valueType": "Probability",
+        "label": "TIL score",
+        "description": "Percentage of stromal area covered by tumour infiltrating lymphocytes. Values between 0 (percent) to 100 (percent).",
+        "classes": []
+      }
+    ],
+    "model": {
+      "architecture": "Combination of multiple U-Nets with EfficientNet B2/B0 encoders, and YOLOv5 networks for detection.",
+      "training": "supervised",
+      "cmpapproach": "2D"
+    },
+    "data": {
+      "training": {
+        "vol_samples": 230
+      },
+      "evaluation": {
+        "vol_samples": 58
+      },
+      "public": false,
+      "external": false
+    }
+  },
+  "details": {
+    "name": "LB2",
+    "version": "55c49c9e-4216-4142-b1c8-f5d85781add3",
+    "devteam": "VUNO",
+    "type": "Segmentation/Prediction hybrid",
+    "date": {
+      "weights": "2023-07-06",
+      "code": "2023-07-06",
+      "pub": "2022-08-26"
+    },
+    "cite": "",
+    "license": {
+      "code": "Apache 2.0",
+      "weights": "CC BY-NC 4.0"
+    },
+    "publications": [],
+    "github": "https://github.com/vuno/tiger_challenge",
+    "zenodo": "https://doi.org/10.5281/zenodo.8112147",
+    "colab": "",
+    "slicer": false
+  },
+  "info": {
+    "use": {
+      "title": "Intended use",
+      "text": "Prediction of the percentage of stomal area covered by tumour infiltrating lymphocytes on H&E-stained whole-slide image of breast cancer histopathology.",
+      "references": [],
+      "tables": []
+    },
+    "analyses": {
+      "title": "Evaluation",
+      "text": "The prognostic value of the automatic \"TIL score\" generated by the submitted algorithms were computed for the test set. This was done by building a multivariate Cox regression model trained with predefined clinical variables and the produced TILs score. The concordance index (Uno’s C-index) of this model was computed and the algorithms were ranked based on its value. ",
+      "references": [
+        {
+          "label": "On the C-statistics for Evaluating Overall Adequacy of Risk Prediction Procedures with Censored Survival Data",
+          "uri": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3079915/"
+        }
+      ],
+      "tables": []
+    },
+    "evaluation": {
+      "title": "Evaluation data",
+      "text": "The test set consists of a separate dataset of n=707 H&E-stained whole-slide breast cancer histopathology images",
+      "references": [],
+      "tables": []
+    },
+    "training": {
+      "title": "Training data",
+      "text": "For the TIGER challenge three public training datasets were made available: 1. WSIROIS: Whole-slide images with manual annotations in regions of interest  2. WSIBULK: Whole-slide images with coarse manual annotation of the tumor bulk  3. WSITILS: Whole-slide images with visual estimation of the TILs at slide level",
+      "references": [
+        {
+          "label": "WSIROIS, WSIBULK, WSITILS on AWS Open Data",
+          "uri": "https://registry.opendata.aws/tiger/"
+        }
+      ],
+      "tables": []
+    },
+    "ethics": {
+      "title": "",
+      "text": "",
+      "references": [],
+      "tables": []
+    },
+    "limitations": {
+      "title": "Limitations",
+      "text": "This algorithm was developed for research purposes only.",
+      "references": [],
+      "tables": []
+    }
+  }
+}

models/gc_tiger_lb2/scripts/tiger_lb2_cli.py

@@ -0,0 +1,50 @@
+"""
+--------------------------------------------------------
+Mhub / DIAG - CLI Run script for the TIGER LB2 Algorithm
+--------------------------------------------------------
+
+--------------------------------------------------------
+Author: Sil van de Leemput
+Email:  [email protected]
+--------------------------------------------------------
+"""
+
+import argparse
+from pathlib import Path
+
+import torch
+
+# The required pipeline methods are imported from the tiger_challenge repository
+# The algorithm.rw module is imported for IO operations
+import pipeline.tils_pipeline as tils_pipeline
+import algorithm.rw as rw
+
+
+def tiger_lb2_cli() -> None:
+    parser = argparse.ArgumentParser("Tiger LB2 Run CLI")
+    parser.add_argument("input_file", type=str, help="Input WSI TIFF file path")
+    parser.add_argument("output_file", type=str, help="Output JSON file path")
+    args = parser.parse_args()
+    run_tiger_lb2(
+        wsi_filepath=Path(args.input_file),
+        output_json_file=Path(args.output_file)
+    )
+
+
+def run_tiger_lb2(wsi_filepath: Path, output_json_file: Path) -> None:
+    if not torch.cuda.is_available():
+        raise RuntimeError("run_tiger_lb2 requires CUDA to be available!")
+
+    print(f"Input WSI: {wsi_filepath}")
+    wsi_mri = rw.open_multiresolutionimage_image(wsi_filepath)
+
+    tils_score_writer = rw.TilsScoreWriter(output_json_file)
+    tils_score = tils_pipeline.run_tils_pipeline(wsi_mri)
+
+    print(f"Writing tils score to {output_json_file}")
+    tils_score_writer.set_tils_score(tils_score=tils_score)
+    tils_score_writer.save()
+
+
+if __name__ == "__main__":
+    tiger_lb2_cli()

models/gc_tiger_lb2/utils/TigerLB2Runner.py

@@ -0,0 +1,59 @@
+"""
+------------------------------------------------
+Mhub / DIAG - Run Module for Tiger LB2 Algorithm
+------------------------------------------------
+
+------------------------------------------------
+Author: Sil van de Leemput
+Email:  [email protected]
+------------------------------------------------
+"""
+from mhubio.core import Instance, InstanceData, IO, Module, ValueOutput, Meta, DataType, FileType
+
+from pathlib import Path
+import numpy as np
+import SimpleITK as sitk
+import torch
+
+import sys
+import json
+
+
+@ValueOutput.Name('til_score')
+@ValueOutput.Meta(Meta(key="value"))
+@ValueOutput.Label('TIL score')
+@ValueOutput.Type(int)
+@ValueOutput.Description('percentage of stromal area covered by tumour infiltrating lymphocytes. Values between 0 (percent) to 100 (percent).')
+class TilScoreOutput(ValueOutput):
+    pass
+
+
+class TigerLB2Runner(Module):
+
+    CLI_SCRIPT_PATH = Path(__file__).parent.parent / "scripts" / "tiger_lb2_cli.py"
+
+    @IO.Instance()
+    @IO.Input('in_data', 'tiff:mod=sm', the='input whole slide image Tiff')
+    @IO.Output('out_data', 'gc_tiger_lb2_til_score.json', 'json:model=TigerLB2TILScore', 'in_data', the='TIGER LB2 TIL score')
+    @IO.OutputData('til_score', TilScoreOutput, data='in_data', the='TIGER LB2 TIL score - percentage of stromal area covered by tumour infiltrating lymphocytes. Values between 0-100 (percent).')
+    def task(self, instance: Instance, in_data: InstanceData, out_data: InstanceData, til_score: TilScoreOutput) -> None:
+        if not torch.cuda.is_available():
+            raise NotImplementedError("TigerLB2Runner requires CUDA to be available!")
+
+        # Execute the Tiger LB2 Algorithm through a Python subprocess
+        self.subprocess(
+            [
+                sys.executable,
+                str(self.CLI_SCRIPT_PATH),
+                in_data.abspath,
+                out_data.abspath,
+            ]
+        )
+
+        if not Path(out_data.abspath).is_file():
+            raise OSError(f"Something went wrong when calling {self.CLI_SCRIPT_PATH} as a subprocess, couldn't find output file: {out_data.abspath}")
+
+        # export output til score as data as well
+        with open(out_data.abspath, "r") as f:
+            til_score.value = json.load(f)
+        assert isinstance(til_score.value, int)

models/gc_tiger_lb2/utils/__init__.py

@@ -0,0 +1 @@
+from .TigerLB2Runner import *